docs-consistency-check

docs-consistency-check is a skill for Claude Code, Codex from Grinv/mal-mcp. It costs 56 tokens per session (1,049 once invoked), scanned A, original, MIT.

A developer skill that checks whether project documentation and metadata still match the tools registered in the source code. It covers files such as README.md, manifests, the changelog, and agent instructions.

In plain words
What is it for?
Use it after changing tools or during an audit of a Model Context Protocol server and its documentation.
Why use it?
Adding, renaming, or removing a tool can leave documentation out of date. This check finds mismatched tool names, authentication details, descriptions, and missing changelog entries.

Skill for Claude CodeCodex

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/grinv/mal-mcp/docs-consistency-check
Any agent
npx skills add Grinv/mal-mcp --skill docs-consistency-check
Clone the repo
git clone --depth 1 https://github.com/Grinv/mal-mcp

Made for: Claude Code, Codex.

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 docs-consistency-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/grinv/mal-mcp/docs-consistency-check.svg)](https://agentmods.dev/skills/grinv/mal-mcp/docs-consistency-check)
Your own site
<a href="https://agentmods.dev/skills/grinv/mal-mcp/docs-consistency-check"><img src="https://agentmods.dev/badge/skills/grinv/mal-mcp/docs-consistency-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,049 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 $0.00056 $0.01049
Opus 5 $0.00028 $0.00524
Sonnet 5 $0.00011 $0.00210
Haiku 4.5 $0.00006 $0.00105

Measured 4d ago against content hash f1f6bc367266, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-consistency-check 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 4d 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.

.agents/skills/docs-consistency-check/SKILL.md · 64 lines

What it actually says

Docs/metadata consistency

Check every one of these, not just a sample:

  • README.md's tool table matches src/tools/*.ts's registrations (names, and the auth-tier column — none / Client ID / OAuth token, per docs/auth.md — against what each tool actually needs).
  • manifest.json's and server.json's tools arrays list the same tool names as what's actually registered — treat a test failure here as authoritative if one exists. Their description fields are deliberately short, independent marketing-style summaries, NOT a copy of the tool's full .describe()/description text in src/tools/*.ts — don't "fix" them to match verbatim, that's not a bug. Do re-read them for accuracy if a tool's behavior changed in a way the short summary now misrepresents.
  • Tool description/field .describe() text in src/tools/*.ts itself: does it still match the actual inputSchema/outputSchema and the real behavior? Cross-check new/edited descriptions against the tool-description-check skill (Glama's TDQS rubric) per AGENTS.md.
  • CHANGELOG.md's [Unreleased] section (see the changelog-style skill for entry style) has one line per real behavior change made in this pass — add missing entries, don't just flag them as missing. Run node scripts/check-changelog-coverage.mjs to list every commit since the last release tag and flag which ones CHANGELOG.md doesn't reference at all — it's not a hard gate (plenty of commits are legitimately internal: dev-dependency bumps, docs-about-docs, CI-only fixes), but triage every line it reports as either "needs an entry" or "correctly excluded," don't skip the check just because most commits usually are internal.
  • docs/api-references.md's "verified live" claims still match the current client code, especially any claim this pass's own fixes just invalidated — and especially the official-API fallback field-gap list, which is exactly the kind of claim a MAL API change could quietly break.
  • docs/auth.md's credential-tier breakdown still matches what each tool actually requires.
  • AGENTS.md's project-shape/file-tree description (including this .agents/skills/ entry) still matches the filesystem.
  • notes/tenrai-reliability.md (gitignored) — if this pass turned up a new Tenrai quirk or reliability data point, log it there with a date, the same way past passes have; don't let a fresh finding live only in this conversation's transcript.
  • PRIVACY.md and SECURITY.md: re-verify every specific claim against the actual current code, don't just skim for plausibility — which credentials exist and how each is transmitted/redacted (e.g. src/lib/errors.ts's redact() actually covering both key=value and JSON "key":"value" shapes, and the tokens.json store's 0600/0700 permissions), what is and isn't cached (incl. cache key/TTL — cross-check the "deliberately not cached" list against src/lib/cache.ts call sites), the current list of read-only vs. OAuth/write tools, and the host-allowlist statement (config.ts's Zod validation vs. an actual fixed allowlist — there isn't one). This class of drift is easy to miss because it reads fine on its own and only breaks against the code: a sibling repo's SECURITY.md/PRIVACY.md both claimed "player-specific data is never cached" after a later feature added exactly that caching, and a separate claim conflated an actually-cached field with a similarly-named never-cached one — neither doc was self-evidently wrong, both required re-reading the client code to catch. Also confirm every root-level doc a README link points to (PRIVACY.md, SECURITY.md, …) is actually in package.json's files array — a new one added there without updating files 404s on the npm tarball (bit PRIVACY.md once already, then recurred for SECURITY.md).
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. 4d ago First seen · 64 lines · 56 tokens per session scan A f1f6bc367266

Subscribe to this mod's changes

docs-consistency-check is a skill published in the GitHub repository Grinv/mal-mcp (2 stars, last pushed 11d ago), licensed MIT. It adds 56 tokens to every session and 1,049 once invoked, about $0.0003 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

live-audit

Audit anilist-mcp-server — build/test/lint gate, live MCP tool edge-case sweep (input validation, not-found paths, mutations with capture/revert), source-level code review, and docs/metadata consistency. Use when asked to test/audit the published or just-fixed anilist-mcp-server package, hunt for bugs/edge cases, or…

Grinv/anilist-mcp-server · 85 tokens

prompt-check

Live-test every MCP Prompt in src/prompts.ts through the real MCP protocol (not a static read) across every argument combination. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.

Grinv/anilist-mcp-server · 53 tokens

tool-description-check

Self-check a new or edited MCP tool description/field .describe() text before committing — verify every behavioral claim against live testing, check for contradictions with sibling tools, and score against Glama's Tool Definition Quality Score (TDQS) rubric. Use whenever a tool description or schema field description…

Grinv/anilist-mcp-server · 74 tokens

release

Cut a release of anilist-mcp-server — draft CHANGELOG entries, check docs/metadata consistency, then bump/tag/push. Use when asked to release, cut a version, or publish a new version of this package.

Grinv/anilist-mcp-server · 48 tokens

fixture-accuracy-check

Make sure a mocked-fetch test fixture mirrors AniList's real GraphQL response shape, not just whatever fields make the current code pass. Use before writing or changing a fixture in src/tests/.test.ts.

Grinv/anilist-mcp-server · 48 tokens

docs-consistency-check

Check README/manifest.json/server.json/CHANGELOG.md/AGENTS.md and docs/.md for drift against the actual registered tools and source. Use after adding, renaming, or removing a tool, or as part of a live-audit pass.

Grinv/anilist-mcp-server · 56 tokens