doc-audit
Skill4 starsChanged 12 days agoMITView on GitHub
8-phase documentation drift audit across all docs, agent instructions, and config files. Use when checking for documentation drift, stale paths/counts, or inconsistencies between code and docs.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- blueclover22/mw_agent_kittheir own version, first seen Nov 4, 2026
- sunitghub/canon-skillstheir own version, first seen Oct 22, 2026
- Sprintlaw/legal-skillstheir own version, first seen Oct 17, 2026
- jrittelmeyer/ai-dev-kittheir own version, first seen Oct 15, 2026
- bekalpaslan/promptlinetheir own version, first seen Oct 13, 2026
- tachyon-zcash/ragutheir own version, first seen Oct 8, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- PackmindHub/packmind★ 321same name
- tachyon-zcash/ragu★ 61same name
- bekalpaslan/promptline★ 11same name
- sunitghub/canon-skills★ 9same name
- Wubabalala/claude-skills★ 4same name
- ApurvBazari/claude-plugins★ 3same name
- blueclover22/mw_agent_kit★ 1same name
- jarosser06/drift★ 1same name
- jrittelmeyer/ai-dev-kit★ 1same name
- s-frantz/agent-memory-trellis★ 1same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- architecture-changeSkill
- brainstormingSkill
- doc-auditSkill
- feature-deliverySkill
- find-skillsSkill
- frontend-designSkill
- hotfixSkill
- jules-tasksSkill
- qa-auditSkill
- release-readinessSkill
- requesting-code-reviewSkill
- setup-repoSkill
- skill-creatorSkill
- systematic-debuggingSkill
- using-superpowersSkill
- writing-plansSkill
- architecture-changeSkill
- brainstormingSkill
- feature-deliverySkill
- find-skillsSkill
- frontend-designSkill
- hotfixSkill
- jules-tasksSkill
- qa-auditSkill
- release-readinessSkill
- requesting-code-reviewSkill
- setup-repoSkill
- skill-creatorSkill
- systematic-debuggingSkill
- using-superpowersSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Principle: Use existing scripts instead of ad-hoc grep commands.
- Distinctive: line 63
Every real file/directory must appear in all file maps.
- Distinctive: line 117
All automated checks from Phase 2 cover config consistency.
- Distinctive: line 125
Verify all files/directories in the repo are listed in the agent file maps (see Phase 0).
- Distinctive: line 129
All agent instruction files must agree on:
- Distinctive: line 150
If any doc fixes were made:
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Documentation Audit
Comprehensive audit to ensure zero documentation drift across ALL docs, agent instructions, and config files.
Principle: Use existing scripts instead of ad-hoc grep commands. Never create temporary audit scripts — all checks are covered by the repo's tooling and test suite.
Complete Documentation Inventory
Layer 1: Primary Docs
<!-- SETUP: Replace with your project's actual doc structure. -->| File | Drift-sensitive fields |
docs/README.md | File tree, asset paths, tech stack |
docs/ARCHITECTURE.md | File paths, component structure |
docs/CHANGELOG.md | Missing entries for recent changes |
[FILL: docs/CONFIG-REFERENCE.md] | [FILL: Schema tables, field descriptions] |
docs/decisions/ | ADR accuracy vs. current implementation |
Layer 2: Agent Instructions
| File | Drift-sensitive fields |
AGENTS.md | File structure (paths), coding rules |
CLAUDE.md | File map (paths), key patterns |
.github/copilot-instructions.md | Key files table (paths), always/never rules |
.agent/rules/coding-standards.md | Rules, path conventions |
| [FILL: Additional agent instruction files] | [FILL: Drift-sensitive fields] |
Layer 3: Root-Level Files
| File | Drift-sensitive fields |
README.md | File paths, quickstart instructions |
| [FILL: Add project-specific root-level files] | [FILL: Drift-sensitive fields] |
Phase 0 — File Tree Completeness (Structural Drift)
Why this is Phase 0: Missing files in file maps is the #1 drift source. Check this first.
