diff --git a/.gitignore b/.gitignore
index edc9aaa..f87f2f7 100644
--- a/.gitignore
+++ b/.gitignore
@@ -8,9 +8,8 @@ __pycache__/
 .venv/
 venv/
 
-# OpenWolf runtime
-.wolf/daemon.log
-.wolf/designqc-captures/
+# OpenWolf (all of it — local-only state)
+.wolf/
 
 # OS
 .DS_Store
diff --git a/.wolf/OPENWOLF.md b/.wolf/OPENWOLF.md
deleted file mode 100644
index aae2a47..0000000
--- a/.wolf/OPENWOLF.md
+++ /dev/null
@@ -1,135 +0,0 @@
-# OpenWolf Operating Protocol
-
-You are working in an OpenWolf-managed project. These rules apply every turn.
-
-## File Navigation
-
-1. Check `.wolf/anatomy.md` BEFORE reading any file. It has a 2-3 line description and token estimate for every file in the project.
-2. If the description in anatomy.md is sufficient for your task, do NOT read the full file.
-3. If a file is not in anatomy.md, search with Grep/Glob, then update anatomy.md with the new entry.
-
-## Code Generation
-
-1. Before generating code, read `.wolf/cerebrum.md` and respect every entry.
-2. Check the `## Do-Not-Repeat` section — these are past mistakes that must not recur.
-3. Follow all conventions in `## Key Learnings` and `## User Preferences`.
-
-## After Actions
-
-1. After every significant action, append a one-line entry to `.wolf/memory.md`:
-   `| HH:MM | description | file(s) | outcome | ~tokens |`
-2. After creating, deleting, or renaming files: update `.wolf/anatomy.md`.
-
-## Cerebrum Learning (MANDATORY — every session)
-
-OpenWolf's value comes from learning across sessions. You MUST update `.wolf/cerebrum.md` whenever you learn something useful. This is not optional.
-
-**Update `## User Preferences` when the user:**
-- Corrects your approach ("no, do it this way instead")
-- Expresses a style preference (naming, structure, formatting)
-- Shows a preferred workflow or tool choice
-- Rejects a suggestion — record what they preferred instead
-- Asks for more/less detail, verbosity, explanation
-
-**Update `## Key Learnings` when you discover:**
-- A project convention not obvious from the code (e.g., "tests go in __tests__/ not test/")
-- A framework-specific pattern this project uses
-- An API behavior that surprised you
-- A dependency quirk or version constraint
-- How modules connect or data flows through the system
-
-**Update `## Do-Not-Repeat` (with date) when:**
-- The user corrects a mistake you made
-- You try something that fails and find the right approach
-- You discover a gotcha that would trip up a fresh session
-
-**Update `## Decision Log` when:**
-- A significant architectural or technical choice is made
-- The user explains why they chose approach A over B
-- A trade-off is explicitly discussed
-
-**The bar is LOW.** If in doubt, add it. A cerebrum entry that's slightly redundant costs nothing. A missing entry means the next session repeats the same discovery process.
-
-## Bug Logging (MANDATORY)
-
-**Log a bug to `.wolf/buglog.json` whenever ANY of these happen:**
-- The user reports an error, bug, or problem
-- A test fails or a command produces an error
-- You fix something that was broken
-- You edit a file more than twice to get it right
-- An import, module, or dependency is missing or wrong
-- A runtime error, type error, or syntax error occurs
-- A build or lint command fails
-- A feature doesn't work as expected
-- You change error handling, try/catch blocks, or validation logic
-- The user says something "doesn't work", "is broken", or "shows wrong X"
-
-**Before fixing:** Read `.wolf/buglog.json` first — the fix may already be known.
-
-**After fixing:** ALWAYS append to `.wolf/buglog.json` with this structure:
-```json
-{
-  "id": "bug-NNN",
-  "timestamp": "ISO date",
-  "error_message": "exact error or user complaint",
-  "file": "file that was fixed",
-  "root_cause": "why it broke",
-  "fix": "what you changed to fix it",
-  "tags": ["relevant", "keywords"],
-  "related_bugs": [],
-  "occurrences": 1,
-  "last_seen": "ISO date"
-}
-```
-
-**The threshold is LOW.** When in doubt, log it. A false positive in the bug log costs nothing. A missed bug means repeating the same mistake later.
-
-## Token Discipline
-
-- Never re-read a file already read this session unless it was modified since.
-- Prefer anatomy.md descriptions over full file reads when possible.
-- Prefer targeted Grep over full file reads when searching for specific code.
-- If appending to a file, do not read the entire file first.
-
-## Design QC
-
-When the user asks you to check, evaluate, or improve the design/UI of their app:
-
-1. Run `openwolf designqc` via Bash to capture screenshots.
-   - The command auto-detects a running dev server, or starts one from package.json if needed
-   - Use `--url <url>` only if auto-detection fails
-   - The command saves compressed JPEG screenshots to `.wolf/designqc-captures/`
-   - Full pages are captured as sectioned viewport-height images (top, section2, ..., bottom)
-2. Read the captured screenshot images from `.wolf/designqc-captures/` using the Read tool.
-3. Evaluate the design against modern standards (Shadcn UI, Tailwind, clean React patterns):
-   - Spacing and whitespace consistency
-   - Typography hierarchy and readability
-   - Color contrast and accessibility (WCAG)
-   - Visual hierarchy and focal points
-   - Component consistency
-   - Whether the design looks "dull" or "white-coded" (generic, no personality)
-4. Provide specific, actionable feedback with fix suggestions.
-5. If the user approves, implement the fixes directly in their code.
-6. After fixes, re-run `openwolf designqc` to capture new screenshots and verify improvement.
-
-**Token awareness:** Each screenshot costs ~2500 tokens. The command compresses images (JPEG quality 70, max width 1200px) to minimize cost. For large apps, use `--routes / /specific-page` to limit captures.
-
-## Reframe — UI Framework Selection
-
-When the user asks to change, pick, migrate, or "reframe" their project's UI framework:
-
-1. Read `.wolf/reframe-frameworks.md` for the full framework knowledge base.
-2. Ask the user the decision questions from the file (current stack, priority, Tailwind usage, theme preference, app type). Stop early once the choice narrows to 1-2 options.
-3. Present a recommendation with reasoning based on the comparison matrix.
-4. Once the user confirms, use the selected framework's prompt from the file — **adapted to the actual project** using `.wolf/anatomy.md` for real file paths, routes, and components.
-5. Execute the migration: install dependencies, update config, refactor components.
-6. After migration, run `openwolf designqc` to verify the new look.
-
-**Do NOT read the entire reframe-frameworks.md into context upfront.** Read the decision questions and comparison matrix first (~50 lines). Only read the specific framework's prompt section after the user chooses.
-
-## Session End
-
-Before ending or when asked to wrap up:
-
-1. Write a session summary to `.wolf/memory.md`.
-2. Review the session: did you learn anything? Did the user correct you? Did you fix a bug? If yes, update `.wolf/cerebrum.md` and/or `.wolf/buglog.json`.
diff --git a/.wolf/anatomy.md b/.wolf/anatomy.md
deleted file mode 100644
index 25f15d5..0000000
--- a/.wolf/anatomy.md
+++ /dev/null
@@ -1,25 +0,0 @@
-# anatomy.md
-
-> Auto-maintained by OpenWolf. Last scanned: 2026-06-03T13:57:12.941Z
-> Files: 9 tracked | Anatomy hits: 0 | Misses: 0
-
-## ../../.claude/plans/
-
-- `in-the-example-folder-immutable-rossum.md` — Plan: PDF → static HTML/CSS site (poppler-utils) (~2113 tok)
-
-## ./
-
-- `.gitignore` — Git ignore rules (~55 tok)
-- `.python-version` (~2 tok)
-- `CLAUDE.md` — CLAUDE.md (~550 tok)
-- `main.py` — Convert every PDF in examples/ into a static HTML/CSS site under output/. (~2847 tok)
-- `pyproject.toml` — Python project configuration (~44 tok)
-- `README.md` — Project documentation (~909 tok)
-
-## .claude/
-
-- `settings.json` (~441 tok)
-
-## .claude/rules/
-
-- `openwolf.md` (~313 tok)
diff --git a/.wolf/buglog.json b/.wolf/buglog.json
deleted file mode 100644
index a11dde9..0000000
--- a/.wolf/buglog.json
+++ /dev/null
@@ -1,4 +0,0 @@
-{
-  "version": 1,
-  "bugs": []
-}
diff --git a/.wolf/cerebrum.md b/.wolf/cerebrum.md
deleted file mode 100644
index 13ee75f..0000000
--- a/.wolf/cerebrum.md
+++ /dev/null
@@ -1,25 +0,0 @@
-# Cerebrum
-
-> OpenWolf's learning memory. Updated automatically as the AI learns from interactions.
-> Do not edit manually unless correcting an error.
-> Last updated: 2026-06-03
-
-## User Preferences
-
-<!-- How the user likes things done. Code style, tools, patterns, communication. -->
-
-## Key Learnings
-
-- **Project:** netgazet — converts NETgazet print PDFs (InDesign-laid-out, ~A3, 16pp) into a static HTML/CSS site under `output/`. Entry point is `main.py`; runs via `python main.py` or `uv run python main.py`. Inputs live in `examples/`.
-- **Conversion approach:** page-as-JPEG via `pdftocairo -jpeg -singlefile -r 150` + responsive `img { max-width: 100% }`. `pdftohtml` was deliberately rejected because its complex-mode output is fixed-pixel and not mobile-responsive. Selectable text is provided as a `<details>` block per page from `pdftotext -layout`, split on form-feed (`\f`).
-- **`pdftocairo` filename quirk:** without `-singlefile` it appends `-<page>.jpg` to the output stem; with `-singlefile` it appends just `.jpg`. The script uses `-singlefile` per page so file paths are predictable.
-- **No third-party Python deps.** Conversion shells out via `subprocess.run([...], check=True)`; `pyproject.toml` keeps `dependencies = []`.
-
-## Do-Not-Repeat
-
-<!-- Mistakes made and corrected. Each entry prevents the same mistake recurring. -->
-<!-- Format: [YYYY-MM-DD] Description of what went wrong and what to do instead. -->
-
-## Decision Log
-
-<!-- Significant technical decisions with rationale. Why X was chosen over Y. -->
diff --git a/.wolf/config.json b/.wolf/config.json
deleted file mode 100644
index d2c76ae..0000000
--- a/.wolf/config.json
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-  "version": 1,
-  "openwolf": {
-    "enabled": true,
-    "anatomy": {
-      "auto_scan_on_init": true,
-      "rescan_interval_hours": 6,
-      "max_description_length": 100,
-      "max_files": 500,
-      "exclude_patterns": [
-        "node_modules",
-        ".git",
-        "dist",
-        "build",
-        ".wolf",
-        ".next",
-        ".nuxt",
-        "coverage",
-        "__pycache__",
-        ".cache",
-        "target",
-        ".vscode",
-        ".idea",
-        ".turbo",
-        ".vercel",
-        ".netlify",
-        ".output",
-        "*.min.js",
-        "*.min.css"
-      ]
-    },
-    "token_audit": {
-      "enabled": true,
-      "report_frequency": "weekly",
-      "waste_threshold_percent": 15,
-      "chars_per_token_code": 3.5,
-      "chars_per_token_prose": 4.0
-    },
-    "cron": {
-      "enabled": true,
-      "max_retry_attempts": 3,
-      "dead_letter_enabled": true,
-      "heartbeat_interval_minutes": 30,
-      "use_claude_p": true,
-      "api_key_env": null
-    },
-    "memory": {
-      "consolidation_after_days": 7,
-      "max_entries_before_consolidation": 200
-    },
-    "cerebrum": {
-      "max_tokens": 2000,
-      "reflection_frequency": "weekly"
-    },
-    "daemon": {
-      "port": 18790,
-      "log_level": "info"
-    },
-    "dashboard": {
-      "enabled": true,
-      "port": 18791
-    },
-    "designqc": {
-      "enabled": true,
-      "viewports": [
-        { "name": "desktop", "width": 1440, "height": 900 },
-        { "name": "mobile", "width": 375, "height": 812 }
-      ],
-      "max_screenshots": 6,
-      "chrome_path": null
-    }
-  }
-}
diff --git a/.wolf/cron-manifest.json b/.wolf/cron-manifest.json
deleted file mode 100644
index 7e2d7f3..0000000
--- a/.wolf/cron-manifest.json
+++ /dev/null
@@ -1,97 +0,0 @@
-{
-  "version": 1,
-  "tasks": [
-    {
-      "id": "anatomy-rescan",
-      "name": "Full anatomy rescan",
-      "schedule": "0 */6 * * *",
-      "description": "Re-scans project filesystem and reconciles anatomy.md",
-      "action": { "type": "scan_project" },
-      "retry": {
-        "max_attempts": 3,
-        "backoff": "exponential",
-        "base_delay_seconds": 30
-      },
-      "failsafe": {
-        "on_failure": "log_and_continue",
-        "alert_after_consecutive_failures": 2,
-        "dead_letter": true
-      },
-      "enabled": true
-    },
-    {
-      "id": "memory-consolidation",
-      "name": "Consolidate old memory",
-      "schedule": "0 2 * * *",
-      "description": "Compress memory.md entries older than 7 days",
-      "action": {
-        "type": "consolidate_memory",
-        "params": { "older_than_days": 7 }
-      },
-      "retry": {
-        "max_attempts": 2,
-        "backoff": "exponential",
-        "base_delay_seconds": 60
-      },
-      "failsafe": {
-        "on_failure": "skip_and_retry_next_cycle",
-        "dead_letter": false
-      },
-      "enabled": true
-    },
-    {
-      "id": "token-audit",
-      "name": "Token audit report",
-      "schedule": "0 0 * * 1",
-      "description": "Weekly waste pattern detection",
-      "action": { "type": "generate_token_report" },
-      "retry": {
-        "max_attempts": 2,
-        "backoff": "linear",
-        "base_delay_seconds": 60
-      },
-      "failsafe": { "on_failure": "log_and_continue", "dead_letter": true },
-      "enabled": true
-    },
-    {
-      "id": "cerebrum-reflection",
-      "name": "Cerebrum reflection",
-      "schedule": "0 3 * * 0",
-      "description": "Weekly AI review of cerebrum.md — prune stale entries, consolidate duplicates",
-      "action": {
-        "type": "ai_task",
-        "params": {
