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 jerseycheese/agent-skills --skill doc-rotgit clone --depth 1 https://github.com/jerseycheese/agent-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/jerseycheese/agent-skills/doc-rot)<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/doc-rot"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/doc-rot/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/jerseycheese/agent-skills/doc-rot"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/doc-rot.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 | $0.00139 | $0.01601 |
| Opus 5 | $0.00069 | $0.00800 |
| Sonnet 5 | $0.00028 | $0.00320 |
| Haiku 4.5 | $0.00014 | $0.00160 |
Grade A, and why
doc-rot 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Rot
Documentation lies as the code moves on. This skill finds the lies and fixes them — across *.md files, inline comments, docstrings, and commented-out code. It's the docs counterpart to dead-code-cleanup, and it enforces the comment hygiene rules in the user's CLAUDE.md ("explain WHY not WHAT"; "one canon version per file"; "update existing docs, don't proactively create new ones").
The core discipline: a doc isn't stale because it looks old — it's stale because it contradicts the code. Ground every call against the actual codebase before flagging it. A "removed" symbol might just be renamed; a "broken" path might live elsewhere now.
Pre-flight
Per the user's git workflow: git fetch && git status, confirm you're on the right base branch (develop if it exists, else main) and up to date. Then scope the doc set — don't boil the ocean. List what's in range (a directory, the README, the files a recent change touched) and confirm before sweeping a whole repo.
What counts as rot
Doc files (*.md)
- References to things that no longer exist — files/paths, npm scripts, CLI flags, config keys, env vars, API/function names. Verify each against the code before flagging.
- Stale setup/usage steps — install commands, toolchain versions, ports, or workflows the code has moved past.
- Code examples that wouldn't run — using removed or renamed APIs, old signatures, deleted imports.
- Dead links — broken internal anchors and relative file links (high confidence); external links (flag, don't chase every one).
- Superseded / duplicate docs — two docs covering the same thing, or a doc describing a feature that's gone. "One canon version per file" — pick the canonical one, fold or remove the rest.
Comments & docstrings
- Contradicts the code below it — the comment says one thing, the code does another. Highest-value find; almost always a real bug-in-waiting.
- Docstring drift —
@param/@returns/documented args that don't match the actual signature. - Anti-pattern comments (per CLAUDE.md): archaeological ("Extracted from X to reduce complexity"), motion-tracking ("Moved from Y on DATE"), obvious ("increment counter" above
counter += 1). - Stale TODO/FIXME — referencing a closed issue or a condition that's already resolved.
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.
- 8d ago First seen · 100 lines · 139 tokens per session scan A e152948e091a
doc-rot is a skill published in the GitHub repository jerseycheese/agent-skills (1 stars, last pushed 7d ago), licensed MIT. It adds 139 tokens to every session and 1,601 once invoked, about $0.0007 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
env-scanner
Scan and audit Gemini CLI, Claude Code, Antigravity, Continue, Windsurf, JetBrains AI, and OpenCode environments. Discovers configurations, audits memory tiers, detects skill extraction state, analyzes behavioral tool chains, checks policy governance (v0.40+), and suggests reusable skills with evidence gating.…
scan
Scan your AI coding tool ecosystem — Gemini CLI, Claude Code, Antigravity (Desktop, CLI, IDE), Continue, Windsurf, JetBrains AI, OpenCode. Produces a maturity score, advisory recommendations, and optionally generates reusable SKILL.md files from your conversation patterns. Use when the user asks to audit their…
chorus-council
Run an LLM council — Claude (correctness), Gemini (edge cases), Cursor (integration), Kilo (maintainability), and you (scope) tackle the same task in parallel. Use when the user wants multiple independent perspectives on a decision, approach, or problem.
chorus-vote
Put a yes/no proposition to five agents and tally YES / NO / ABSTAIN votes when the user wants a quick decision signal.
chorus-parallel-debug
Parallel root-cause hypotheses from multiple agents for a reported bug. Use when the user says "parallel debug", "chorus debug", "multiple hypotheses", or "debug with all agents".
chorus-parallel-review
Parallel code review of the current git diff from multiple agents — Claude (correctness/security), Gemini (edge cases), Cursor (integration), Kilo (maintainability), and you (scope/simplicity). Use when the user says "parallel review", "review with all agents", or "chorus review".