documentation-audit

documentation-audit is a skill for Claude Code, Codex from int2t05/engineering-skills. It costs 77 tokens per session (1,419 once invoked), scanned A, original, MIT.

Documentation review that compares five formal project documents—PRD, TECH, API, FLOW, and TODO—with the current code. It records mismatches and brings the documents back in line with reality.

In plain words
What is it for?
Use it when documentation is stale after a change, when code and specifications disagree, or when these project documents need to be synchronized.
Why use it?
It helps prevent developers from relying on instructions, interfaces, or diagrams that no longer match the software.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the engineering-skills plugin — 48 skills, 1 agent, 1 hook shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/int2t05/engineering-skills/documentation-audit
Any agent
npx skills add int2t05/engineering-skills --skill documentation-audit
Clone the repo
git clone --depth 1 https://github.com/int2t05/engineering-skills

Made for: Claude Code, Codex.

Or install engineering-skills, the plugin that ships this one along with the rest of its 48 skills, 1 agent, 1 hook.

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.

agentmods badge for documentation-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/int2t05/engineering-skills/documentation-audit.svg)](https://agentmods.dev/skills/int2t05/engineering-skills/documentation-audit)
Your own site
<a href="https://agentmods.dev/skills/int2t05/engineering-skills/documentation-audit"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/documentation-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,419 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00077 $0.01419
Opus 5 $0.00039 $0.00709
Sonnet 5 $0.00015 $0.00284
Haiku 4.5 $0.00008 $0.00142

Measured 5d ago against content hash 77a83efb54c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-audit scanned grade A with 0 findings 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 5d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/09-operate/documentation-audit/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Audit

Sync the five formal docs (PRD/TECH/API/FLOW/TODO) to the code, then produce an audit report. Documentation must reflect reality — this skill brings drifted docs back into alignment and records what changed.

When to use

  • A formal doc (PRD/TECH/API/FLOW/TODO) contradicts the current code
  • Documentation is stale or out of sync after a feature ship
  • Manual request to synchronize all documentation with the codebase
  • Writing new documentation from scratch (see references/writing-docs.md)

Not for: open source GitHub presence polishing (use oss-polish); designing API contracts (use api-design); writing the PRD/TECH themselves (use spec/architecture).

Steps

1. Discovery — locate the five formal docs and code structure

Find every formal doc and map the codebase layout so later steps know where to look.

# Locate the five formal docs (project-level)
ls docs/PRD.md docs/TECH.md docs/TODO.md docs/API/*.md docs/FLOW/*.md 2>/dev/null
# Version-level variants (if multi-version project)
ls docs/v*/*.md 2>/dev/null
# Detect API framework for the API drift step
grep -Ei "express|fastify|@nestjs|fastapi|flask|django|gin|echo" package.json requirements.txt go.mod 2>/dev/null

Record which docs exist and which are missing. Missing docs are gaps to flag — not to create here (creation belongs to spec/architecture/api-design).

2. PRD & TECH drift — implementation vs spec

Read the code's actual behavior and compare against PRD/TECH:

  • Features in code but not in PRD — shipped without spec; flag for spec.
  • Features in PRD but not in code — spec aspirational or feature removed; update PRD to match reality.
  • Components in TECH but not in code — planned but not implemented; update TECH.
  • Components in code but not in TECH — undocumented; add to TECH.

3. API drift — endpoints vs docs/API/*.md

Extract every route declaration from code and match against docs/API/:

  • express: grep -rh "\(app\|router\)\.\(get\|post\|put\|delete\|patch\|all\)" --include="*.ts" --include="*.js"
  • fastify: grep -rh "\(app\|fastify\)\.\(get\|post\|put\|delete\|patch\|all\)" --include="*.ts" --include="*.js"
  • nestjs: grep -rh "@\(Get\|Post\|Put\|Delete\|Patch\|All\)" --include="*.ts"
  • fastapi / flask: grep -rh "@app\.\(get\|post\|put\|delete\|patch\)" --include="*.py"

Read the full file on GitHub · 105 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 5d ago First seen · 105 lines · 77 tokens per session scan A 77a83efb54c4

Subscribe to this mod's changes

documentation-audit is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 4d ago), licensed MIT. It adds 77 tokens to every session and 1,419 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

release-notes

Generate and publish concise, evidence-based notes in the body of the latest existing GitHub Release. Use only when the user explicitly invokes $release-notes or explicitly asks to update the latest existing GitHub Release body. Do not invoke for general release planning, changelog, tag, or version tasks.

kenryu42/cc-safety-net · 65 tokens

add-teams

Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.

microsoft/power-platform-skills · 31 tokens

sys-configure

Configure Claude Octopus — redirects to /octo:setup interactive wizard.

nyldn/claude-octopus · 18 tokens

recipe-front-review

Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.

shinpr/claude-code-workflows · 29 tokens

37signals-way

Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…

wondelai/skills · 177 tokens

service-desk

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…

cbrock84/headcount · 73 tokens