Compare the actual file tree against every file-map section in agent instruction files and docs:
- List actual files:
ls src/,ls config/,ls docs/ - Cross-check against file maps in:
| File | Section name |
AGENTS.md | ## File Structure |
CLAUDE.md | ## File Map |
[FILL: docs/README.md] | [FILL: Section name for file tree] |
- Every real file/directory must appear in all file maps. Flag any missing entries.
Phase 1 — Identify What Changed
git diff --stat
git log --oneline -10Classify the change type:
- Config change → schema, examples, stats references may be stale
- UI/layout change → styling guide, layout constraints may be stale
- New feature → user flow, architecture, changelog, roadmap may be stale
- File added/removed/renamed → file trees, path references may be stale
- Agent rule change → must propagate to ALL agent instruction files
Phase 2 — Run Automated Drift Checks
Do not use ad-hoc grep commands or create temporary scripts for checks that existing tooling already covers.
# Run all automated tests
npm test
# [FILL: Add any project-specific drift/stats scripts here]Verify policy alignment:
- Agent docs do not hardcode mutable totals as static source-of-truth values
- If a snapshot number is documented, it is clearly labeled with snapshot context/date
Phase 3 — Verify Path Conventions
# Find references to potentially stale paths
grep -rn "[FILL: old-path-prefix]" docs/ .agent/ .claude/ .github/ AGENTS.md CLAUDE.md --include="*.md"Current correct conventions:
- [FILL: Path convention 1 — e.g. "No leading
/or./in asset paths"] - [FILL: Path convention 2 — e.g. "Assets at
assets/{name}.ext"]
Phase 4 — Verify Config ↔ Code Consistency
Use existing tooling — do not write ad-hoc scripts for these checks.
All automated checks from Phase 2 cover config consistency. If they all pass, this phase is done.
Phase 5 — Cross-Check Agent Files
5a. File map sync (structural)
Verify all files/directories in the repo are listed in the agent file maps (see Phase 0).
5b. Fact consistency
All agent instruction files must agree on:
| Fact | Must match across |
| Coding rules | AGENTS.md, CLAUDE.md, copilot-instructions.md, coding-standards.md |
| Security requirements | AGENTS.md, CLAUDE.md, copilot-instructions.md, coding-standards.md |
| [FILL: Project-specific fact] | [FILL: Which files must agree] |
Phase 6 — Workflow & Skill Consistency
.agent/workflows/doc-audit.md— This workflow is itself still accurate? (meta-audit).claude/skills/doc-audit/SKILL.md— Same as above?.github/pull_request_template.md— Contains explicit docs/ADR/policy alignment gates?- [FILL: Any project-specific workflows to check]
Phase 7 — Update CHANGELOG
If any doc fixes were made:
### Fixed
- Documentation drift: updated [specific counts/paths/conventions] across [N] filesChange → Doc Impact Matrix
<!-- SETUP: Fill in the impact matrix for your project. -->| If you changed… | Update these docs |
| File added/removed/renamed | AGENTS.md (file structure), CLAUDE.md (file map), docs/ARCHITECTURE.md |
| Architecture decision | docs/decisions/ (add new ADR file) |
| New feature / bug fix | docs/CHANGELOG.md |
| Coding rule changed | AGENTS.md, CLAUDE.md, copilot-instructions.md, coding-standards.md |
| [FILL: Project-specific change] | [FILL: Affected docs] |
Drift Severity
| Level | Description | Action |
| 🔴 Critical | Wrong paths, wrong schema, contradictory policy rules | Fix immediately |
| 🟠 High | Missing files in agent file maps, outdated conventions | Fix before next AI-assisted change |
| 🟡 Medium | Missing changelog entry, outdated roadmap | Fix in next doc pass |
| 🟢 Low | Stylistic inconsistency | Fix when convenient |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