-          "prompt": "Review this cerebrum.md. Remove duplicate preferences (keep newer). Remove Do-Not-Repeat entries older than 90 days if no longer relevant. Consolidate Key Learnings that overlap. Keep the file under 2000 tokens. Return the cleaned file content only.",
-          "context_files": [".wolf/cerebrum.md"]
-        }
-      },
-      "retry": {
-        "max_attempts": 1,
-        "backoff": "none",
-        "base_delay_seconds": 0
-      },
-      "failsafe": { "on_failure": "log_and_continue", "dead_letter": false },
-      "enabled": true
-    },
-    {
-      "id": "project-suggestions",
-      "name": "AI suggestions",
-      "schedule": "0 4 * * 1",
-      "description": "Weekly AI analysis with project improvement suggestions",
-      "action": {
-        "type": "ai_task",
-        "params": {
-          "prompt": "Based on the recent memory entries and current project structure, provide: 1) Key achievements this week, 2) Code improvements to consider, 3) Logical next tasks, 4) Technical debt or risks. Be specific and actionable. Return as JSON: {achievements:[], improvements:[], next_tasks:[], risks:[]}",
-          "context_files": [".wolf/memory.md", ".wolf/anatomy.md"]
-        }
-      },
-      "retry": {
-        "max_attempts": 1,
-        "backoff": "none",
-        "base_delay_seconds": 0
-      },
-      "failsafe": { "on_failure": "log_and_continue", "dead_letter": false },
-      "enabled": true
-    }
-  ]
-}
diff --git a/.wolf/cron-state.json b/.wolf/cron-state.json
deleted file mode 100644
index d85cc62..0000000
--- a/.wolf/cron-state.json
+++ /dev/null
@@ -1,7 +0,0 @@
-{
-  "last_heartbeat": "2026-06-03T13:15:40.431Z",
-  "engine_status": "running",
-  "execution_log": [],
-  "dead_letter_queue": [],
-  "upcoming": []
-}
\ No newline at end of file
diff --git a/.wolf/designqc-report.json b/.wolf/designqc-report.json
deleted file mode 100644
index 8f658ee..0000000
--- a/.wolf/designqc-report.json
+++ /dev/null
@@ -1,6 +0,0 @@
-{
-  "captured_at": null,
-  "captures": [],
-  "total_size_kb": 0,
-  "estimated_tokens": 0
-}
\ No newline at end of file
diff --git a/.wolf/hooks/_session.json b/.wolf/hooks/_session.json
deleted file mode 100644
index d15a4f4..0000000
--- a/.wolf/hooks/_session.json
+++ /dev/null
@@ -1,39 +0,0 @@
-{
-  "session_id": "session-2026-06-03-1555",
-  "started": "2026-06-03T13:55:38.248Z",
-  "files_read": {
-    "/home/seppe4/vscode_projects/netgazet/output/index.html": {
-      "count": 1,
-      "tokens": 0,
-      "first_read": "2026-06-03T13:56:13.931Z"
-    },
-    "/home/seppe4/vscode_projects/netgazet/.gitignore": {
-      "count": 1,
-      "tokens": 0,
-      "first_read": "2026-06-03T13:57:08.826Z"
-    }
-  },
-  "files_written": [
-    {
-      "file": "/home/seppe4/vscode_projects/netgazet/README.md",
-      "action": "create",
-      "tokens": 1039,
-      "at": "2026-06-03T13:57:02.392Z"
-    },
-    {
-      "file": "/home/seppe4/vscode_projects/netgazet/.gitignore",
-      "action": "create",
-      "tokens": 59,
-      "at": "2026-06-03T13:57:12.946Z"
-    }
-  ],
-  "edit_counts": {
-    "README.md": 1,
-    ".gitignore": 1
-  },
-  "anatomy_hits": 0,
-  "anatomy_misses": 2,
-  "repeated_reads_warned": 0,
-  "cerebrum_warnings": 0,
-  "stop_count": 1
-}
\ No newline at end of file
diff --git a/.wolf/hooks/package.json b/.wolf/hooks/package.json
deleted file mode 100644
index 3dbc1ca..0000000
--- a/.wolf/hooks/package.json
+++ /dev/null
@@ -1,3 +0,0 @@
-{
-  "type": "module"
-}
diff --git a/.wolf/hooks/post-read.js b/.wolf/hooks/post-read.js
deleted file mode 100644
index 5d22fbb..0000000
--- a/.wolf/hooks/post-read.js
+++ /dev/null
@@ -1,69 +0,0 @@
-import * as path from "node:path";
-import { getWolfDir, ensureWolfDir, readJSON, writeJSON, readMarkdown, parseAnatomy, estimateTokens, readStdin, normalizePath } from "./shared.js";
-async function main() {
-    ensureWolfDir();
-    const wolfDir = getWolfDir();
-    const hooksDir = path.join(wolfDir, "hooks");
-    const sessionFile = path.join(hooksDir, "_session.json");
-    const raw = await readStdin();
-    let input;
-    try {
-        input = JSON.parse(raw);
-    }
-    catch {
-        process.exit(0);
-        return;
-    }
-    const filePath = input.tool_input?.file_path ?? input.tool_input?.path ?? "";
-    const content = input.tool_output?.content ?? "";
-    if (!filePath) {
-        process.exit(0);
-        return;
-    }
-    const normalizedFile = normalizePath(filePath);
-    // Skip tracking for .wolf/ internal files — consistent with pre-read
-    const projectDir = normalizePath(process.env.CLAUDE_PROJECT_DIR || process.cwd());
-    const relToProject = normalizedFile.startsWith(projectDir)
-        ? normalizedFile.slice(projectDir.length).replace(/^\//, "")
-        : "";
-    if (relToProject.startsWith(".wolf/") || relToProject.startsWith(".wolf\\")) {
-        process.exit(0);
-        return;
-    }
-    const ext = path.extname(filePath).toLowerCase();
-    const codeExts = new Set([".ts", ".js", ".tsx", ".jsx", ".py", ".rs", ".go", ".java", ".c", ".cpp", ".css", ".json", ".yaml", ".yml"]);
-    const proseExts = new Set([".md", ".txt", ".rst"]);
-    const type = codeExts.has(ext) ? "code" : proseExts.has(ext) ? "prose" : "mixed";
-    let tokens = content ? estimateTokens(content, type) : 0;
-    // Fallback: if tool_output had no content, use anatomy token estimate
-    if (tokens === 0) {
-        const anatomyContent = readMarkdown(path.join(wolfDir, "anatomy.md"));
-        const sections = parseAnatomy(anatomyContent);
-        for (const [sectionKey, entries] of sections) {
-            for (const entry of entries) {
-                const entryRelPath = normalizePath(path.join(sectionKey, entry.file));
-                if (normalizedFile.endsWith(entryRelPath) || normalizedFile.endsWith("/" + entryRelPath)) {
-                    tokens = entry.tokens;
-                    break;
-                }
-            }
-            if (tokens > 0)
-                break;
-        }
-    }
-    const session = readJSON(sessionFile, { files_read: {} });
-    if (session.files_read[normalizedFile]) {
-        session.files_read[normalizedFile].tokens = tokens;
-    }
-    else {
-        session.files_read[normalizedFile] = {
-            count: 1,
-            tokens,
-            first_read: new Date().toISOString(),
-        };
-    }
-    writeJSON(sessionFile, session);
-    process.exit(0);
-}
-main().catch(() => process.exit(0));
-//# sourceMappingURL=post-read.js.map
\ No newline at end of file
diff --git a/.wolf/hooks/post-write.js b/.wolf/hooks/post-write.js
deleted file mode 100644
index 9a5ce97..0000000
--- a/.wolf/hooks/post-write.js
+++ /dev/null
@@ -1,503 +0,0 @@
-import * as fs from "node:fs";
-import * as path from "node:path";
-import * as crypto from "node:crypto";
-import { getWolfDir, ensureWolfDir, readJSON, writeJSON, parseAnatomy, serializeAnatomy, extractDescription, estimateTokens, appendMarkdown, timeShort, readStdin, normalizePath } from "./shared.js";
-async function main() {
-    ensureWolfDir();
-    const wolfDir = getWolfDir();
-    const hooksDir = path.join(wolfDir, "hooks");
-    const sessionFile = path.join(hooksDir, "_session.json");
-    const projectRoot = process.env.CLAUDE_PROJECT_DIR || process.cwd();
-    const raw = await readStdin();
-    let input;
-    try {
-        input = JSON.parse(raw);
-    }
-    catch {
-        process.exit(0);
-        return;
-    }
-    const toolName = input.tool_name ?? "Write";
-    const filePath = input.tool_input?.file_path ?? input.tool_input?.path ?? "";
-    if (!filePath) {
-        process.exit(0);
-        return;
-    }
-    const absolutePath = path.isAbsolute(filePath) ? filePath : path.join(projectRoot, filePath);
-    // Skip processing for .wolf/ internal files to avoid slow self-referential updates
-    const relPath = normalizePath(path.relative(projectRoot, absolutePath));
-    if (relPath.startsWith(".wolf/")) {
-        process.exit(0);
-        return;
-    }
-    // Never track .env files in anatomy — they contain secrets
-    const baseName = path.basename(absolutePath);
-    if (baseName === ".env" || baseName.startsWith(".env.")) {
-        process.exit(0);
-        return;
-    }
-    const oldStr = input.tool_input?.old_string ?? "";
-    const newStr = input.tool_input?.new_string ?? "";
-    // 1. Update anatomy.md
-    try {
-        const anatomyPath = path.join(wolfDir, "anatomy.md");
-        let anatomyContent;
-        try {
-            anatomyContent = fs.readFileSync(anatomyPath, "utf-8");
-        }
-        catch {
-            anatomyContent = "# anatomy.md\n\n> Auto-maintained by OpenWolf.\n";
-        }
-        const sections = parseAnatomy(anatomyContent);
-        const relPathLocal = normalizePath(path.relative(projectRoot, absolutePath));
-        const dir = path.dirname(relPathLocal);
-        const fileName = path.basename(relPathLocal);
-        const sectionKey = dir === "." ? "./" : dir + "/";
-        let fileContent = "";
-        try {
-            fileContent = fs.readFileSync(absolutePath, "utf-8");
-        }
-        catch {
-            fileContent = input.tool_input?.content ?? "";
-        }
-        const desc = extractDescription(absolutePath).slice(0, 100);
-        const ext = path.extname(absolutePath).toLowerCase();
-        const codeExts = new Set([".ts", ".js", ".tsx", ".jsx", ".py", ".json", ".yaml", ".yml", ".css"]);
-        const proseExts = new Set([".md", ".txt", ".rst"]);
-        const type = codeExts.has(ext) ? "code" : proseExts.has(ext) ? "prose" : "mixed";
-        const tokens = estimateTokens(fileContent, type);
-        if (!sections.has(sectionKey))
-            sections.set(sectionKey, []);
-        const entries = sections.get(sectionKey);
-        const idx = entries.findIndex((e) => e.file === fileName);
-        if (idx !== -1) {
-            entries[idx] = { file: fileName, description: desc, tokens };
-        }
-        else {
-            entries.push({ file: fileName, description: desc, tokens });
-        }
-        let fileCount = 0;
-        for (const [, list] of sections)
-            fileCount += list.length;
-        const serialized = serializeAnatomy(sections, {
-            lastScanned: new Date().toISOString(),
-            fileCount,
-            hits: 0,
-            misses: 0,
-        });
-        const tmp = anatomyPath + "." + crypto.randomBytes(4).toString("hex") + ".tmp";
-        try {
-            fs.writeFileSync(tmp, serialized, "utf-8");
-            fs.renameSync(tmp, anatomyPath);
-        }
-        catch {
-            try {
-                fs.writeFileSync(anatomyPath, serialized, "utf-8");
-            }
-            catch { }
-            try {
-                fs.unlinkSync(tmp);
-            }
-            catch { }
-        }
-    }
-    catch { }
-    // 2. Append richer entry to memory.md
-    try {
-        const action = toolName === "Write" ? "Created" : toolName === "MultiEdit" ? "Multi-edited" : "Edited";
-        const relFile = normalizePath(path.relative(projectRoot, absolutePath));
-        const fileContent = input.tool_input?.content ?? "";
-        const ext = path.extname(absolutePath).toLowerCase();
-        const codeExts = new Set([".ts", ".js", ".tsx", ".jsx", ".py", ".json", ".yaml", ".yml", ".css"]);
-        const type = codeExts.has(ext) ? "code" : "mixed";
-        const writeTokens = estimateTokens(fileContent || newStr, type);
-        let changeDesc = "";
-        if (oldStr && newStr) {
-            changeDesc = summarizeEdit(oldStr, newStr, baseName);
-        }
-        const memoryPath = path.join(wolfDir, "memory.md");
-        const outcome = changeDesc || "—";
-        appendMarkdown(memoryPath, `| ${timeShort()} | ${action} ${relFile} | ${outcome} | ~${writeTokens} |\n`);
-    }
-    catch { }
-    // 3. Record in session tracker + track edit counts
-    try {
-        const session = readJSON(sessionFile, { files_written: [], edit_counts: {} });
-        if (!session.edit_counts)
-            session.edit_counts = {};
-        const normalizedFile = normalizePath(filePath);
-        const action = toolName === "Write" ? "create" : "edit";
-        const fileContent = input.tool_input?.content ?? "";
-        const tokens = estimateTokens(fileContent || newStr, "code");
-        session.files_written.push({
-            file: normalizedFile,
-            action,
-            tokens,
-            at: new Date().toISOString(),
-        });
-        const editKey = normalizePath(path.relative(projectRoot, absolutePath));
-        session.edit_counts[editKey] = (session.edit_counts[editKey] || 0) + 1;
-        writeJSON(sessionFile, session);
-        if (session.edit_counts[editKey] >= 3) {
-            process.stderr.write(`⚠️ OpenWolf: ${baseName} has been edited ${session.edit_counts[editKey]} times this session. If you're fixing a bug, remember to log it to .wolf/buglog.json.\n`);
-        }
-    }
-    catch { }
-    // 4. Auto-detect bug-fix patterns and log them
-    try {
-        if (oldStr && newStr) {
-            autoDetectBugFix(wolfDir, absolutePath, projectRoot, oldStr, newStr);
-        }
-    }
-    catch { }
-    process.exit(0);
-}
-// ─── Edit Summarizer ─────────────────────────────────────────────
-function summarizeEdit(oldStr, newStr, filename) {
-    const oldLines = oldStr.split("\n");
-    const newLines = newStr.split("\n");
-    const oldCount = oldLines.length;
-    const newCount = newLines.length;
-    const ext = path.extname(filename).toLowerCase();
-    // --- Structural fixes ---
-    if (newStr.includes("try") && newStr.includes("catch") && !oldStr.includes("catch")) {
-        return "added error handling";
-    }
-    if (newStr.includes("?.") && !oldStr.includes("?."))
