A workflow for finding documentation that no longer matches the code in Merlin. It checks which documented code references changed and updates the affected documentation after verification.

Use it to audit stale guides and references, review the relevant code changes, and refresh verified documentation.

A document can remain valid-looking while describing old behavior; ordinary formatting checks do not detect that meaning has changed.

How ucb-bar/merlin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ucb-bar/merlin. 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/ucb-bar/merlin/main/.claude/skills/docs-doctor/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ucb-bar/merlin

Made for: Claude Code.

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/ucb-bar/merlin/docs-doctor/github.svg)](https://agentmods.dev/skills/ucb-bar/merlin/docs-doctor)

Your own site

<a href="https://agentmods.dev/skills/ucb-bar/merlin/docs-doctor"><img src="https://agentmods.dev/badge/skills/ucb-bar/merlin/docs-doctor/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/ucb-bar/merlin/docs-doctor"><img src="https://agentmods.dev/badge/skills/ucb-bar/merlin/docs-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 849 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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.00849
Opus 5.5	$0.00027	$0.00340
Sonnet 5.5	$0.00013	$0.00170
Haiku 4.5	$0.00007	$0.00085

Measured 15d ago against content hash 8feb857743e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs-doctor 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 15d 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.

.claude/skills/docs-doctor/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

docs-doctor — keep docs from falling behind the code

The linters (check_docs.py, wired into the Stop/pre-commit/CI gates) catch mechanical drift: stale generated files, invalid front-matter, retired paths. They CANNOT catch semantic drift — a guide that still parses fine but describes code that has since changed. That is this skill's job.

The deterministic backbone (LLM proposes, gate disposes)

Every durable doc under docs/ carries front-matter with last_verified: YYYY-MM-DD and code_refs: [<paths the doc describes>]. The worklist is computed deterministically — you never guess what's stale:

.venv/bin/python build_tools/scripts/check_docs_freshness.py --json

Returns {"drift": [...], "uncategorized": [...]}. Each drift entry is a doc whose last_verified predates the newest git commit touching one of its code_refs:

{"doc": "guides/dse.md", "last_verified": "2026-07-07",
 "stale_code_refs": [{"path": "merlin/python/merlin/dse", "last_commit": "2026-07-20"}]}

The loop (per drift candidate)

See what changed. For each stale code_ref, read the diff since the doc was last verified: git log --oneline --since=<last_verified> -- <path> then git diff <first>~1..HEAD -- <path>.
Read the doc (docs/<doc>).
Judge:
- Doc still accurate (change was internal/irrelevant) → only bump last_verified to today.
- Doc now wrong/incomplete → edit the prose to match the code, THEN bump last_verified.
- Can't tell → leave last_verified alone and flag it for a human; do NOT bump.
Never bump last_verified without having actually reconciled the doc against the diff. The date is a claim that a human/agent verified the doc against the code as of that day.
After edits, regenerate the hub and re-check: .venv/bin/python build_tools/scripts/gen_docs_index.py && .venv/bin/python build_tools/scripts/check_docs.py.
Commit in a small batch (shared tree — see CLAUDE.md): docs(doctor): re-verify <doc> vs <ref>.

Read the full file on GitHub · 65 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.

15d ago First seen · 65 lines · 67 tokens per session scan A 8feb857743e7

Subscribe to this mod's changes

docs-doctor is a skill published in the GitHub repository ucb-bar/merlin (21 stars, last pushed yesterday), licensed Apache-2.0. It adds 67 tokens to every session and 849 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-14.

Writing and docs

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

merlin: Skill for Claude Code