swe:docs-drift-audit

swe:docs-drift-audit is a skill for Claude Code from ckorhonen/swe-skills. It costs 94 tokens per session (1,146 once invoked), scanned A, original, MIT.

A repository audit that compares human-facing and operational documentation with the code, configuration, interfaces, workflows, and project structure. It looks for documentation that has become inaccurate or incomplete after changes.

In plain words
What is it for?
Use it to check documentation after code or workflow changes, identify mismatches and gaps, and plan focused updates to READMEs, runbooks, or related operational guides.
Why use it?
It helps find stale instructions and missing runbook or README updates before they mislead developers or operators. Findings are tied to repository evidence and limited to the smallest needed fixes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the swe-skills plugin — 17 skills shipped together

Good fit Use it to check documentation after code or workflow changes, identify mismatches and gaps, and plan focused updates to READMEs, runbooks, or related operational guides.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckorhonen/swe-skills/docs-drift-audit
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.

Any agent
npx skills add ckorhonen/swe-skills --skill docs-drift-audit
Clone the repo
git clone --depth 1 https://github.com/ckorhonen/swe-skills

Made for: Claude Code.

Or install swe-skills, the plugin that ships this one along with the rest of its 17 skills.

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 swe:docs-drift-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckorhonen/swe-skills/docs-drift-audit/github.svg)](https://agentmods.dev/skills/ckorhonen/swe-skills/docs-drift-audit)
Your own site
<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/docs-drift-audit"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/docs-drift-audit/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.

agentmods 80×15 button for swe:docs-drift-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/docs-drift-audit"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/docs-drift-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,146 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01146
Opus 5 $0.00047 $0.00573
Sonnet 5 $0.00019 $0.00229
Haiku 4.5 $0.00009 $0.00115

Measured 10d ago against content hash e6d258aa62d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

swe:docs-drift-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 10d 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/docs-drift-audit/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SWE Docs Drift Audit

What This Skill Does

Use this skill to find documentation that no longer matches the repository's current behavior.

The goal is not to rewrite docs broadly. The goal is to compare the repo's current reality against its human-facing and operational documentation, then report where drift exists and what should change.

Typical outputs include:

  • a short list of documentation gaps or mismatches
  • the code, config, or workflow evidence behind each gap
  • the smallest documentation updates that would close the gap
  • explicit notes for anything that looks stale but is not yet proven

When To Use

Use this skill when the user wants to:

  • check whether docs still match a recent code or config change
  • audit runbooks, READMEs, changelogs, or operational docs for drift
  • find missing docs after a workflow, interface, or structure change
  • prepare a bounded documentation update plan based on repo evidence

Do Not Use

Do not use this skill for:

  • updating agent-facing guidance such as AGENTS.md or CLAUDE.md
  • rewriting documentation for style alone
  • generic repo orientation with no docs-mismatch goal
  • inventing documentation from product expectations instead of repo evidence

Inputs To Confirm

Confirm or infer:

  • repo or package scope
  • which documentation families matter most
  • whether the user wants report-only output or a doc-update plan
  • whether a recent change, PR, or commit range is the primary trigger
  • any no-touch areas, such as generated docs or external docs owned elsewhere

If the scope is unclear, ask for the smallest useful boundary before proceeding.

Instructions

Step 1: Define The Change Surface

Start by identifying the change surface that may have caused drift.

Inspect:

  • recent commits or the referenced PR
  • changed code, config, or interfaces
  • workflows, scripts, routes, jobs, or repo structure changes

Name the actual affected surfaces before looking at docs.

Step 2: Inventory Relevant Documentation

Read the full file on GitHub · 177 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.

  1. 10d ago First seen · 177 lines · 94 tokens per session scan A e6d258aa62d5

Subscribe to this mod's changes

swe:docs-drift-audit is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,146 once invoked, about $0.0005 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

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.

SethGammon/Citadel · 56 tokens

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens

design-sync-upload

An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.

modu-ai/moai-cowork · 211 tokens