-        return "added optional chaining";
-    if (newStr.includes("?? ") && !oldStr.includes("?? "))
-        return "added nullish coalescing";
-    // --- Deleted code ---
-    if (!newStr.trim() || newStr.trim().length < oldStr.trim().length * 0.2) {
-        return `removed ${oldCount} lines`;
-    }
-    // --- Import changes ---
-    const oldImports = oldLines.filter(l => /^\s*(import|require|use |from )/.test(l)).length;
-    const newImports = newLines.filter(l => /^\s*(import|require|use |from )/.test(l)).length;
-    if (newImports > oldImports && Math.abs(newCount - oldCount) <= newImports - oldImports + 1) {
-        return `added ${newImports - oldImports} import(s)`;
-    }
-    // --- Value/string replacement (common bug fix: wrong value) ---
-    if (oldCount === 1 && newCount === 1) {
-        const o = oldStr.trim();
-        const n = newStr.trim();
-        // String literal change
-        const oStr = o.match(/['"`]([^'"`]+)['"`]/);
-        const nStr = n.match(/['"`]([^'"`]+)['"`]/);
-        if (oStr && nStr && oStr[1] !== nStr[1]) {
-            return `"${oStr[1].slice(0, 25)}" → "${nStr[1].slice(0, 25)}"`;
-        }
-        // Number change
-        const oNum = o.match(/\b(\d+\.?\d*)\b/);
-        const nNum = n.match(/\b(\d+\.?\d*)\b/);
-        if (oNum && nNum && oNum[1] !== nNum[1] && o.replace(oNum[1], "") === n.replace(nNum[1], "")) {
-            return `${oNum[1]} → ${nNum[1]}`;
-        }
-        return "inline fix";
-    }
-    // --- Method/function call changes ---
-    const oldCalls = extractCalls(oldStr);
-    const newCalls = extractCalls(newStr);
-    const addedCalls = newCalls.filter(c => !oldCalls.includes(c));
-    const removedCalls = oldCalls.filter(c => !newCalls.includes(c));
-    if (removedCalls.length === 1 && addedCalls.length === 1) {
-        return `${removedCalls[0]}() → ${addedCalls[0]}()`;
-    }
-    // --- CSS/style changes ---
-    if (ext === ".css" || ext === ".scss" || ext === ".vue" || ext === ".tsx" || ext === ".jsx") {
-        const oldProps = (oldStr.match(/[\w-]+\s*:/g) || []).map(p => p.replace(/\s*:/, ""));
-        const newProps = (newStr.match(/[\w-]+\s*:/g) || []).map(p => p.replace(/\s*:/, ""));
-        const changed = newProps.filter(p => !oldProps.includes(p));
-        if (changed.length > 0 && changed.length <= 3) {
-            return `CSS: ${changed.join(", ")}`;
-        }
-    }
-    // --- Condition changes ---
-    const oldConds = (oldStr.match(/if\s*\(([^)]+)\)/g) || []);
-    const newConds = (newStr.match(/if\s*\(([^)]+)\)/g) || []);
-    if (newConds.length > oldConds.length) {
-        return `added ${newConds.length - oldConds.length} condition(s)`;
-    }
-    // --- Function modified ---
-    const fnMatch = newStr.match(/(?:function|def|fn|func|async\s+function)\s+(\w+)/);
-    if (fnMatch) {
-        return `modified ${fnMatch[1]}()`;
-    }
-    // --- Class/method context ---
-    const methodMatch = newStr.match(/(?:public|private|protected)?\s*(?:async\s+)?(\w+)\s*\([^)]*\)\s*[:{]/);
-    if (methodMatch) {
-        return `modified ${methodMatch[1]}()`;
-    }
-    // --- Size-based fallback ---
-    if (newCount > oldCount + 5)
-        return `expanded (+${newCount - oldCount} lines)`;
-    if (oldCount > newCount + 5)
-        return `reduced (-${oldCount - newCount} lines)`;
-    return `${oldCount}→${newCount} lines`;
-}
-function extractCalls(code) {
-    return [...new Set((code.match(/(\w+)\s*\(/g) || [])
-            .map(m => m.match(/(\w+)/)?.[1] || "")
-            .filter(n => n.length > 2 && !["if", "for", "while", "switch", "catch", "function", "return", "new", "typeof", "instanceof", "const", "let", "var"].includes(n)))];
-}
-// ─── Auto Bug Detection ──────────────────────────────────────────
-function autoDetectBugFix(wolfDir, absolutePath, projectRoot, oldStr, newStr) {
-    const bugLogPath = path.join(wolfDir, "buglog.json");
-    const bugLog = readJSON(bugLogPath, { version: 1, bugs: [] });
-    const relFile = normalizePath(path.relative(projectRoot, absolutePath));
-    const basename = path.basename(absolutePath);
-    const ext = path.extname(basename).toLowerCase();
-    // Detect what kind of fix this is
-    const detection = detectFixPattern(oldStr, newStr, ext);
-    if (!detection)
-        return;
-    // Check for recent duplicate (same file + same category within 5 min)
-    const recentDupe = bugLog.bugs.find(b => {
-        if (path.basename(b.file) !== basename)
-            return false;
-        if (!b.tags.includes("auto-detected"))
-            return false;
-        if (!b.tags.includes(detection.category))
-            return false;
-        const bugTime = new Date(b.last_seen).getTime();
-        return (Date.now() - bugTime) < 5 * 60 * 1000;
-    });
-    if (recentDupe) {
-        recentDupe.occurrences++;
-        recentDupe.last_seen = new Date().toISOString();
-        // Append additional context
-        if (detection.context && !recentDupe.fix.includes(detection.context)) {
-            recentDupe.fix += ` | Also: ${detection.context}`;
-        }
-        writeJSON(bugLogPath, bugLog);
-        return;
-    }
-    const nextId = `bug-${String(bugLog.bugs.length + 1).padStart(3, "0")}`;
-    bugLog.bugs.push({
-        id: nextId,
-        timestamp: new Date().toISOString(),
-        error_message: detection.summary,
-        file: relFile,
-        root_cause: detection.rootCause,
-        fix: detection.fix,
-        tags: ["auto-detected", detection.category, ext.replace(".", "") || "unknown"],
-        related_bugs: [],
-        occurrences: 1,
-        last_seen: new Date().toISOString(),
-    });
-    writeJSON(bugLogPath, bugLog);
-}
-function detectFixPattern(oldStr, newStr, ext) {
-    const oldLines = oldStr.split("\n");
-    const newLines = newStr.split("\n");
-    // --- Error handling added ---
-    if (newStr.includes("catch") && !oldStr.includes("catch")) {
-        const fn = newStr.match(/(?:function|def|async)\s+(\w+)/)?.[1] || "unknown";
-        return {
-            category: "error-handling",
-            summary: `Missing error handling in ${path.basename(fn)}`,
-            rootCause: "Code path had no error handling — exceptions would propagate uncaught",
-            fix: `Added try/catch block`,
-            context: extractChangedLines(oldStr, newStr),
-        };
-    }
-    // --- Null/undefined safety ---
-    if ((newStr.includes("?.") && !oldStr.includes("?.")) ||
-        (newStr.includes("?? ") && !oldStr.includes("?? ")) ||
-        (/!==?\s*(null|undefined)/.test(newStr) && !/!==?\s*(null|undefined)/.test(oldStr))) {
-        return {
-            category: "null-safety",
-            summary: `Null/undefined access in ${path.basename(path.basename(""))}`,
-            rootCause: "Property access on potentially null/undefined value",
-            fix: `Added null safety (optional chaining or null check)`,
-            context: extractChangedLines(oldStr, newStr),
-        };
-    }
-    // --- Guard clause / early return added ---
-    if (/if\s*\([^)]*\)\s*(return|throw|continue|break)/.test(newStr) &&
-        !/if\s*\([^)]*\)\s*(return|throw|continue|break)/.test(oldStr)) {
-        const condition = newStr.match(/if\s*\(([^)]+)\)/)?.[1]?.trim().slice(0, 60) || "condition";
-        return {
-            category: "guard-clause",
-            summary: `Missing guard clause`,
-            rootCause: `No early return/throw for edge case: ${condition}`,
-            fix: `Added guard clause: if (${condition.slice(0, 40)})`,
-        };
-    }
-    // --- Wrong value / string fix (very common bug) ---
-    if (oldLines.length <= 3 && newLines.length <= 3) {
-        const oldJoined = oldStr.trim();
-        const newJoined = newStr.trim();
-        // String literal changed
-        const oStrs = oldJoined.match(/['"`]([^'"`]{2,})['"`]/g) || [];
-        const nStrs = newJoined.match(/['"`]([^'"`]{2,})['"`]/g) || [];
-        if (oStrs.length > 0 && nStrs.length > 0) {
-            for (let i = 0; i < Math.min(oStrs.length, nStrs.length); i++) {
-                if (oStrs[i] !== nStrs[i]) {
-                    return {
-                        category: "wrong-value",
-                        summary: `Incorrect value in code`,
-                        rootCause: `Had ${oStrs[i].slice(0, 50)}`,
-                        fix: `Changed to ${nStrs[i].slice(0, 50)}`,
-                    };
-                }
-            }
-        }
-        // Variable name / method call changed
-        const oldTokens = tokenizeCode(oldJoined);
-        const newTokens = tokenizeCode(newJoined);
-        const changed = [];
-        for (let i = 0; i < Math.min(oldTokens.length, newTokens.length); i++) {
-            if (oldTokens[i] !== newTokens[i]) {
-                changed.push([oldTokens[i], newTokens[i]]);
-            }
-        }
-        if (changed.length === 1 && changed[0][0].length > 2) {
-            return {
-                category: "wrong-reference",
-                summary: `Wrong reference: ${changed[0][0]} should be ${changed[0][1]}`,
-                rootCause: `Used "${changed[0][0]}" instead of "${changed[0][1]}"`,
-                fix: `Changed ${changed[0][0]} → ${changed[0][1]}`,
-            };
-        }
-    }
-    // --- Logic fix (condition changed) ---
-    const oldCond = oldStr.match(/if\s*\(([^)]+)\)/)?.[1];
-    const newCond = newStr.match(/if\s*\(([^)]+)\)/)?.[1];
-    if (oldCond && newCond && oldCond !== newCond && oldLines.length <= 5) {
-        return {
-            category: "logic-fix",
-            summary: `Wrong condition in logic`,
-            rootCause: `Condition was: if (${oldCond.slice(0, 50)})`,
-            fix: `Changed to: if (${newCond.slice(0, 50)})`,
-        };
-    }
-    // --- Operator fix (=== vs ==, > vs >=, etc.) ---
-    const opChange = findOperatorChange(oldStr, newStr);
-    if (opChange) {
-        return {
-            category: "operator-fix",
-            summary: `Wrong operator: ${opChange.old} should be ${opChange.new}`,
-            rootCause: `Used "${opChange.old}" instead of "${opChange.new}"`,
-            fix: `Changed operator ${opChange.old} → ${opChange.new}`,
-        };
-    }
-    // --- Missing import/require ---
-    const oldImports = new Set((oldStr.match(/(?:import|require)\s*\(?['"]([^'"]+)['"]\)?/g) || []).map(m => m));
-    const newImports = (newStr.match(/(?:import|require)\s*\(?['"]([^'"]+)['"]\)?/g) || []);
-    const addedImports = newImports.filter(i => !oldImports.has(i));
-    if (addedImports.length > 0 && newLines.length - oldLines.length <= addedImports.length + 2) {
-        const modules = addedImports.map(i => i.match(/['"]([^'"]+)['"]/)?.[1] || "").filter(Boolean);
-        return {
-            category: "missing-import",
-            summary: `Missing import: ${modules.join(", ")}`,
-            rootCause: `Module(s) not imported: ${modules.join(", ")}`,
-            fix: `Added import(s) for ${modules.join(", ")}`,
-        };
-    }
-    // --- Return value fix ---
-    const oldReturn = oldStr.match(/return\s+(.+)/)?.[1]?.trim();
-    const newReturn = newStr.match(/return\s+(.+)/)?.[1]?.trim();
-    if (oldReturn && newReturn && oldReturn !== newReturn && oldLines.length <= 5) {
-        return {
-            category: "return-value",
-            summary: `Wrong return value`,
-            rootCause: `Was returning: ${oldReturn.slice(0, 50)}`,
-            fix: `Now returns: ${newReturn.slice(0, 50)}`,
-        };
-    }
-    // --- Async/await fix ---
-    if (newStr.includes("await ") && !oldStr.includes("await ")) {
-        return {
-            category: "async-fix",
-            summary: `Missing await`,
-            rootCause: `Async call without await — returned Promise instead of value`,
-            fix: `Added await to async call`,
-            context: extractChangedLines(oldStr, newStr),
-        };
-    }
-    if (newStr.includes("async ") && !oldStr.includes("async ")) {
-        return {
-            category: "async-fix",
-            summary: `Function not marked async`,
-            rootCause: `Function uses await but wasn't declared async`,
-            fix: `Added async modifier`,
-        };
-    }
-    // --- Type annotation/cast fix ---
-    if (ext === ".ts" || ext === ".tsx") {
-        if ((newStr.includes(" as ") && !oldStr.includes(" as ")) ||
-            (newStr.includes(": ") && !oldStr.includes(": ") && oldLines.length <= 3)) {
-            return {
-                category: "type-fix",
-                summary: `Type error`,
-                rootCause: `Missing or incorrect type annotation`,
-                fix: `Added type assertion/annotation`,
-                context: extractChangedLines(oldStr, newStr),
-            };
-        }
-    }
-    // --- CSS/style fix ---
-    if (ext === ".css" || ext === ".scss" || ext === ".vue" || ext === ".tsx" || ext === ".jsx") {
-        const oldProps = extractCSSProps(oldStr);
-        const newProps = extractCSSProps(newStr);
-        const changedProps = [...newProps.entries()].filter(([k, v]) => oldProps.get(k) !== v && oldProps.has(k));
-        if (changedProps.length > 0 && changedProps.length <= 3) {
-            const desc = changedProps.map(([k, v]) => `${k}: ${oldProps.get(k)} → ${v}`).join("; ");
-            return {
-                category: "style-fix",
-                summary: `CSS fix: ${changedProps.map(([k]) => k).join(", ")}`,
-                rootCause: desc,
-                fix: `Changed ${desc}`,
-            };
-        }
-    }
-    // --- Significant diff (catch-all for substantial edits) ---
-    const diffRatio = Math.abs(newStr.length - oldStr.length) / Math.max(oldStr.length, 1);
-    if (diffRatio > 0.3 && oldLines.length >= 3 && newLines.length >= 3) {
-        // Only log if there's meaningful structural change, not just additions
-        const removedLines = oldLines.filter(l => l.trim() && !newLines.some(nl => nl.trim() === l.trim()));
-        if (removedLines.length >= 2) {
-            return {
-                category: "refactor",
-                summary: `Significant refactor of ${path.basename("")}`,
-                rootCause: `${removedLines.length} lines replaced/restructured`,
-                fix: `Rewrote ${oldLines.length}→${newLines.length} lines (${removedLines.length} removed)`,
-                context: removedLines.slice(0, 2).map(l => l.trim().slice(0, 50)).join("; "),
-            };
-        }
-    }
-    return null;
-}
-function extractChangedLines(oldStr, newStr) {
-    const oldLines = new Set(oldStr.split("\n").map(l => l.trim()).filter(Boolean));
-    const newLines = newStr.split("\n").map(l => l.trim()).filter(Boolean);
-    const added = newLines.filter(l => !oldLines.has(l));
-    return added.slice(0, 2).map(l => l.slice(0, 60)).join("; ");
-}
-function tokenizeCode(code) {
-    return code.replace(/[^\w$]/g, " ").split(/\s+/).filter(t => t.length > 0);
-}
-function findOperatorChange(oldStr, newStr) {
-    const operators = ["===", "!==", "==", "!=", ">=", "<=", ">>", "<<", "&&", "||", "??"];
-    for (const op of operators) {
-        if (oldStr.includes(op) && !newStr.includes(op)) {
-            for (const op2 of operators) {
-                if (op2 !== op && newStr.includes(op2) && !oldStr.includes(op2)) {
-                    return { old: op, new: op2 };
-                }
-            }
-        }
-    }
-    return null;
-}
-function extractCSSProps(code) {
-    const props = new Map();
-    const matches = code.matchAll(/([\w-]+)\s*:\s*([^;}\n]+)/g);
-    for (const m of matches) {
-        props.set(m[1].trim(), m[2].trim());
-    }
-    return props;
-}
-main().catch(() => process.exit(0));
-//# sourceMappingURL=post-write.js.map
\ No newline at end of file
diff --git a/.wolf/hooks/pre-read.js b/.wolf/hooks/pre-read.js
deleted file mode 100644
index 6ba67d0..0000000
--- a/.wolf/hooks/pre-read.js
+++ /dev/null
@@ -1,80 +0,0 @@
-import * as path from "node:path";
-import { getWolfDir, ensureWolfDir, readJSON, writeJSON, readMarkdown, parseAnatomy, readStdin, normalizePath } from "./shared.js";
-async function main() {
-    ensureWolfDir();
-    const wolfDir = getWolfDir();
-    const hooksDir = path.join(wolfDir, "hooks");
-    const sessionFile = path.join(hooksDir, "_session.json");
-    const raw = await readStdin();
-    let input;
-    try {
-        input = JSON.parse(raw);
-    }
-    catch {
-        process.exit(0);
-        return;
-    }
-    const filePath = input.tool_input?.file_path ?? input.tool_input?.path ?? "";
-    if (!filePath) {
-        process.exit(0);
-        return;
-    }
-    const normalizedFile = normalizePath(filePath);
-    // Skip tracking for .wolf/ internal files — they're infrastructure, not project files.
-    // Counting them inflates anatomy miss rates since .wolf/ is excluded from anatomy scanning.
-    const projectDir = normalizePath(process.env.CLAUDE_PROJECT_DIR || process.cwd());
-    const relToProject = normalizedFile.startsWith(projectDir)
-        ? normalizedFile.slice(projectDir.length).replace(/^\//, "")
-        : "";
-    if (relToProject.startsWith(".wolf/") || relToProject.startsWith(".wolf\\")) {
-        process.exit(0);
-        return;
-    }
-    const session = readJSON(sessionFile, {
-        session_id: "", files_read: {}, anatomy_hits: 0, anatomy_misses: 0,
-        repeated_reads_warned: 0,
-    });
-    // Check if already read this session
-    if (session.files_read[normalizedFile]) {
-        const prev = session.files_read[normalizedFile];
-        process.stderr.write(`⚡ OpenWolf: ${path.basename(normalizedFile)} was already read this session (~${prev.tokens} tokens). Consider using your existing knowledge of this file.\n`);
-        session.files_read[normalizedFile].count++;
-        session.repeated_reads_warned++;
-        writeJSON(sessionFile, session);
-        process.exit(0);
-        return;
-    }
-    // Check anatomy.md for this file
-    const anatomyContent = readMarkdown(path.join(wolfDir, "anatomy.md"));
-    const sections = parseAnatomy(anatomyContent);
-    let found = false;
-    for (const [sectionKey, entries] of sections) {
-        for (const entry of entries) {
-            // Build the full relative path from the section key + filename for accurate matching
-            const entryRelPath = normalizePath(path.join(sectionKey, entry.file));
-            if (normalizedFile.endsWith(entryRelPath) || normalizedFile.endsWith("/" + entryRelPath)) {
-                process.stderr.write(`📋 OpenWolf anatomy: ${entry.file} — ${entry.description} (~${entry.tokens} tok)\n`);
-                found = true;
-                break;
-            }
-        }
-        if (found)
-            break;
-    }
-    if (found) {
-        session.anatomy_hits++;
-    }
-    else {
-        session.anatomy_misses++;
-    }
-    // Record initial read entry (tokens will be updated in post-read)
-    session.files_read[normalizedFile] = {
-        count: 1,
-        tokens: 0,
-        first_read: new Date().toISOString(),
-    };
-    writeJSON(sessionFile, session);
-    process.exit(0);
-}
-main().catch(() => process.exit(0));
-//# sourceMappingURL=pre-read.js.map
\ No newline at end of file
diff --git a/.wolf/hooks/pre-write.js b/.wolf/hooks/pre-write.js
deleted file mode 100644
index 2e84303..0000000
--- a/.wolf/hooks/pre-write.js
+++ /dev/null
@@ -1,121 +0,0 @@
-import * as fs from "node:fs";
-import * as path from "node:path";
-import { getWolfDir, ensureWolfDir, readJSON, readMarkdown, readStdin } from "./shared.js";
-async function main() {
-    ensureWolfDir();
-    const wolfDir = getWolfDir();
-    const raw = await readStdin();
-    let input;
-    try {
-        input = JSON.parse(raw);
-    }
-    catch {
-        process.exit(0);
-        return;
-    }
-    // For Edit tool, the meaningful content is old_string + new_string
-    const content = input.tool_input?.content ?? "";
-    const oldStr = input.tool_input?.old_string ?? "";
-    const newStr = input.tool_input?.new_string ?? "";
-    const filePath = input.tool_input?.file_path ?? input.tool_input?.path ?? "";
-    const allContent = [content, oldStr, newStr].join("\n");
-    if (!allContent.trim()) {
-        process.exit(0);
-        return;
-    }
-    // 1. Cerebrum Do-Not-Repeat check
-    checkCerebrum(wolfDir, allContent);
-    // 2. Bug log: search for similar past bugs when editing code
-    // This fires when Claude is about to edit a file — if the edit looks like a fix
-    // (changing error handling, modifying catch blocks, etc.), check the bug log
-    if (filePath && (oldStr || content)) {
-        checkBugLog(wolfDir, filePath, oldStr, newStr, content);
-    }
-    process.exit(0);
-}
-function checkCerebrum(wolfDir, content) {
-    const cerebrumContent = readMarkdown(path.join(wolfDir, "cerebrum.md"));
-    const doNotRepeatSection = cerebrumContent.split("## Do-Not-Repeat")[1];
-    if (!doNotRepeatSection)
-        return;
-    const entries = doNotRepeatSection.split("## ")[0];
-    const lines = entries.split("\n").filter((l) => l.trim().startsWith("[") || l.trim().startsWith("-"));
-    for (const line of lines) {
-        const trimmed = line.trim().replace(/^[-*]\s*/, "").replace(/^\[[\d-]+\]\s*/, "");
-        if (!trimmed)
-            continue;
-        const patterns = [];
-        const quotedMatches = trimmed.match(/"([^"]+)"/g) || trimmed.match(/'([^']+)'/g) || trimmed.match(/`([^`]+)`/g);
-        if (quotedMatches) {
-            for (const qm of quotedMatches) {
-                patterns.push(qm.replace(/["'`]/g, ""));
-            }
-        }
-        const neverMatch = trimmed.match(/(?:never use|avoid|don't use|do not use)\s+(\w+)/i);
-        if (neverMatch)
-            patterns.push(neverMatch[1]);
-        for (const pattern of patterns) {
-            try {
-                const regex = new RegExp(`\\b${pattern.replace(/[.*+?^${}()|[\]\\]/g, "\\$&")}\\b`, "i");
-                if (regex.test(content)) {
-                    process.stderr.write(`⚠️ OpenWolf cerebrum warning: "${trimmed}" — check your code before proceeding.\n`);
-                }
-            }
-            catch { }
-        }
-    }
-}
-// Common words that appear in most code — must be excluded from similarity matching
-const STOP_WORDS = new Set([
-    "error", "function", "return", "const", "this", "that", "with", "from",
-    "import", "export", "class", "interface", "type", "undefined", "null",
-    "true", "false", "string", "number", "object", "array", "value",
-    "file", "path", "name", "data", "response", "request", "result",
-    "should", "must", "does", "have", "been", "will", "would", "could",
-    "when", "then", "else", "each", "some", "every", "only",
-]);
-function checkBugLog(wolfDir, filePath, oldStr, newStr, content) {
-    const bugLogPath = path.join(wolfDir, "buglog.json");
-    if (!fs.existsSync(bugLogPath))
-        return;
-    const bugLog = readJSON(bugLogPath, { version: 1, bugs: [] });
-    if (bugLog.bugs.length === 0)
-        return;
-    const basename = path.basename(filePath);
-    // ONLY surface bugs that match the SAME file being edited.
