luum-home/luum-cognitive-os/audit-integrity

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

'Use when you need this Cognitive OS skill: Symlink-aware integrity audit

Install

npx vskill@latest install luum-home/luum-cognitive-os/audit-integrity

SKILL.md

Purpose

Standardized integrity audit that correctly handles symlinks. Replaces ad-hoc [ -f ] checks that agents improvise (and get wrong — a prior audit reported 20 ghost hooks that were actually valid symlinks).

Invocation

/audit-integrity [--scope hooks|libs|skills|all] [--fix]

What to Do

Step 1: Source the file checker
bash
source hooks/_lib/file_checker.sh
Step 2: For each component type, cross-reference settings.json with disk

Hooks:

bash
# For each hook in .claude/settings.json:
#   1. Extract the path from the command field
#   2. Use file_exists_strict (not [ -f ]) to check
#   3. If symlink: resolve with resolve_path, report both paths
#   4. If broken symlink: use is_broken_symlink to detect
#   5. Classify: ALIVE (exists + registered), DORMANT (exists + not registered),
#      GHOST (registered + missing), BROKEN_SYMLINK (registered + broken target)

Libs:

bash
# For each .py in lib/:
#   1. Check if imported by any hook or other lib
#   2. Resolve symlinks before checking imports
#   3. Classify: ALIVE (has callers), DEAD (no callers), BROKEN_CHAIN (calls missing lib)

Skills:

bash
# For each SKILL.md in skills/ and packages/*/skills/:
#   1. Check if listed in CATALOG.md
#   2. Classify: ACTIVE (has content), STUB (empty/placeholder), ORPHANED (not in catalog)
Step 3: Report

Output a structured table:

Component Type | Total | Alive | Dead | Ghost | Broken Symlink
hooks          |    48 |    48 |    0 |     0 |              0
libs           |    95 |    55 |    34|     0 |              6
skills         |   120 |   120 |    0 |     0 |              0
Step 4: If --fix
  • Remove GHOST entries from settings.json
  • Report BROKEN_SYMLINK targets for manual resolution
  • Do NOT delete files — only clean config references

Rules

  • ALWAYS use hooks/_lib/file_checker.sh functions, NEVER raw [ -f ]
  • ALWAYS resolve symlinks with readlink -f before classifying as missing
  • Report both the symlink path AND the resolved target path
  • When counting, count the symlink as ONE component (not symlink + target)
  • Cross-validate findings before reporting — if a file appears missing, verify with ls -la and readlink -f

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/luum-home/luum-cognitive-os/audit-integrity/badge)](https://verified-skill.com/skills/luum-home/luum-cognitive-os/audit-integrity)

Something wrong with this skill or its page? Tell us.