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.
npx skills add ckorhonen/swe-skills --skill docs-drift-auditgit clone --depth 1 https://github.com/ckorhonen/swe-skillsWrote 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.
[](https://agentmods.dev/skills/ckorhonen/swe-skills/docs-drift-audit)<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.
<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>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 | $0.00094 | $0.01146 |
| Opus 5 | $0.00047 | $0.00573 |
| Sonnet 5 | $0.00019 | $0.00229 |
| Haiku 4.5 | $0.00009 | $0.00115 |
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.
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.mdorCLAUDE.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
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.
- 10d ago First seen · 177 lines · 94 tokens per session scan A e6d258aa62d5
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.
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…
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.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
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.
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.
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.