-    // Cross-file matching is too noisy and risks misdirecting Claude.
-    const fileMatches = bugLog.bugs.filter(b => {
-        const bugBasename = path.basename(b.file);
-        return bugBasename === basename;
-    });
-    if (fileMatches.length === 0)
-        return;
-    // Further filter: require tag or error_message overlap with the edit content
-    const editText = (oldStr + " " + newStr + " " + content).toLowerCase();
-    const editTokens = tokenize(editText);
-    const relevant = fileMatches.filter(bug => {
-        // Check if any bug tag appears in the edit content
-        const tagHit = bug.tags.some(t => editText.includes(t.toLowerCase()));
-        if (tagHit)
-            return true;
-        // Check meaningful word overlap (excluding stop words)
-        const bugTokens = tokenize(bug.error_message + " " + bug.root_cause);
-        const overlap = [...editTokens].filter(t => bugTokens.has(t));
-        // Require at least 3 meaningful overlapping words
-        return overlap.length >= 3;
-    });
-    if (relevant.length === 0)
-        return;
-    // Surface as a FYI, not a directive — Claude should evaluate, not blindly apply
-    process.stderr.write(`📋 OpenWolf buglog: ${relevant.length} past bug(s) found for ${basename} — review for context, do NOT apply blindly:\n`);
-    for (const bug of relevant.slice(0, 2)) {
-        process.stderr.write(`   [${bug.id}] "${bug.error_message.slice(0, 70)}"\n   Cause: ${bug.root_cause.slice(0, 80)}\n   Fix: ${bug.fix.slice(0, 80)}\n`);
-    }
-}
-function tokenize(text) {
-    return new Set(text.replace(/[^\w\s]/g, " ").split(/\s+/)
-        .filter(w => w.length > 3 && !STOP_WORDS.has(w.toLowerCase()))
-        .map(w => w.toLowerCase()));
-}
-main().catch(() => process.exit(0));
-//# sourceMappingURL=pre-write.js.map
\ No newline at end of file
diff --git a/.wolf/hooks/session-start.js b/.wolf/hooks/session-start.js
deleted file mode 100644
index 7da38f3..0000000
--- a/.wolf/hooks/session-start.js
+++ /dev/null
@@ -1,77 +0,0 @@
-import * as fs from "node:fs";
-import * as path from "node:path";
-import { getWolfDir, ensureWolfDir, writeJSON, appendMarkdown, readJSON, timestamp, timeShort } from "./shared.js";
-async function main() {
-    ensureWolfDir();
-    const wolfDir = getWolfDir();
-    // Clean up stale .tmp files left from failed atomic writes
-    try {
-        const files = fs.readdirSync(wolfDir);
-        for (const f of files) {
-            if (f.endsWith(".tmp")) {
-                try {
-                    fs.unlinkSync(path.join(wolfDir, f));
-                }
-                catch { }
-            }
-        }
-    }
-    catch { }
-    const hooksDir = path.join(wolfDir, "hooks");
-    const sessionFile = path.join(hooksDir, "_session.json");
-    const now = new Date();
-    const sessionId = `session-${now.toISOString().slice(0, 10)}-${String(now.getHours()).padStart(2, "0")}${String(now.getMinutes()).padStart(2, "0")}`;
-    // Create fresh session state
-    writeJSON(sessionFile, {
-        session_id: sessionId,
-        started: timestamp(),
-        files_read: {},
-        files_written: [],
-        edit_counts: {},
-        anatomy_hits: 0,
-        anatomy_misses: 0,
-        repeated_reads_warned: 0,
-        cerebrum_warnings: 0,
-        stop_count: 0,
-    });
-    // Append session header to memory.md
-    const memoryPath = path.join(wolfDir, "memory.md");
-    const header = `\n## Session: ${now.toISOString().slice(0, 10)} ${timeShort()}\n\n| Time | Action | File(s) | Outcome | ~Tokens |\n|------|--------|---------|---------|--------|\n`;
-    appendMarkdown(memoryPath, header);
-    // Check cerebrum freshness — remind Claude to learn
-    try {
-        const cerebrumPath = path.join(wolfDir, "cerebrum.md");
-        const cerebrumContent = fs.readFileSync(cerebrumPath, "utf-8");
-        const stat = fs.statSync(cerebrumPath);
-        const daysSinceUpdate = (Date.now() - stat.mtimeMs) / (1000 * 60 * 60 * 24);
-        // Count actual entries (non-comment, non-empty lines in content sections)
-        const entryLines = cerebrumContent.split("\n").filter(l => {
-            const t = l.trim();
-            return t.startsWith("- ") || t.startsWith("* ") || (t.startsWith("[") && t.includes("]"));
-        });
-        if (entryLines.length < 3) {
-            process.stderr.write(`💡 OpenWolf: cerebrum.md has only ${entryLines.length} entries. Learn from this session — record user preferences, project conventions, and mistakes to .wolf/cerebrum.md.\n`);
-        }
-        else if (daysSinceUpdate > 3) {
-            process.stderr.write(`💡 OpenWolf: cerebrum.md hasn't been updated in ${Math.floor(daysSinceUpdate)} days. Look for opportunities to add learnings this session.\n`);
-        }
-    }
-    catch { }
-    // Check buglog — remind if empty
-    try {
-        const buglogPath = path.join(wolfDir, "buglog.json");
-        const buglog = readJSON(buglogPath, { bugs: [] });
-        if (buglog.bugs.length === 0) {
-            process.stderr.write(`📋 OpenWolf: buglog.json is empty. If you encounter or fix any bugs, errors, or failed tests this session, log them to .wolf/buglog.json.\n`);
-        }
-    }
-    catch { }
-    // Increment total_sessions in token-ledger
-    const ledgerPath = path.join(wolfDir, "token-ledger.json");
-    const ledger = readJSON(ledgerPath, { version: 1, lifetime: { total_sessions: 0 } });
-    ledger.lifetime.total_sessions++;
-    writeJSON(ledgerPath, ledger);
-    process.exit(0);
-}
-main().catch(() => process.exit(0));
-//# sourceMappingURL=session-start.js.map
\ No newline at end of file
diff --git a/.wolf/hooks/shared.js b/.wolf/hooks/shared.js
deleted file mode 100644
index e402d75..0000000
--- a/.wolf/hooks/shared.js
+++ /dev/null
@@ -1,614 +0,0 @@
-import * as fs from "node:fs";
-import * as path from "node:path";
-import * as crypto from "node:crypto";
-export function getWolfDir() {
-    // Prefer CLAUDE_PROJECT_DIR so hooks work even if CWD changes during a session
-    const projectDir = process.env.CLAUDE_PROJECT_DIR || process.cwd();
-    return path.join(projectDir, ".wolf");
-}
-/**
- * Bail out silently if .wolf/ directory doesn't exist in the current project.
- * Call this at the top of every hook to avoid crashes in non-OpenWolf projects.
- */
-export function ensureWolfDir() {
-    const wolfDir = getWolfDir();
-    if (!fs.existsSync(wolfDir)) {
-        process.exit(0);
-    }
-}
-export function readJSON(filePath, fallback) {
-    try {
-        return JSON.parse(fs.readFileSync(filePath, "utf-8"));
-    }
-    catch {
-        return fallback;
-    }
-}
-export function writeJSON(filePath, data) {
-    const dir = path.dirname(filePath);
-    if (!fs.existsSync(dir))
-        fs.mkdirSync(dir, { recursive: true });
-    const tmp = filePath + "." + crypto.randomBytes(4).toString("hex") + ".tmp";
-    try {
-        fs.writeFileSync(tmp, JSON.stringify(data, null, 2), "utf-8");
-        fs.renameSync(tmp, filePath);
-    }
-    catch {
-        // On Windows, rename can fail if another process holds a handle.
-        // Fall back to direct write and clean up the tmp file.
-        try {
-            fs.writeFileSync(filePath, JSON.stringify(data, null, 2), "utf-8");
-        }
-        catch { }
-        try {
-            fs.unlinkSync(tmp);
-        }
-        catch { }
-    }
-}
-export function readMarkdown(filePath) {
-    try {
-        return fs.readFileSync(filePath, "utf-8");
-    }
-    catch {
-        return "";
-    }
-}
-export function appendMarkdown(filePath, line) {
-    const dir = path.dirname(filePath);
-    if (!fs.existsSync(dir))
-        fs.mkdirSync(dir, { recursive: true });
-    fs.appendFileSync(filePath, line, "utf-8");
-}
-export function parseAnatomy(content) {
-    const sections = new Map();
-    let currentSection = "";
-    for (const line of content.split("\n")) {
-        const sm = line.match(/^## (.+)/);
-        if (sm) {
-            currentSection = sm[1].trim();
-            if (!sections.has(currentSection))
-                sections.set(currentSection, []);
-            continue;
-        }
-        if (!currentSection)
-            continue;
-        const em = line.match(/^- `([^`]+)`(?:\s+—\s+(.+?))?\s*\(~(\d+)\s+tok\)$/);
-        if (em) {
-            sections.get(currentSection).push({
-                file: em[1],
-                description: em[2] || "",
-                tokens: parseInt(em[3], 10),
-            });
-        }
-    }
-    return sections;
-}
-export function serializeAnatomy(sections, metadata) {
-    const lines = [
-        "# anatomy.md",
-        "",
-        `> Auto-maintained by OpenWolf. Last scanned: ${metadata.lastScanned}`,
-        `> Files: ${metadata.fileCount} tracked | Anatomy hits: ${metadata.hits} | Misses: ${metadata.misses}`,
-        "",
-    ];
-    const keys = [...sections.keys()].sort();
-    for (const key of keys) {
-        lines.push(`## ${key}`);
-        lines.push("");
-        const entries = sections.get(key).sort((a, b) => a.file.localeCompare(b.file));
-        for (const e of entries) {
-            const desc = e.description ? ` — ${e.description}` : "";
-            lines.push(`- \`${e.file}\`${desc} (~${e.tokens} tok)`);
-        }
-        lines.push("");
-    }
-    return lines.join("\n");
-}
-export function extractDescription(filePath) {
-    const MAX_DESC = 150;
-    const basename = path.basename(filePath);
-    const ext = path.extname(basename).toLowerCase();
-    const known = {
-        "package.json": "Node.js package manifest",
-        "tsconfig.json": "TypeScript configuration",
-        ".gitignore": "Git ignore rules",
-        "README.md": "Project documentation",
-        "composer.json": "PHP package manifest",
-        "requirements.txt": "Python dependencies",
-        "schema.sql": "Database schema",
-        "Dockerfile": "Docker container definition",
-        "docker-compose.yml": "Docker Compose services",
-        "Cargo.toml": "Rust package manifest",
-        "go.mod": "Go module definition",
-        "Gemfile": "Ruby dependencies",
-        "pubspec.yaml": "Dart/Flutter package manifest",
-    };
-    if (known[basename])
-        return known[basename];
-    let content;
-    try {
-        const fd = fs.openSync(filePath, "r");
-        const buf = Buffer.alloc(12288); // 12KB
-        const n = fs.readSync(fd, buf, 0, 12288, 0);
-        fs.closeSync(fd);
-        content = buf.subarray(0, n).toString("utf-8");
-    }
-    catch {
-        return "";
-    }
-    if (!content.trim())
-        return "";
-    const cap = (s) => s.length <= MAX_DESC ? s : s.slice(0, MAX_DESC - 3) + "...";
-    // Markdown heading
-    if (ext === ".md" || ext === ".mdx") {
-        const m = content.match(/^#{1,2}\s+(.+)$/m);
-        if (m)
-            return cap(m[1].trim());
-    }
-    // HTML title
-    if (ext === ".html" || ext === ".htm") {
-        const m = content.match(/<title[^>]*>([^<]+)<\/title>/i);
-        if (m)
-            return cap(m[1].trim());
-    }
-    // JSDoc / PHPDoc / Javadoc — first meaningful line
-    const jm = content.match(/\/\*\*\s*\n?\s*\*?\s*(.+)/);
-    if (jm) {
-        const l = jm[1].replace(/\*\/$/, "").trim();
-        if (l && !l.startsWith("@") && l.length > 5)
-            return cap(l);
-    }
-    // Python docstring
-    if (ext === ".py") {
-        const dm = content.match(/^(?:#[^\n]*\n)*\s*(?:"""(.+?)"""|'''(.+?)''')/s);
-        if (dm) {
-            const first = (dm[1] || dm[2]).split("\n")[0].trim();
-            if (first && first.length > 3)
-                return cap(first);
-        }
-    }
-    // Rust doc comments
-    if (ext === ".rs") {
-        const lines = content.split("\n");
-        for (const line of lines.slice(0, 20)) {
-            const m = line.match(/^\s*(?:\/\/\/|\/\/!)\s*(.+)/);
-            if (m && m[1].length > 5)
-                return cap(m[1].trim());
-        }
-    }
-    // Go package comment
-    if (ext === ".go") {
-        const m = content.match(/\/\/\s*Package\s+\w+\s+(.*)/);
-        if (m)
-            return cap(m[1].trim());
-    }
-    // C# XML doc
-    if (ext === ".cs") {
-        const m = content.match(/<summary>\s*([\s\S]*?)\s*<\/summary>/);
-        if (m) {
-            const text = m[1].replace(/\/\/\/\s*/g, "").replace(/\s+/g, " ").trim();
-            if (text.length > 5)
-                return cap(text);
-        }
-    }
-    // Elixir @moduledoc
-    if (ext === ".ex" || ext === ".exs") {
-        const m = content.match(/@moduledoc\s+"""\s*\n\s*(.*)/);
-        if (m)
-            return cap(m[1].trim());
-    }
-    // Header comment (skip generic ones)
-    const hdrLines = content.split("\n");
-    for (const line of hdrLines.slice(0, 15)) {
-        const t = line.trim();
-        if (!t || t === "<?php" || t.startsWith("#!") || t.startsWith("namespace") || t.startsWith("use ") || t.startsWith("import ") || t.startsWith("from ") || t.startsWith("require") || t.startsWith("module "))
-            continue;
-        const cm = t.match(/^(?:\/\/|#|--)\s*(.+)/);
-        if (cm) {
-            const text = cm[1].trim();
-            const lower = text.toLowerCase();
-            if (text.length > 5 && !lower.startsWith("copyright") && !lower.startsWith("license") && !lower.startsWith("@") && !lower.startsWith("strict") && !lower.startsWith("generated") && !lower.startsWith("eslint-") && !lower.startsWith("nolint")) {
-                return cap(text);
-            }
-        }
-        if (!t.startsWith("//") && !t.startsWith("#") && !t.startsWith("/*") && !t.startsWith("*") && !t.startsWith("--"))
-            break;
-    }
-    // ─── PHP / Laravel ───────────────────────────────────────
-    if (ext === ".php") {
-        if (basename.endsWith(".blade.php")) {
-            const ext2 = content.match(/@extends\(\s*['"]([^'"]+)['"]\s*\)/);
-            const sections = (content.match(/@section\(\s*['"](\w+)['"]/g) || []).map(s => s.match(/['"](\w+)['"]/)?.[1]).filter(Boolean);
-            const parts = [];
-            if (ext2)
-                parts.push(`extends ${ext2[1]}`);
-            if (sections.length)
-                parts.push(`sections: ${sections.join(", ")}`);
-            return cap(parts.length ? `Blade: ${parts.join(", ")}` : "Blade template");
-        }
-        const classM = content.match(/class\s+(\w+)(?:\s+extends\s+(\w+))?/);
-        const className = classM?.[1] || "";
-        const parent = classM?.[2] || "";
-        const pubMethods = (content.match(/public\s+function\s+(\w+)/g) || [])
-            .map(m => m.match(/public\s+function\s+(\w+)/)?.[1])
-            .filter(n => n && n !== "__construct" && n !== "middleware");
-        if (basename.endsWith("Controller.php") || parent === "Controller") {
-            if (pubMethods.length > 0) {
-                const display = pubMethods.slice(0, 5).join(", ");
