A maintenance workflow for finding outdated, inaccurate, or irrelevant project documentation. It checks documents, referenced files, and code examples for signs that they no longer match the project.

Use it for scheduled or on-demand documentation audits, especially after milestones, major code changes, or onboarding problems.

Documentation can become misleading after refactoring or long periods without review. This workflow identifies stale material and can optionally apply fixes.

How YougLin-dev/Aha-Loop configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to YougLin-dev/Aha-Loop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/YougLin-dev/Aha-Loop/main/.agents/skills/doc-review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/youglin-dev/aha-loop/doc-review/github.svg)](https://agentmods.dev/skills/youglin-dev/aha-loop/doc-review)

Your own site

<a href="https://agentmods.dev/skills/youglin-dev/aha-loop/doc-review"><img src="https://agentmods.dev/badge/skills/youglin-dev/aha-loop/doc-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/youglin-dev/aha-loop/doc-review"><img src="https://agentmods.dev/badge/skills/youglin-dev/aha-loop/doc-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,546 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.01546
Opus 5.5	$0.00013	$0.00618
Sonnet 5.5	$0.00007	$0.00309
Haiku 4.5	$0.00003	$0.00155

Measured 2mo ago against content hash ce102e4a96a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doc-review scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w "%{http_code}" URL

.agents/skills/doc-review/SKILL.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doc Review Skill

Systematically review documentation for staleness, accuracy, and relevance.

The Job

Scan all documentation files
Check for staleness indicators
Verify referenced code/files still exist
Identify outdated content
Generate cleanup report
Optionally apply fixes

When to Use

Scheduled

After each milestone completion
Monthly maintenance cycle
Before major releases

On Demand

When documentation feels outdated
After significant refactoring
When onboarding reveals confusion

Review Process

Step 1: Inventory Documentation

Scan for documentation files:

find . -name "*.md" -not -path "./.git/*" -not -path "./.vendor/*" -not -path "./.worktrees/*"

Common locations:

README.md (root and subdirs)
docs/ directory
AGENTS.md, CLAUDE.md
.claude/skills/*/SKILL.md
knowledge/ directory
scripts/aha-loop/templates/

Step 2: Check Staleness Indicators

For each document, check:

Indicator	Check Method	Threshold
Last modified	`git log -1`	> 30 days
Referenced files	grep + verify	Missing = stale
Code examples	Syntax check	Errors = stale
Version numbers	Compare to actual	Mismatch = stale
Links	HTTP check	Broken = stale

Step 3: Verify Code References

For each code reference in docs:

## Code Reference Check

File: [doc-path]
Reference: `src/main.rs:45-60`
Status: [Exists | Missing | Changed]

If Changed:
- Original: [what doc says]
- Current: [what code shows]
- Action: [Update doc | Flag for review]

Step 4: Check External Links

# Extract URLs
grep -oP 'https?://[^\s)]+' file.md

# Check each URL
curl -s -o /dev/null -w "%{http_code}" URL

Step 5: Generate Report

Create docs-review-report.md:

# Documentation Review Report

**Date:** [YYYY-MM-DD]
**Reviewed:** [N] files
**Issues Found:** [N]

## Summary

| Category | Count |
|----------|-------|
| Stale (>30 days) | [N] |
| Missing References | [N] |
| Broken Links | [N] |
| Outdated Examples | [N] |

## Issues by File

### [file1.md]
- [ ] Line 45: Reference to `src/old.rs` - file no longer exists
- [ ] Line 78: Code example uses deprecated API

### [file2.md]
- [ ] Line 12: Version "1.0.0" should be "2.0.0"
- [ ] Line 56: Broken link to external docs

## Recommended Actions

1. **Delete:** [files that should be removed]
2. **Update:** [files that need content updates]
3. **Review:** [files that need human review]

## Auto-fixable

The following can be auto-fixed:
- [ ] Update version numbers
- [ ] Remove dead links
- [ ] Update file paths

Run `./scripts/aha-loop/doc-cleaner.sh --fix` to apply.

Read the full file on GitHub · 288 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 288 lines · 33 tokens per session scan A ce102e4a96a3

Subscribe to this mod's changes

doc-review is a skill published in the GitHub repository YougLin-dev/Aha-Loop (178 stars, last pushed 9mo ago), licensed MIT. It adds 33 tokens to every session and 1,546 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Writing and docs

doc-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
doc-reviewYougLin-dev/Aha-Loop	Skill	178	9mo ago	MIT	A	33	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

Aha-Loop: Skill for Claude Code