-                return cap(pubMethods.length > 5 ? `${display} + ${pubMethods.length - 5} more` : display);
-            }
-        }
-        if (parent === "Model" || parent === "Authenticatable") {
-            const parts = [];
-            const tbl = content.match(/\$table\s*=\s*['"]([^'"]+)['"]/);
-            if (tbl)
-                parts.push(`table: ${tbl[1]}`);
-            const fill = content.match(/\$fillable\s*=\s*\[([^\]]*)\]/s);
-            if (fill) {
-                const c = (fill[1].match(/['"]/g) || []).length / 2;
-                parts.push(`${Math.floor(c)} fields`);
-            }
-            const rels = (content.match(/\$this->(hasMany|hasOne|belongsTo|belongsToMany|morphMany|morphTo)\(/g) || []).length;
-            if (rels)
-                parts.push(`${rels} rels`);
-            return cap(parts.length ? `Model — ${parts.join(", ")}` : `Model: ${className}`);
-        }
-        if (basename.match(/^\d{4}_\d{2}_\d{2}/)) {
-            const create = content.match(/Schema::create\(\s*['"]([^'"]+)['"]/);
-            if (create)
-                return `Migration: create ${create[1]} table`;
-            const alter = content.match(/Schema::table\(\s*['"]([^'"]+)['"]/);
-            if (alter)
-                return `Migration: alter ${alter[1]} table`;
-            return "Database migration";
-        }
-        if (className && pubMethods.length > 0) {
-            const display = pubMethods.slice(0, 4).join(", ");
-            return cap(pubMethods.length > 4 ? `${className}: ${display} + ${pubMethods.length - 4} more` : `${className}: ${display}`);
-        }
-    }
-    // ─── TS/JS/React/Next.js ─────────────────────────────────
-    if (ext === ".ts" || ext === ".tsx" || ext === ".js" || ext === ".jsx" || ext === ".mjs" || ext === ".cjs") {
-        // React component
-        if (ext === ".tsx" || ext === ".jsx") {
-            const comp = content.match(/(?:export\s+(?:default\s+)?)?(?:function|const)\s+(\w+)/);
-            const parts = [];
-            if (comp)
-                parts.push(comp[1]);
-            const renders = [];
-            if (/<(?:form|Form)/i.test(content))
-                renders.push("form");
-            if (/<(?:table|Table|DataTable)/i.test(content))
-                renders.push("table");
-            if (/<(?:dialog|Dialog|Modal|Drawer)/i.test(content))
-                renders.push("modal");
-            if (renders.length)
-                parts.push(`renders ${renders.join(", ")}`);
-            if (parts.length)
-                return cap(parts.join(" — "));
-        }
-        // Next.js conventions
-        if (basename === "page.tsx" || basename === "page.js")
-            return "Next.js page component";
-        if (basename === "layout.tsx" || basename === "layout.js")
-            return "Next.js layout";
-        if (basename === "route.ts" || basename === "route.js") {
-            const methods = [...new Set((content.match(/export\s+(?:async\s+)?function\s+(GET|POST|PUT|PATCH|DELETE)/g) || [])
-                    .map(m => m.match(/(GET|POST|PUT|PATCH|DELETE)/)?.[1]))].filter(Boolean);
-            return methods.length ? `Next.js API route: ${methods.join(", ")}` : "Next.js API route";
-        }
-        // Express/Fastify routes
-        const routeHits = content.match(/\.(get|post|put|patch|delete)\s*\(\s*['"`]/g);
-        if (routeHits && routeHits.length > 0) {
-            const methods = [...new Set(routeHits.map(r => r.match(/\.(get|post|put|patch|delete)/)?.[1]?.toUpperCase()))];
-            return cap(`API routes: ${methods.join(", ")} (${routeHits.length} endpoints)`);
-        }
-        // tRPC router
-        if (content.includes("createTRPCRouter") || content.includes("publicProcedure")) {
-            const procs = (content.match(/\.(query|mutation|subscription)\s*\(/g) || []).length;
-            return procs ? `tRPC router: ${procs} procedures` : "tRPC router";
-        }
-        // Zod schemas
-        if (content.includes("z.object") || content.includes("z.string")) {
-            const schemas = (content.match(/(?:export\s+)?(?:const|let)\s+(\w+)\s*=\s*z\./g) || [])
-                .map(s => s.match(/(?:const|let)\s+(\w+)/)?.[1]).filter(Boolean);
-            if (schemas.length)
-                return cap(`Zod schemas: ${schemas.slice(0, 4).join(", ")}${schemas.length > 4 ? ` + ${schemas.length - 4} more` : ""}`);
-        }
-        // Exports summary
-        const exports = (content.match(/export\s+(?:async\s+)?(?:function|class|const|interface|type|enum)\s+(\w+)/g) || [])
-            .map(e => e.match(/(\w+)$/)?.[1]).filter(Boolean);
-        if (exports.length > 0 && exports.length <= 5)
-            return `Exports ${exports.join(", ")}`;
-        if (exports.length > 5)
-            return cap(`Exports ${exports.slice(0, 4).join(", ")} + ${exports.length - 4} more`);
-    }
-    // ─── Python / Django / FastAPI / Flask ────────────────────
-    if (ext === ".py") {
-        // Django model
-        if (content.includes("models.Model")) {
-            const cls = content.match(/class\s+(\w+)\(.*models\.Model\)/);
-            const fields = (content.match(/^\s+\w+\s*=\s*models\.\w+/gm) || []).length;
-            return cap(`Model: ${cls?.[1] || "unknown"}, ${fields} fields`);
-        }
-        // FastAPI/Flask routes
-        if (content.includes("@router.") || content.includes("@app.")) {
-            const routes = (content.match(/@(?:router|app)\.(get|post|put|patch|delete)\s*\(/g) || []);
-            return cap(routes.length ? `API: ${routes.length} endpoints` : "API router");
-        }
-        // Pydantic
-        if (content.includes("BaseModel") && content.includes("Field(")) {
-            const cls = content.match(/class\s+(\w+)\(.*BaseModel\)/);
-            return cls ? `Pydantic: ${cls[1]}` : "Pydantic model";
-        }
-        // Celery
-        if (content.includes("@shared_task") || content.includes("@app.task")) {
-            const tasks = (content.match(/def\s+(\w+)/g) || []).map(m => m.match(/def\s+(\w+)/)?.[1]).filter(n => n && !n.startsWith("_"));
-            return cap(tasks.length ? `Celery tasks: ${tasks.join(", ")}` : "Celery task");
-        }
-        // Generic
-        const pyClass = content.match(/class\s+(\w+)/);
-        const funcs = (content.match(/def\s+(\w+)/g) || []).map(f => f.match(/def\s+(\w+)/)?.[1]).filter(n => n && !n.startsWith("_"));
-        if (pyClass && funcs.length > 0)
-            return cap(funcs.length > 4 ? `${pyClass[1]}: ${funcs.slice(0, 4).join(", ")} + ${funcs.length - 4} more` : `${pyClass[1]}: ${funcs.join(", ")}`);
-        if (funcs.length > 0)
-            return cap(funcs.slice(0, 4).join(", "));
-    }
-    // ─── Go ──────────────────────────────────────────────────
-    if (ext === ".go") {
-        const handlers = (content.match(/func\s+(\w+)\s*\(\s*\w+\s+http\.ResponseWriter/g) || [])
-            .map(m => m.match(/func\s+(\w+)/)?.[1]).filter(Boolean);
-        if (handlers.length)
-            return cap(`HTTP handlers: ${handlers.slice(0, 5).join(", ")}`);
-        const iface = content.match(/type\s+(\w+)\s+interface\s*\{/);
-        if (iface)
-            return `Interface: ${iface[1]}`;
-        const structM = content.match(/type\s+(\w+)\s+struct\s*\{/);
-        if (structM)
-            return `Struct: ${structM[1]}`;
-        const funcs = (content.match(/^func\s+(\w+)/gm) || []).map(m => m.match(/func\s+(\w+)/)?.[1]).filter(n => n && n[0] === n[0].toUpperCase());
-        if (funcs.length)
-            return cap(funcs.slice(0, 5).join(", "));
-    }
-    // ─── Rust ────────────────────────────────────────────────
-    if (ext === ".rs") {
-        const structM = content.match(/pub\s+struct\s+(\w+)/);
-        if (structM) {
-            const methods = (content.match(/pub\s+(?:async\s+)?fn\s+(\w+)/g) || []).map(m => m.match(/fn\s+(\w+)/)?.[1]).filter(Boolean);
-            return cap(methods.length ? `${structM[1]}: ${methods.slice(0, 4).join(", ")}` : `Struct: ${structM[1]}`);
-        }
-        const traitM = content.match(/pub\s+trait\s+(\w+)/);
-        if (traitM)
-            return `Trait: ${traitM[1]}`;
-        const enumM = content.match(/pub\s+enum\s+(\w+)/);
-        if (enumM)
-            return `Enum: ${enumM[1]}`;
-        const fns = (content.match(/pub\s+(?:async\s+)?fn\s+(\w+)/g) || []).map(m => m.match(/fn\s+(\w+)/)?.[1]).filter(Boolean);
-        if (fns.length)
-            return cap(fns.slice(0, 5).join(", "));
-    }
-    // ─── Java / Spring ───────────────────────────────────────
-    if (ext === ".java") {
-        const cls = content.match(/(?:public\s+)?class\s+(\w+)/);
-        const className = cls?.[1] || basename.replace(".java", "");
-        const annotations = (content.match(/@(RestController|Controller|Service|Repository|Component|Entity|Configuration)/g) || []).map(a => a.slice(1));
-        const mappings = (content.match(/@(?:Get|Post|Put|Patch|Delete|Request)Mapping/g) || []).length;
-        if (mappings)
-            return cap(`${annotations[0] || "Spring"}: ${className} (${mappings} endpoints)`);
-        if (annotations.length)
-            return `${annotations[0]}: ${className}`;
-        if (content.includes("@Entity"))
-            return `Entity: ${className}`;
-        const methods = (content.match(/public\s+(?:static\s+)?(?:\w+(?:<[\w,\s]+>)?)\s+(\w+)\s*\(/g) || [])
-            .map(m => m.match(/(\w+)\s*\(/)?.[1]).filter(n => n && n !== className);
-        if (methods.length)
-            return cap(`${className}: ${methods.slice(0, 4).join(", ")}`);
-        return className ? `Class: ${className}` : "";
-    }
-    // ─── Kotlin ──────────────────────────────────────────────
-    if (ext === ".kt" || ext === ".kts") {
-        const cls = content.match(/(?:data\s+)?class\s+(\w+)/);
-        if (content.match(/data\s+class/))
-            return `Data class: ${cls?.[1] || basename.replace(/\.kts?$/, "")}`;
-        if (content.includes("routing {"))
-            return "Ktor routing";
-        const fns = (content.match(/fun\s+(\w+)/g) || []).map(m => m.match(/fun\s+(\w+)/)?.[1]).filter(Boolean);
-        if (cls && fns.length)
-            return cap(`${cls[1]}: ${fns.slice(0, 4).join(", ")}`);
-        if (fns.length)
-            return cap(fns.slice(0, 5).join(", "));
-    }
-    // ─── C# / .NET ───────────────────────────────────────────
-    if (ext === ".cs") {
-        const cls = content.match(/(?:public\s+)?(?:partial\s+)?class\s+(\w+)(?:\s*:\s*(\w+))?/);
-        const className = cls?.[1] || basename.replace(".cs", "");
-        const parent = cls?.[2] || "";
-        if (parent === "Controller" || parent === "ControllerBase" || content.includes("[ApiController]")) {
-            const actions = (content.match(/\[Http(Get|Post|Put|Patch|Delete)\]/g) || []).map(a => a.match(/Http(\w+)/)?.[1]).filter(Boolean);
-            return cap(actions.length ? `API Controller: ${className} (${[...new Set(actions)].join(", ")})` : `Controller: ${className}`);
-        }
-        if (parent === "DbContext" || content.includes("DbSet<")) {
-            const sets = (content.match(/DbSet<(\w+)>/g) || []).map(s => s.match(/<(\w+)>/)?.[1]).filter(Boolean);
-            return cap(sets.length ? `DbContext: ${sets.join(", ")}` : `DbContext: ${className}`);
-        }
-        return className ? `Class: ${className}` : "";
-    }
-    // ─── Ruby / Rails ────────────────────────────────────────
-    if (ext === ".rb") {
-        const cls = content.match(/class\s+(\w+)(?:\s*<\s*(\w+(?:::\w+)?))?/);
-        const className = cls?.[1] || "";
-        const parent = cls?.[2] || "";
-        if (parent?.includes("Controller")) {
-            const actions = (content.match(/def\s+(index|show|new|create|edit|update|destroy|\w+)/g) || [])
-                .map(m => m.match(/def\s+(\w+)/)?.[1]).filter(n => n && !n.startsWith("_"));
-            return cap(actions.length ? `Controller: ${actions.join(", ")}` : `Controller: ${className}`);
-        }
-        if (parent === "ApplicationRecord" || parent === "ActiveRecord::Base")
-            return `Model: ${className}`;
-        if (basename.match(/^\d{14}_/)) {
-            const create = content.match(/create_table\s+:(\w+)/);
-            return create ? `Migration: create ${create[1]}` : "Database migration";
-        }
-        const methods = (content.match(/def\s+(\w+)/g) || []).map(m => m.match(/def\s+(\w+)/)?.[1]).filter(n => n && !n.startsWith("_"));
-        if (cls && methods.length)
-            return cap(`${className}: ${methods.slice(0, 4).join(", ")}`);
-    }
-    // ─── Swift ───────────────────────────────────────────────
-    if (ext === ".swift") {
-        if (content.includes(": View") || content.includes("some View")) {
-            const name = content.match(/struct\s+(\w+)\s*:\s*View/);
-            return name ? `SwiftUI view: ${name[1]}` : "SwiftUI view";
-        }
-        const proto = content.match(/protocol\s+(\w+)/);
-        if (proto)
-            return `Protocol: ${proto[1]}`;
-        const struct = content.match(/(?:public\s+)?struct\s+(\w+)/);
-        const cls = content.match(/(?:public\s+)?class\s+(\w+)/);
-        const name = struct?.[1] || cls?.[1] || "";
-        if (name)
-            return `${struct ? "Struct" : "Class"}: ${name}`;
-    }
-    // ─── Dart / Flutter ──────────────────────────────────────
-    if (ext === ".dart") {
-        if (content.includes("StatefulWidget") || content.includes("StatelessWidget")) {
-            const name = content.match(/class\s+(\w+)\s+extends\s+(?:Stateful|Stateless)Widget/);
-            return name ? `${content.includes("StatefulWidget") ? "Stateful" : "Stateless"} widget: ${name[1]}` : "Flutter widget";
-        }
-        const cls = content.match(/class\s+(\w+)/);
-        if (cls)
-            return `Class: ${cls[1]}`;
-    }
-    // ─── Vue / Svelte / Astro ────────────────────────────────
-    if (ext === ".vue") {
-        const name = content.match(/name:\s*['"]([^'"]+)['"]/);
-        const setup = content.includes("<script setup");
-        const parts = [];
-        if (name)
-            parts.push(name[1]);
-        if (setup)
-            parts.push("setup");
-        return cap(parts.length ? `Vue: ${parts.join(", ")}` : "Vue component");
-    }
-    if (ext === ".svelte")
-        return `Svelte: ${basename.replace(".svelte", "")}`;
-    if (ext === ".astro")
-        return `Astro: ${basename.replace(".astro", "")}`;
-    // ─── CSS / SCSS / Less ───────────────────────────────────
-    if (ext === ".css" || ext === ".scss" || ext === ".less") {
-        const rules = (content.match(/^[.#@][^\n{]+/gm) || []).length;
-        const vars = (content.match(/--[\w-]+\s*:/g) || []).length;
-        const parts = [];
-        if (rules)
-            parts.push(`${rules} rules`);
-        if (vars)
-            parts.push(`${vars} vars`);
-        return cap(parts.length ? `Styles: ${parts.join(", ")}` : "Stylesheet");
-    }
-    // ─── SQL ─────────────────────────────────────────────────
-    if (ext === ".sql") {
-        const creates = (content.match(/CREATE\s+TABLE\s+(?:IF\s+NOT\s+EXISTS\s+)?[`"']?(\w+)/gi) || [])
-            .map(m => m.match(/(?:TABLE\s+(?:IF\s+NOT\s+EXISTS\s+)?)([`"']?\w+)/i)?.[1]?.replace(/[`"']/g, "")).filter(Boolean);
-        if (creates.length)
-            return cap(`SQL: tables: ${creates.slice(0, 4).join(", ")}`);
-    }
-    // ─── Proto / GraphQL ─────────────────────────────────────
-    if (ext === ".proto") {
-        const msgs = (content.match(/message\s+(\w+)/g) || []).map(m => m.match(/message\s+(\w+)/)?.[1]).filter(Boolean);
-        const services = (content.match(/service\s+(\w+)/g) || []).map(m => m.match(/service\s+(\w+)/)?.[1]).filter(Boolean);
-        const parts = [];
-        if (msgs.length)
-            parts.push(`messages: ${msgs.slice(0, 3).join(", ")}`);
-        if (services.length)
-            parts.push(`services: ${services.join(", ")}`);
-        return cap(parts.length ? `Proto: ${parts.join(", ")}` : "");
-    }
-    if (ext === ".graphql" || ext === ".gql") {
-        const types = (content.match(/type\s+(\w+)/g) || []).map(m => m.match(/type\s+(\w+)/)?.[1]).filter(Boolean);
-        return cap(types.length ? `GraphQL: types: ${types.slice(0, 4).join(", ")}` : "GraphQL schema");
-    }
-    // ─── YAML ────────────────────────────────────────────────
-    if (ext === ".yaml" || ext === ".yml") {
-        if (content.includes("runs-on:")) {
-            const name = content.match(/^name:\s*(.+)$/m);
-            return cap(name ? `CI: ${name[1].trim()}` : "GitHub Actions workflow");
-        }
-        if (content.includes("apiVersion:") && content.includes("kind:")) {
-            const kind = content.match(/kind:\s*(\w+)/);
-            return cap(kind ? `K8s ${kind[1]}` : "Kubernetes manifest");
-        }
-        if (content.includes("services:") && (basename.includes("docker") || basename.includes("compose"))) {
-            const services = (content.match(/^\s{2}\w+:/gm) || []).length;
-            return `Docker Compose: ${services} services`;
-        }
-    }
-    // ─── TOML ────────────────────────────────────────────────
-    if (ext === ".toml") {
-        const desc = content.match(/^description\s*=\s*"([^"]+)"/m);
-        if (desc)
-            return cap(desc[1]);
-    }
-    // ─── Elixir ──────────────────────────────────────────────
-    if (ext === ".ex" || ext === ".exs") {
-        const mod = content.match(/defmodule\s+([\w.]+)/);
-        if (content.includes("Phoenix.LiveView"))
-            return cap(mod ? `LiveView: ${mod[1]}` : "Phoenix LiveView");
-        if (content.includes("Controller"))
-            return cap(mod ? `Phoenix controller: ${mod[1]}` : "Phoenix controller");
-        const fns = (content.match(/def\s+(\w+)/g) || []).map(m => m.match(/def\s+(\w+)/)?.[1]).filter(Boolean);
-        if (mod && fns.length)
-            return cap(`${mod[1]}: ${fns.slice(0, 4).join(", ")}`);
-        if (mod)
-            return mod[1];
-    }
-    // ─── Lua ─────────────────────────────────────────────────
-    if (ext === ".lua") {
-        const fns = (content.match(/function\s+(?:\w+[.:])?(\w+)/g) || []).map(m => m.match(/(\w+)\s*$/)?.[1]).filter(Boolean);
-        if (fns.length)
-            return cap(fns.slice(0, 5).join(", "));
-    }
-    // ─── Zig ─────────────────────────────────────────────────
-    if (ext === ".zig") {
-        const fns = (content.match(/pub\s+fn\s+(\w+)/g) || []).map(m => m.match(/fn\s+(\w+)/)?.[1]).filter(Boolean);
-        if (fns.length)
-            return cap(fns.slice(0, 5).join(", "));
-    }
-    // Last resort
-    const declM = content.match(/(?:function|class|const|interface|type|enum)\s+(\w+)/);
-    if (declM) {
-        const name = declM[1];
-        const methods = (content.match(/(?:public\s+)?(?:async\s+)?(?:function\s+|(?:get|set)\s+)(\w+)\s*\(/g) || [])
-            .map(m => m.match(/(\w+)\s*\(/)?.[1]).filter(n => n && n !== name && n !== "__construct" && n !== "constructor");
-        if (methods.length > 0 && methods.length <= 5)
-            return cap(`${name}: ${methods.join(", ")}`);
-        if (methods.length > 5)
-            return cap(`${name}: ${methods.slice(0, 3).join(", ")} + ${methods.length - 3} more`);
-        return `Declares ${name}`;
-    }
-    return "";
-}
-export function estimateTokens(text, type = "mixed") {
-    const ratio = type === "code" ? 3.5 : type === "prose" ? 4.0 : 3.75;
-    return Math.ceil(text.length / ratio);
-}
-export function timestamp() {
-    return new Date().toISOString();
-}
-export function timeShort() {
-    const d = new Date();
-    return `${String(d.getHours()).padStart(2, "0")}:${String(d.getMinutes()).padStart(2, "0")}`;
-}
-export function readStdin() {
-    return new Promise((resolve) => {
-        const chunks = [];
-        process.stdin.on("data", (chunk) => chunks.push(chunk));
-        process.stdin.on("end", () => resolve(Buffer.concat(chunks).toString("utf-8")));
-        // If no stdin data after 4s, resolve with whatever we have so far.
-        // On Windows, stdin delivery from Claude Code hooks can be slow.
-        setTimeout(() => resolve(chunks.length ? Buffer.concat(chunks).toString("utf-8") : "{}"), 4000);
-    });
-}
-export function normalizePath(p) {
-    return p.replace(/\\/g, "/");
-}
-//# sourceMappingURL=shared.js.map
\ No newline at end of file
diff --git a/.wolf/hooks/stop.js b/.wolf/hooks/stop.js
deleted file mode 100644
index e215ac6..0000000
--- a/.wolf/hooks/stop.js
+++ /dev/null
@@ -1,147 +0,0 @@
-import * as fs from "node:fs";
-import * as path from "node:path";
-import { getWolfDir, ensureWolfDir, readJSON, writeJSON, appendMarkdown, timeShort } from "./shared.js";
-async function main() {
-    ensureWolfDir();
-    const wolfDir = getWolfDir();
-    const hooksDir = path.join(wolfDir, "hooks");
-    const sessionFile = path.join(hooksDir, "_session.json");
-    const session = readJSON(sessionFile, {
-        session_id: "",
-        started: "",
-        files_read: {},
-        files_written: [],
-        edit_counts: {},
-        anatomy_hits: 0,
-        anatomy_misses: 0,
-        repeated_reads_warned: 0,
-        cerebrum_warnings: 0,
-        stop_count: 0,
-    });
-    session.stop_count++;
-    // Only write to ledger if there's been activity
-    const readCount = Object.keys(session.files_read).length;
-    const writeCount = session.files_written.length;
-    if (readCount === 0 && writeCount === 0) {
-        writeJSON(sessionFile, session);
-        process.exit(0);
-        return;
-    }
-    // Check for files edited many times without a buglog entry
-    checkForMissingBugLogs(wolfDir, session);
-    // Check if cerebrum was updated this session (it should be if there were edits)
-    checkCerebrumFreshness(wolfDir, session);
-    // Build session entry for ledger
-    const reads = Object.entries(session.files_read).map(([file, data]) => ({
-        file,
-        tokens_estimated: data.tokens,
-        was_repeated: data.count > 1,
-        anatomy_had_description: false, // simplified
-    }));
-    const writes = session.files_written.map((w) => ({
-        file: w.file,
-        tokens_estimated: w.tokens,
-        action: w.action,
-    }));
-    const inputTokens = reads.reduce((sum, r) => sum + r.tokens_estimated, 0);
-    const outputTokens = writes.reduce((sum, w) => sum + w.tokens_estimated, 0);
-    const sessionEntry = {
-        id: session.session_id,
-        started: session.started,
-        ended: new Date().toISOString(),
-        reads,
-        writes,
-        totals: {
-            input_tokens_estimated: inputTokens,
-            output_tokens_estimated: outputTokens,
-            reads_count: readCount,
-            writes_count: writeCount,
-            repeated_reads_blocked: session.repeated_reads_warned,
-            anatomy_lookups: session.anatomy_hits,
-        },
-    };
-    // Update token-ledger.json
-    const ledgerPath = path.join(wolfDir, "token-ledger.json");
-    const ledger = readJSON(ledgerPath, {
-        version: 1,
-        created_at: "",
-        lifetime: {
-            total_tokens_estimated: 0,
-            total_reads: 0,
-            total_writes: 0,
-            total_sessions: 0,
-            anatomy_hits: 0,
-            anatomy_misses: 0,
-            repeated_reads_blocked: 0,
-            estimated_savings_vs_bare_cli: 0,
-        },
-        sessions: [],
-        daemon_usage: [],
-        waste_flags: [],
-        optimization_report: { last_generated: null, patterns: [] },
-    });
-    ledger.sessions.push(sessionEntry);
-    ledger.lifetime.total_reads += readCount;
-    ledger.lifetime.total_writes += writeCount;
-    ledger.lifetime.total_tokens_estimated += inputTokens + outputTokens;
-    ledger.lifetime.anatomy_hits += session.anatomy_hits;
-    ledger.lifetime.anatomy_misses += session.anatomy_misses;
-    ledger.lifetime.repeated_reads_blocked += session.repeated_reads_warned;
-    // Estimate savings: anatomy hits save ~200 tokens each, repeated reads blocked save their token count
-    const savedFromAnatomy = session.anatomy_hits * 200;
-    const savedFromRepeats = Object.values(session.files_read)
-        .filter((r) => r.count > 1)
-        .reduce((sum, r) => sum + r.tokens * (r.count - 1), 0);
-    ledger.lifetime.estimated_savings_vs_bare_cli += savedFromAnatomy + savedFromRepeats;
-    writeJSON(ledgerPath, ledger);
-    // Write a session summary line to memory.md if there was meaningful activity
-    if (writeCount > 0) {
-        try {
-            const uniqueFiles = new Set(session.files_written.map(w => path.basename(w.file)));
-            const fileList = [...uniqueFiles].slice(0, 5).join(", ");
-            const memoryPath = path.join(wolfDir, "memory.md");
-            appendMarkdown(memoryPath, `| ${timeShort()} | Session end: ${writeCount} writes across ${uniqueFiles.size} files (${fileList}) | ${readCount} reads | ~${inputTokens + outputTokens} tok |\n`);
-        }
-        catch { }
-    }
-    writeJSON(sessionFile, session);
-    process.exit(0);
-}
-/**
- * Check if files were edited multiple times but buglog.json wasn't updated.
- * Emit a stderr reminder so Claude sees it in the next turn.
- */
-function checkForMissingBugLogs(wolfDir, session) {
-    if (!session.edit_counts)
-        return;
-    const multiEditFiles = Object.entries(session.edit_counts)
-        .filter(([, count]) => count >= 3)
-        .map(([file]) => path.basename(file));
-    if (multiEditFiles.length === 0)
-        return;
-    // Check if buglog was written to this session
-    const buglogWritten = session.files_written.some(w => w.file.includes("buglog.json"));
-    if (!buglogWritten) {
-        process.stderr.write(`⚠️ OpenWolf: Files edited 3+ times this session (${multiEditFiles.join(", ")}) but buglog.json was not updated. If you fixed bugs, please log them.\n`);
-    }
-}
-/**
- * Check if cerebrum.md was updated recently. If it hasn't been updated in
- * a while and there was significant activity, emit a gentle reminder.
- */
-function checkCerebrumFreshness(wolfDir, session) {
-    const cerebrumPath = path.join(wolfDir, "cerebrum.md");
-    try {
-        const stat = fs.statSync(cerebrumPath);
-        const hoursSinceUpdate = (Date.now() - stat.mtimeMs) / (1000 * 60 * 60);
-        // If cerebrum hasn't been updated in 24h+ and there were significant writes
-        if (hoursSinceUpdate > 24 && session.files_written.length >= 3) {
-            process.stderr.write(`💡 OpenWolf: cerebrum.md hasn't been updated in ${Math.floor(hoursSinceUpdate)}h. Did you learn any user preferences, conventions, or gotchas this session? Consider updating .wolf/cerebrum.md.\n`);
-        }
-    }
-    catch {
-        // cerebrum.md doesn't exist, that's ok
-    }
-}
-main().catch(() => process.exit(0));
-//# sourceMappingURL=stop.js.map
\ No newline at end of file
diff --git a/.wolf/identity.md b/.wolf/identity.md
deleted file mode 100644
index 8328ccd..0000000
--- a/.wolf/identity.md
+++ /dev/null
@@ -1,9 +0,0 @@
-# Identity
-
-- **Name:** netgazet
-- **Role:** AI development assistant for netgazet
-- **Tone:** Direct, concise, technically precise
-- **Constraints:**
-  - Never modify .env or secret files without explicit user confirmation
-  - Never delete files without explicit user confirmation
-  - Always explain why before making architectural changes
diff --git a/.wolf/memory.md b/.wolf/memory.md
deleted file mode 100644
index a9a8b98..0000000
--- a/.wolf/memory.md
+++ /dev/null
@@ -1,36 +0,0 @@
-# Memory
-
-> Chronological action log. Hooks and AI append to this file automatically.
-> Old sessions are consolidated by the daemon weekly.
-
-## Session: 2026-06-03 15:15
-
-| Time | Action | File(s) | Outcome | ~Tokens |
-|------|--------|---------|---------|--------|
-
-## Session: 2026-06-03 15:16
-
-| Time | Action | File(s) | Outcome | ~Tokens |
-|------|--------|---------|---------|--------|
-| 15:16 | Created CLAUDE.md | — | ~587 |
-| 15:16 | Session end: 1 writes across 1 files (CLAUDE.md) | 0 reads | ~628 tok |
-| 15:17 | Session end: 1 writes across 1 files (CLAUDE.md) | 1 reads | ~1178 tok |
-| 15:25 | Created ../../.claude/plans/in-the-example-folder-immutable-rossum.md | — | ~2254 |
-| 15:29 | Created main.py | — | ~2847 |
-| 15:30 | Implemented PDF→HTML converter (poppler-utils, stdlib only) | main.py | 32 pages rendered, output/ ≈ 20MB | ~3000 |
-| 15:30 | Generated output/ site | output/index.html, output/styles.css, output/NETgazet-07_okt2024/*, output/NETgazet-08_apr2025/* | 2 issues × 16 pages | ~500 |
-| 15:30 | Session end: 3 writes across 3 files (CLAUDE.md, in-the-example-folder-immutable-rossum.md, main.py) | 4 reads | ~6439 tok |
-| 15:34 | Session end: 3 writes across 3 files (CLAUDE.md, in-the-example-folder-immutable-rossum.md, main.py) | 4 reads | ~6439 tok |
-| 15:35 | Session end: 3 writes across 3 files (CLAUDE.md, in-the-example-folder-immutable-rossum.md, main.py) | 4 reads | ~6439 tok |
-
-## Session: 2026-06-03 15:52
-
-| Time | Action | File(s) | Outcome | ~Tokens |
-|------|--------|---------|---------|--------|
-
-## Session: 2026-06-03 15:55
-
-| Time | Action | File(s) | Outcome | ~Tokens |
-|------|--------|---------|---------|--------|
-| 15:57 | Created README.md | — | ~970 |
-| 15:57 | Created .gitignore | — | ~55 |
diff --git a/.wolf/reframe-frameworks.md b/.wolf/reframe-frameworks.md
deleted file mode 100644
index 2742fa4..0000000
--- a/.wolf/reframe-frameworks.md
+++ /dev/null
@@ -1,597 +0,0 @@
-# OpenWolf Reframe — UI Framework Knowledge Base
-
-When the user asks to change, pick, migrate, or "reframe" their UI framework, use this file to guide the conversation and generate the right migration prompt.
-
-## Decision Questions
-
-Ask these in order. Stop early if the answer narrows to 1-2 frameworks.
-
-1. **What framework/library does your project currently use?** (React, Vue, Svelte, plain HTML, etc.)
-2. **What's your priority?** (a) Stunning animations, (b) Fast setup / ship quickly, (c) Full design control, (d) Accessibility-first, (e) Business/enterprise look
-3. **Do you use Tailwind CSS already?** (Yes → most options work. No → Chakra UI or DaisyUI are easier without it)
-4. **Light mode, dark mode, or both?**
-5. **Is this a landing page, a dashboard/app, or both?**
-
-## Quick Selection Guide
-
-| Priority | Recommended |
-|----------|-------------|
-| Fastest setup | DaisyUI, Preline UI |
-| Stunning animations | Aceternity UI, Magic UI |
-| Maximum control | shadcn/ui, Headless UI |
-| Most free components | Origin UI (400+) |
-| Multi-framework (React + Vue + Svelte) | Park UI, DaisyUI, Flowbite |
-| AI product aesthetic | Cult UI |
-| Polished defaults + accessibility | HeroUI, Chakra UI |
-| Business/enterprise | Flowbite, shadcn/ui |
-
-## Comparison Matrix
-
-| Framework | Styling | Animation | Setup | Best For | Cost |
-|-----------|---------|-----------|-------|----------|------|
-| shadcn/ui | Tailwind + Radix | Minimal | Medium | Full apps, dashboards | Free |
-| Aceternity UI | Tailwind + Framer Motion | Heavy, cinematic | Easy (copy-paste) | Animated landing pages | Free / Pro |
-| Magic UI | Tailwind + Motion | Purposeful, polished | Easy (shadcn CLI) | SaaS marketing | Free / Pro |
-| DaisyUI | Tailwind plugin | CSS transitions | Very easy | Rapid prototyping | Free |
-| HeroUI | Tailwind + React Aria | Smooth built-in | Easy | React apps, accessible | Free |
-| Chakra UI | CSS-in-JS (Emotion) | Built-in transitions | Easy | Themed React apps | Free |
-| Flowbite | Tailwind plugin | CSS transitions | Very easy | Multi-framework, business | Free / Pro |
-| Preline UI | Tailwind plugin | CSS + minimal JS | Very easy | Speed-focused builds | Free / Pro |
-| Park UI | Tailwind + Ark UI | Minimal | Medium | Multi-framework, design systems | Free |
-| Origin UI | Tailwind + shadcn | Minimal | Easy (copy-paste) | Max component variety | Free |
-| Headless UI | Custom Tailwind | Custom (Transition) | Medium-Hard | Full design control | Free |
-| Cult UI | Tailwind + shadcn | Modern, subtle | Medium | AI apps, full-stack | Free |
-
----
-
-## Framework Prompts
-
-After the user selects a framework, use the corresponding prompt below. **Adapt it to the user's actual project** — replace generic references with their real file structure, existing routes, and components from `.wolf/anatomy.md`.
-
----
-
-### shadcn/ui
-
-**Stack:** React, Tailwind CSS, Radix UI
-**Install:** `npx shadcn@latest init`
-**Site:** ui.shadcn.com
-
-```
-Build a modern, minimalist landing page using Next.js 14+ (App Router), TypeScript, Tailwind CSS, and shadcn/ui components.
-
-ARCHITECTURE:
-- Use Next.js App Router with server components by default, client components only when interactivity is needed
-- Organize: /app for routes, /components/ui for shadcn primitives, /components/sections for page sections, /lib for utilities
-- Use CSS variables for theming via shadcn's built-in system
-
-DESIGN PRINCIPLES:
-- Minimalist with generous whitespace (py-24 to py-32 section spacing)
-- Max-width container (max-w-6xl mx-auto) with responsive padding
-- Typography hierarchy: text-5xl/6xl hero → text-3xl section titles → text-lg body
-- Muted color palette with ONE bold accent color for CTAs
-- Subtle micro-interactions on hover (scale, opacity transitions)
-- Dark mode support via shadcn's theme provider
-
-SECTIONS TO BUILD:
-1. Navbar — sticky, transparent-to-solid on scroll, logo left, nav center, CTA button right
-2. Hero — large headline (max 8 words), subtext (max 2 lines), primary CTA button + secondary ghost button, optional hero image or abstract illustration
-3. Social proof — logo cloud of 5-6 partner/client logos in grayscale
-4. Features — 3-column bento grid with icon, title, description per card using shadcn Card component
-5. How it works — 3-step numbered process with connecting line
-6. Testimonials — carousel or grid of 3 testimonial cards with avatar, quote, name, role
-7. Pricing — 3-tier pricing table using shadcn Card, highlight the recommended plan with ring/border accent
-8. FAQ — accordion using shadcn Accordion component
-9. CTA — full-width section with headline, subtext, and primary action button
-10. Footer — 4-column grid (brand, product links, company links, legal), copyright at bottom
-
-COMPONENT USAGE:
-- Button (primary, secondary, ghost, outline variants)
-- Card, CardHeader, CardContent, CardFooter
-- Accordion, AccordionItem, AccordionTrigger, AccordionContent
-- Badge for labels/tags
-- Separator for dividers
-- NavigationMenu for navbar
-
-CODE QUALITY:
-- Fully responsive (mobile-first)
-- Semantic HTML (section, nav, main, footer)
-- Accessible (proper aria labels, keyboard navigation)
-- Performant (lazy load images, optimize fonts via next/font)
-- Clean component separation (each section is its own component)
-```
-
----
-
-### Aceternity UI
-
-**Stack:** React, Next.js, Tailwind CSS, Framer Motion
-**Install:** Copy-paste or `npx shadcn@latest add [component]`
-**Site:** ui.aceternity.com
-
-```
-Build a visually stunning, animation-rich landing page using Next.js 14+, TypeScript, Tailwind CSS, and Aceternity UI components with Framer Motion.
-
-ARCHITECTURE:
-- Next.js App Router with client components for animated sections
-- Organize: /app, /components/aceternity (copied components), /components/sections, /lib
-- Install Framer Motion for animation engine
-
-DESIGN PRINCIPLES:
-- Dark theme as primary (bg-black/bg-slate-950 backgrounds)
-- Dramatic contrast with glowing accents (cyan, purple, or emerald)
-- Layered depth via gradients, glows, and glassmorphism
-- Cinematic scroll-triggered animations with staggered reveals
-- Generous padding (py-32+), large typography (text-6xl/7xl hero)
-- Noise/grain texture overlays for visual richness
-
-SECTIONS TO BUILD WITH ACETERNITY COMPONENTS:
-1. Navbar — floating navbar with backdrop blur, animated on scroll
-2. Hero — use Aceternity's "Spotlight" or "Lamp" effect as background, massive headline with TextGenerateEffect or TypewriterEffect, gradient text on key words, two CTAs with HoverBorderGradient buttons
-3. Logo cloud — use InfiniteMovingCards for auto-scrolling partner logos
-4. Features — BentoGrid layout with animated cards, each card has BackgroundGradient or CardSpotlight hover effect
-5. Product showcase — use Aceternity's 3DCard or ParallaxScroll for product screenshots/mockups
-6. Testimonials — AnimatedTestimonials or InfiniteMovingCards with quote, avatar, name
-7. How it works — use TracingBeam component for a connected step-by-step flow
-8. Pricing — dark cards with GlowingStarsBackground, highlighted tier has animated border (MovingBorder)
-9. CTA — full-width with BackgroundBeams or Meteors effect behind headline and button
-10. Footer — clean 4-column layout with subtle separator
-
-ANIMATION GUIDELINES:
-- Page load: stagger hero elements (title → subtitle → buttons) with 0.15s delay each
-- Scroll: use Framer Motion's whileInView for reveal animations (fade up + slight scale)
-- Hover: cards lift (translateY -4px) with glow intensification
-- Keep animations performant (use transform/opacity only, will-change where needed)
-- Respect prefers-reduced-motion
-
-CODE QUALITY:
-- Mobile-first responsive design
-- Lazy load heavy animation components
-- Each section is a standalone component file
-- Accessible despite heavy animation (aria labels, focus states)
-```
-
----
-
-### Magic UI
-
-**Stack:** React, TypeScript, Tailwind CSS, Motion (Framer Motion)
-**Install:** `npx shadcn@latest add [component]` (shadcn CLI compatible)
-**Site:** magicui.design
-
-```
-Build a polished, trend-forward SaaS landing page using Next.js 14+, TypeScript, Tailwind CSS, and Magic UI animated components.
-
-ARCHITECTURE:
-- Next.js App Router, server components where possible
-- Magic UI components installed via shadcn CLI into /components/magicui
-- Section components in /components/sections
-- Shared config in /lib (cn utility, site config)
-
-DESIGN PRINCIPLES:
-- Clean and modern, inspired by Linear/Vercel aesthetic
-- Light or dark mode with smooth toggle transition
-- Restrained animation — purposeful motion that guides attention, not distracts
-- High contrast text, muted backgrounds (slate-50 light / slate-950 dark)
-- Monospace or geometric sans-serif for headings, clean sans for body
-- ONE signature color (blue-500, violet-500, or emerald-500) for accents
-
-SECTIONS TO BUILD WITH MAGIC UI COMPONENTS:
-1. Navbar — clean horizontal nav, use MagicUI ShimmerButton for primary CTA
-2. Hero — large headline with AnimatedGradientText on key phrase, NumberTicker for a live stat ("10,000+ users"), DotPattern or GridPattern as subtle background, two buttons (ShimmerButton primary + outline secondary)
-3. Social proof — Marquee component for auto-scrolling logos horizontally
-4. Features — use MagicCard components in a 3-column grid, each with icon + title + description, subtle hover glow effect
-5. Bento showcase — BentoGrid layout showing product capabilities, mix of large and small tiles with different content types (text, mini-demos, stats)
-6. Metrics — AnimatedList showing live activity feed OR NumberTicker showing key stats (users, uptime, speed)
-7. Testimonials — Marquee of testimonial cards (vertical or horizontal scroll)
-8. Pricing — 3 tiers with clean card design, NeonGradientCard for featured plan, BorderBeam on hover
-9. CTA — centered layout with AnimatedShinyText headline, Particles or Meteors background effect
-10. Footer — minimal 3-4 column grid, muted text, social icons
-
-ANIMATION STRATEGY:
-- Use BlurIn / FadeIn for section entrance animations
-- NumberTicker for any statistics or metrics
-- Marquee for any horizontally scrolling content
-- Keep transitions under 600ms, use ease-out curves
-- Mobile: reduce or disable particle/meteor effects for performance
-
-CODE QUALITY:
-- Fully responsive with mobile breakpoints
-- Semantic HTML throughout
-- next/font for optimized typography
-- Image optimization via next/image
-- Component-per-section architecture
-```
-
----
-
-### DaisyUI
-
-**Stack:** Tailwind CSS plugin (framework-agnostic)
-**Install:** `npm i -D daisyui` + add to tailwind.config
-**Site:** daisyui.com
-
-```
-Build a clean, professional landing page using Tailwind CSS and DaisyUI component classes.
-
-ARCHITECTURE:
-- Framework of choice with Tailwind CSS + DaisyUI plugin
-- Use DaisyUI's semantic class system (btn, card, hero, navbar, etc.)
-- Select a DaisyUI theme (or create custom) in tailwind.config.js
-- Organize by sections in /components/sections
-
-DESIGN PRINCIPLES:
-- Pick ONE DaisyUI theme as base (e.g., "winter" for clean light, "night" for dark, "corporate" for professional)
-- Customize theme colors in tailwind.config to match brand
-- Minimalist layout with clean spacing (p-8 to p-16 sections)
-- Let DaisyUI's built-in design system handle consistency
-- Typography via DaisyUI's prose class for content sections
-
-SECTIONS TO BUILD WITH DAISYUI CLASSES:
-1. Navbar — "navbar" component with "dropdown" for mobile menu, "btn btn-primary" for CTA
-2. Hero — "hero" component with "hero-content", large headline, subtext, "btn btn-primary" + "btn btn-ghost"
-3. Social proof — logo row using "flex" with "opacity-50 grayscale" on images
-4. Features — "card" components in a responsive grid, each with "card-body", uses "bg-base-200" for contrast
-5. Stats — "stats" component with "stat" items showing key metrics
-6. Steps — "steps" component (horizontal on desktop, vertical on mobile)
-7. Testimonials — "chat" component styled as testimonials OR "card" grid with "avatar"
-8. Pricing — "card" components with "badge badge-primary" for recommended plan
-9. FAQ — "collapse" or "collapse-plus" components for expandable Q&A
-10. Footer — "footer" component with 3-4 columns, "footer-title" for headings
-
-CODE QUALITY:
-- Fully responsive using Tailwind breakpoints
-- Zero custom CSS needed (DaisyUI handles it)
-- Accessible by default (DaisyUI follows ARIA patterns)
-- Fast load times (CSS-only, no JS shipped)
-- Works with any framework or plain HTML
-```
-
----
-
-### HeroUI (formerly NextUI)
-
-**Stack:** React, Tailwind CSS, React Aria
-**Install:** `npm i @heroui/react`
-**Site:** heroui.com
-
-```
-Build an elegant, accessible landing page using Next.js 14+, TypeScript, Tailwind CSS, and HeroUI components.
-
-ARCHITECTURE:
-- Next.js App Router with HeroUI Provider wrapping the app
-- Import only needed components from @heroui/react (tree-shakeable)
-- Organize: /app, /components/sections, /lib
-- Use HeroUI's built-in theme system for consistent styling
-
-DESIGN PRINCIPLES:
-- Soft, modern aesthetic with rounded corners and smooth surfaces
-- Light mode primary with dark mode support via HeroUI's theme toggle
-- Subtle shadows and blur effects (HeroUI's built-in elevation system)
-- Clean sans-serif typography, generous line heights
-- Smooth transitions on all interactive elements (HeroUI provides these by default)
-
-SECTIONS TO BUILD WITH HEROUI COMPONENTS:
-1. Navbar — HeroUI Navbar with NavbarBrand, NavbarContent, NavbarItem, NavbarMenuToggle for mobile
-2. Hero — large headline, descriptive subtext, Button (color="primary" size="lg") + Button (variant="bordered")
-3. Social proof — Avatar group for client logos or Chip components for trust badges
-4. Features — Card components in grid, each with CardHeader, CardBody, use Divider between sections
-5. Product demo — Tabs component to show different product views/features interactively
-6. Testimonials — Card grid with User component (avatar + name + role) inside each card
-7. Pricing — Card components with Chip for "Popular" badge, Listbox for feature lists
-8. FAQ — Accordion component with AccordionItem for each question
-9. CTA — centered section with Input + Button combo for email capture
-10. Footer — clean grid with Link components, Divider above copyright
-
-CODE QUALITY:
-- Fully responsive with HeroUI's responsive props
-- Accessible by default (React Aria foundation)
-- Server-side rendering compatible
-- Optimized bundle (import individual components)
-- TypeScript strict mode
-```
-
----
-
-### Chakra UI
-
-**Stack:** React, Emotion (CSS-in-JS)
-**Install:** `npm i @chakra-ui/react`
-**Site:** chakra-ui.com
-
-```
-Build a clean, accessible landing page using Next.js 14+, TypeScript, and Chakra UI v3.
-
-ARCHITECTURE:
-- Next.js App Router with ChakraProvider at root
-- Use Chakra's design tokens and theme extension for brand customization
-- Organize: /app, /components/sections, /theme (custom theme config)
-
-DESIGN PRINCIPLES:
-- Clean and warm aesthetic using Chakra's polished defaults
-- Consistent spacing using Chakra's space scale (4, 8, 12, 16, 20, 24)
-- Typography: use Chakra's Heading and Text components
-- Color mode support (light/dark) via useColorMode hook
-- Accessible-first: every component follows WAI-ARIA by default
-
-SECTIONS TO BUILD WITH CHAKRA COMPONENTS:
-1. Navbar — Flex with HStack, IconButton for mobile menu, Button for CTA
-2. Hero — VStack centered, Heading size="4xl", Text, HStack with two Buttons
-3. Social proof — HStack/Wrap of grayscale Image components
-4. Features — SimpleGrid columns={{base:1, md:3}} of VStack cards with Icon, Heading, Text
-5. Stats — Stat component group with StatLabel, StatNumber, StatHelpText
-6. Testimonials — SimpleGrid of Card with Avatar, Text (quote), Heading (name)
-7. Pricing — SimpleGrid of Card, Badge for "Popular", List for features
-8. FAQ — Accordion with AccordionItem, AccordionButton, AccordionPanel
-9. CTA — Box with bg gradient, VStack centered, Heading, Text, Button
-10. Footer — SimpleGrid columns={{base:2, md:4}} with VStack, Heading, Link
-
-THEME EXTENSION:
-const theme = extendTheme({
-  colors: { brand: { 50: '...', 500: '...', 900: '...' } },
-  fonts: { heading: 'Your Font', body: 'Your Font' },
-  components: { Button: { defaultProps: { colorScheme: 'brand' } } }
-})
-
-CODE QUALITY:
-- Fully responsive using Chakra's responsive array/object syntax
-- Dark mode ready with useColorModeValue
-- Accessible by default
-- TypeScript throughout with proper prop types
-```
-
----
-
-### Flowbite
-
-**Stack:** Tailwind CSS (React, Vue, Svelte, Angular)
-**Install:** `npm i flowbite flowbite-react`
-**Site:** flowbite.com
-
-```
-Build a professional, conversion-optimized landing page using Next.js 14+, Tailwind CSS, and Flowbite React components.
-
-ARCHITECTURE:
-- Next.js App Router with Flowbite React components
-- Import from flowbite-react (Button, Card, Navbar, Footer, etc.)
-- Flowbite Tailwind plugin in tailwind.config for interactive styles
-
-DESIGN PRINCIPLES:
-- Business-professional aesthetic (clean, trustworthy, conversion-focused)
-- Cool neutral palette (slate/gray) with strong brand accent
-- Focus on readability and clear information hierarchy
-
-SECTIONS TO BUILD WITH FLOWBITE COMPONENTS:
-1. Navbar — Flowbite Navbar with Navbar.Brand, Navbar.Toggle, Navbar.Collapse
-2. Hero — Jumbotron-style, large Heading, Button group
-3. Social proof — row of client logos
-4. Features — Card components in responsive grid with icon badge, title, description
-5. Content — alternating image + text rows
-6. Testimonials — Blockquote or Card with Rating component for stars
-7. Pricing — Card with List for features, Badge for highlighted plan
-8. FAQ — Accordion component
-9. Newsletter CTA — TextInput + Button in a styled Banner
-10. Footer — Flowbite Footer with Footer.LinkGroup, Footer.Brand, Footer.Copyright
-
-CODE QUALITY:
-- Fully responsive (components are responsive by default)
-- Accessible (follows WAI-ARIA)
-- Works server-side with Next.js
-- Production-ready component patterns
-```
-
----
-
-### Preline UI
-
-**Stack:** Tailwind CSS (HTML-first, React/Vue plugins)
-**Install:** `npm i preline` + add plugin to tailwind.config
-**Site:** preline.co
-
-```
-Build a sleek, modern landing page using Next.js 14+, Tailwind CSS, and Preline UI components.
-
-ARCHITECTURE:
-- Next.js App Router with Preline's Tailwind plugin
-- Use Preline's HTML component patterns (class-based, minimal JS)
-- Import preline JS for interactive components (dropdowns, modals, accordions)
-
-DESIGN PRINCIPLES:
-- Modern SaaS aesthetic (clean lines, airy spacing, professional)
-- Neutral base (white/slate) with vibrant accent for CTAs
-- Large section padding (py-16 to py-24)
-
-SECTIONS TO BUILD WITH PRELINE PATTERNS:
-1. Navbar — header component with mega menu support, sticky on scroll
-2. Hero — centered or split layout, large headline with gradient text, two CTA buttons
-3. Social proof — logo ticker or static row with grayscale filter
-4. Features — icon + text cards in 3-column grid
-5. Tabs showcase — tab component showing different product features per tab
-6. Testimonials — grid or slider of testimonial cards
-7. Pricing — pricing table pattern with toggle for monthly/annual
-8. Stats — counter section with large numbers + labels
-9. FAQ — accordion component with smooth expand/collapse
-10. CTA + Footer — email input + button CTA above multi-column footer
-
-CODE QUALITY:
-- Fully responsive with Tailwind breakpoints
-- Accessible (follows ARIA standards)
-- Lightweight (CSS + minimal JS)
-- Works with any framework via HTML classes
-```
-
----
-
-### Park UI
-
-**Stack:** React/Vue/Solid, Ark UI (headless), Tailwind CSS
-**Install:** Copy-paste components (shadcn-style)
-**Site:** park-ui.com
-
-```
-Build a refined, design-system-driven landing page using Next.js 14+, TypeScript, Tailwind CSS, and Park UI components.
-
-ARCHITECTURE:
-- Next.js App Router with Park UI components (Ark UI + Tailwind CSS)
-- Copy-paste component installation (like shadcn)
-- Organize: /app, /components/ui (Park UI primitives), /components/sections
-
-DESIGN PRINCIPLES:
-- Polished and systematic (design-system quality)
-- Neutral, sophisticated palette with deliberate accent usage
-- Consistent spacing and sizing via Park UI's token scale
-- Light/dark mode via Park UI's built-in theme tokens
-
-SECTIONS TO BUILD WITH PARK UI COMPONENTS:
-1. Navbar — navigation components, clean horizontal layout, mobile drawer
-2. Hero — Heading + Text with proper token sizing, Button pair (solid + outline)
-3. Social proof — subtle logo row with muted styling
-4. Features — Card components in grid with Icon, Heading, Text
-5. Tabs showcase — Tabs component for interactive product feature display
-6. Testimonials — Card-based layout with Avatar + quote
-7. Pricing — Card grid with Badge for recommended tier
-8. FAQ — Accordion component (Ark UI primitive, styled via Park UI)
-9. CTA — centered section with Input + Button
-10. Footer — grid layout with Link groups and Separator
-
-CODE QUALITY:
-- Fully responsive and accessible
-- Ark UI headless primitives for rock-solid accessibility
-- TypeScript strict mode
-- Component-per-section architecture
-```
-
----
-
-### Origin UI
-
-**Stack:** React, Tailwind CSS, shadcn/ui foundation
-**Install:** Copy-paste (400+ free components)
-**Site:** originui.com
-
-```
-Build a polished, component-rich landing page using Next.js 14+, TypeScript, Tailwind CSS, and Origin UI components (built on shadcn/ui).
-
-ARCHITECTURE:
-- Next.js App Router with shadcn/ui base + Origin UI component variants
-- Copy-paste Origin UI components into /components/ui
-- Origin UI extends shadcn patterns with 400+ variant options
-
-DESIGN PRINCIPLES:
-- Professional and versatile (many style variants per component)
-- Pick a cohesive subset of variants that match your brand
-- Consistent spacing and typography aligned with shadcn's token system
-- Focus on component quality and consistency over flashy animation
-
-SECTIONS TO BUILD:
-1. Navbar — choose from Origin UI's multiple navbar variants
-2. Hero — select a hero variant (centered, split, with background pattern)
-3. Social proof — logo cloud variant
-4. Features — pick feature section variant (grid, list, bento, with images)
-5. Content — alternating image/text sections
-6. Testimonials — choose testimonial variant (cards, quotes, carousel)
-7. Pricing — select pricing table variant (simple, comparison, with toggle)
-8. FAQ — accordion variant
-9. CTA — pick CTA variant (centered, with input, split layout)
-10. Footer — choose footer variant (simple, multi-column, with newsletter)
-
-CODE QUALITY:
-- Fully responsive (all components are mobile-first)
-- Accessible (shadcn/ui + Radix UI foundation)
-- TypeScript throughout
-- Minimal dependencies
-```
-
----
-
-### Headless UI
-
-**Stack:** React or Vue, Tailwind CSS (by Tailwind Labs)
-**Install:** `npm i @headlessui/react`
-**Site:** headlessui.com
-
-```
-Build a custom-designed, fully accessible landing page using Next.js 14+, TypeScript, Tailwind CSS, and Headless UI for interactive components.
-
-ARCHITECTURE:
-- Next.js App Router with Tailwind CSS for all styling
-- Headless UI only for interactive behavior (menus, dialogs, tabs, disclosure, transitions)
-- All visual design is custom Tailwind — Headless UI provides zero styling
-- Organize: /app, /components/ui (custom-styled wrappers), /components/sections
-
-DESIGN PRINCIPLES:
-- Completely custom aesthetic — you control every pixel
-- Minimalist, editorial-quality design (think Stripe, Linear, Vercel)
-- Monochrome base with ONE signature accent color
-- Large whitespace, precise typography, meticulous alignment
-- Every interactive element is keyboard-navigable and screen-reader friendly
-
-SECTIONS TO BUILD:
-1. Navbar — custom with Headless UI Popover for dropdowns, Disclosure for mobile menu
-2. Hero — pure Tailwind, dramatic typography, clean CTAs
-3. Social proof — pure Tailwind logo row
-4. Features — custom card grid, optional Tab component for tabbed showcase
-5. Product showcase — TabGroup for interactive product views
-6. Testimonials — pure Tailwind card grid
-7. Pricing — RadioGroup for plan selection, Switch for monthly/annual toggle
-8. FAQ — Disclosure component for accessible expand/collapse
-9. CTA — pure Tailwind centered section
-10. Footer — pure Tailwind grid layout
-
-HEADLESS UI COMPONENTS TO LEVERAGE:
-- Popover — navbar dropdowns
-- Disclosure — mobile menu, FAQ items
-- Dialog — modals/overlays
-- Transition — smooth enter/leave animations
-- RadioGroup — plan selection
-- Switch — toggles
-- TabGroup — tabbed content
-
-CODE QUALITY:
-- 100% accessible (Headless UI's core guarantee)
-- Fully responsive custom Tailwind design
-- Keyboard navigation on all interactive elements
-- TypeScript with proper generics
-- Zero design dependencies — total creative control
-```
-
----
-
-### Cult UI
-
-**Stack:** React, Next.js, Tailwind CSS, shadcn/ui foundation
-**Install:** Copy-paste or CLI
-**Site:** cult-ui.com
-
-```
-Build a modern, AI-forward landing page using Next.js 14+, TypeScript, Tailwind CSS, and Cult UI components.
-
-ARCHITECTURE:
-- Next.js App Router with Cult UI components (extends shadcn/ui)
-- Full-stack ready (Cult UI includes backend-aware patterns)
-- Use Cult UI's AI-specific blocks if building an AI product
-
-DESIGN PRINCIPLES:
-- Tech-forward, developer-centric aesthetic
-- Dark mode primary with high-contrast accents
-- Modern gradients and subtle glow effects
-- Clean code-like typography (mono fonts for accents)
-- Purposeful animation that communicates AI/tech sophistication
-
-SECTIONS TO BUILD:
-1. Navbar — modern floating nav with glass effect
-2. Hero — bold headline with animated text effect, live demo or interactive element, gradient mesh background
-3. Features — AI blocks for feature cards, animated icons or micro-interactions
-4. Live demo — interactive component showing product in action
-5. Code showcase — syntax-highlighted code examples using Cult UI's code block components
-6. Testimonials — modern card layout with subtle animation
-7. Pricing — clean tier comparison with feature matrix
-8. Open source / community — GitHub stars counter, contributor avatars
-9. CTA — compelling action section with email input or waitlist signup
-10. Footer — developer-friendly footer with docs links, API reference, status page
-
-CODE QUALITY:
-- Full-stack patterns (API routes + client components)
-- TypeScript strict mode throughout
-- Accessible interactive components
-- Production-ready architecture patterns
-```
diff --git a/.wolf/suggestions.json b/.wolf/suggestions.json
deleted file mode 100644
index 769f42b..0000000
--- a/.wolf/suggestions.json
+++ /dev/null
@@ -1,4 +0,0 @@
-{
-  "suggestions": [],
-  "generated_at": null
-}
\ No newline at end of file
diff --git a/.wolf/token-ledger.json b/.wolf/token-ledger.json
deleted file mode 100644
index 8ffe6a6..0000000
--- a/.wolf/token-ledger.json
+++ /dev/null
@@ -1,261 +0,0 @@
-{
-  "version": 1,
-  "created_at": "2026-06-03T13:15:37.485Z",
-  "lifetime": {
-    "total_tokens_estimated": 21123,
-    "total_reads": 14,
-    "total_writes": 11,
-    "total_sessions": 4,
-    "anatomy_hits": 4,
-    "anatomy_misses": 10,
-    "repeated_reads_blocked": 0,
-    "estimated_savings_vs_bare_cli": 800
-  },
-  "sessions": [
-    {
-      "id": "session-2026-06-03-1516",
-      "started": "2026-06-03T13:16:36.725Z",
-      "ended": "2026-06-03T13:16:48.722Z",
-      "reads": [],
-      "writes": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/CLAUDE.md",
-          "tokens_estimated": 628,
-          "action": "create"
-        }
-      ],
-      "totals": {
-        "input_tokens_estimated": 0,
-        "output_tokens_estimated": 628,
-        "reads_count": 0,
-        "writes_count": 1,
-        "repeated_reads_blocked": 0,
-        "anatomy_lookups": 0
-      }
-    },
-    {
-      "id": "session-2026-06-03-1516",
-      "started": "2026-06-03T13:16:36.725Z",
-      "ended": "2026-06-03T13:17:38.452Z",
-      "reads": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/CLAUDE.md",
-          "tokens_estimated": 550,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        }
-      ],
-      "writes": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/CLAUDE.md",
-          "tokens_estimated": 628,
-          "action": "create"
-        }
-      ],
-      "totals": {
-        "input_tokens_estimated": 550,
-        "output_tokens_estimated": 628,
-        "reads_count": 1,
-        "writes_count": 1,
-        "repeated_reads_blocked": 0,
-        "anatomy_lookups": 1
-      }
-    },
-    {
-      "id": "session-2026-06-03-1516",
-      "started": "2026-06-03T13:16:36.725Z",
-      "ended": "2026-06-03T13:30:44.458Z",
-      "reads": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/CLAUDE.md",
-          "tokens_estimated": 550,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/index.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/NETgazet-07_okt2024/page-01.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/NETgazet-07_okt2024/index.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        }
-      ],
-      "writes": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/CLAUDE.md",
-          "tokens_estimated": 628,
-          "action": "create"
-        },
-        {
-          "file": "/home/seppe4/.claude/plans/in-the-example-folder-immutable-rossum.md",
-          "tokens_estimated": 2414,
-          "action": "create"
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/main.py",
-          "tokens_estimated": 2847,
-          "action": "create"
-        }
-      ],
-      "totals": {
-        "input_tokens_estimated": 550,
-        "output_tokens_estimated": 5889,
-        "reads_count": 4,
-        "writes_count": 3,
-        "repeated_reads_blocked": 0,
-        "anatomy_lookups": 1
-      }
-    },
-    {
-      "id": "session-2026-06-03-1516",
-      "started": "2026-06-03T13:16:36.725Z",
-      "ended": "2026-06-03T13:34:03.911Z",
-      "reads": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/CLAUDE.md",
-          "tokens_estimated": 550,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/index.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/NETgazet-07_okt2024/page-01.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/NETgazet-07_okt2024/index.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        }
-      ],
-      "writes": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/CLAUDE.md",
-          "tokens_estimated": 628,
-          "action": "create"
-        },
-        {
-          "file": "/home/seppe4/.claude/plans/in-the-example-folder-immutable-rossum.md",
-          "tokens_estimated": 2414,
-          "action": "create"
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/main.py",
-          "tokens_estimated": 2847,
-          "action": "create"
-        }
-      ],
-      "totals": {
-        "input_tokens_estimated": 550,
-        "output_tokens_estimated": 5889,
-        "reads_count": 4,
-        "writes_count": 3,
-        "repeated_reads_blocked": 0,
-        "anatomy_lookups": 1
-      }
-    },
-    {
-      "id": "session-2026-06-03-1516",
-      "started": "2026-06-03T13:16:36.725Z",
-      "ended": "2026-06-03T13:35:12.255Z",
-      "reads": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/CLAUDE.md",
-          "tokens_estimated": 550,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/index.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/NETgazet-07_okt2024/page-01.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/NETgazet-07_okt2024/index.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        }
-      ],
-      "writes": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/CLAUDE.md",
-          "tokens_estimated": 628,
-          "action": "create"
-        },
-        {
-          "file": "/home/seppe4/.claude/plans/in-the-example-folder-immutable-rossum.md",
-          "tokens_estimated": 2414,
-          "action": "create"
-        },
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/main.py",
-          "tokens_estimated": 2847,
-          "action": "create"
-        }
-      ],
-      "totals": {
-        "input_tokens_estimated": 550,
-        "output_tokens_estimated": 5889,
-        "reads_count": 4,
-        "writes_count": 3,
-        "repeated_reads_blocked": 0,
-        "anatomy_lookups": 1
-      }
-    },
-    {
-      "id": "session-2026-06-03-1555",
-      "started": "2026-06-03T13:55:38.248Z",
-      "ended": "2026-06-03T13:56:28.840Z",
-      "reads": [
-        {
-          "file": "/home/seppe4/vscode_projects/netgazet/output/index.html",
-          "tokens_estimated": 0,
-          "was_repeated": false,
-          "anatomy_had_description": false
-        }
-      ],
-      "writes": [],
-      "totals": {
-        "input_tokens_estimated": 0,
-        "output_tokens_estimated": 0,
-        "reads_count": 1,
-        "writes_count": 0,
-        "repeated_reads_blocked": 0,
-        "anatomy_lookups": 0
-      }
-    }
-  ],
-  "daemon_usage": [],
-  "waste_flags": [],
-  "optimization_report": {
-    "last_generated": null,
-    "patterns": []
-  }
-}
\ No newline at end of file