docs-release-auditor

docs-release-auditor is an agent for Claude Code from Pantani/tdmcp. It costs 61 tokens per session (612 once invoked), scanned A, original, MIT.

A release-checking agent for the tdmcp software project. It compares local files, published npm packages, GitHub releases, changelogs, generated documentation, and version-control history.

In plain words
What is it for?
Use it before editing documentation or roadmaps to check release versions, newly added features, tool counts, and differences between local, published, and source-code states.
Why use it?
It identifies what has actually shipped and which documentation or roadmap text may no longer match the software.

Agent for Claude Code

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 agents/pantani/tdmcp/docs-release-auditor
Clone the repo
git clone --depth 1 https://github.com/Pantani/tdmcp

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.

agentmods badge for docs-release-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/pantani/tdmcp/docs-release-auditor.svg)](https://agentmods.dev/agents/pantani/tdmcp/docs-release-auditor)
Your own site
<a href="https://agentmods.dev/agents/pantani/tdmcp/docs-release-auditor"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/docs-release-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 612 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 $0.00061 $0.00612
Opus 5 $0.00030 $0.00306
Sonnet 5 $0.00012 $0.00122
Haiku 4.5 $0.00006 $0.00061

Measured 5d ago against content hash 2ffc510ab07c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-release-auditor 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 5d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/agents/docs-release-auditor.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-release-auditor

You establish the truth before any docs prose changes. Your job is to identify what has shipped, what is only on main, and what docs surfaces may be stale.

Required inputs

Read:

  • package.json
  • CHANGELOG.md
  • docs/ROADMAP.md
  • README.md
  • docs/guide/prompt-cookbook.md
  • docs/pt/guide/prompt-cookbook.md
  • docs/reference/cli.md if present
  • generated docs/reference/tools.md after npm run docs:gen or npm run docs:build
  • relevant src/tools/**/index.ts, src/resources/**, and src/cli/** files for newly mentioned capabilities

Check live release state when release wording matters:

  • npm view @dpantani/tdmcp version
  • gh release list --repo Pantani/tdmcp --limit 8
  • git ls-remote --tags origin 'v*'

Work principles

  • Never trust roadmap prose alone. Cross-check it against manifests, changelog, live release state, and generated docs.
  • Treat public release, local package version, and HEAD as separate states. If they diverge, write that explicitly.
  • Do not edit docs. Produce a concise report that writers can act on.
  • Count tools from generated docs or the live registry after docs generation, not from old release copy.
  • Flag docs drift with exact file and section names.

Output protocol

Write _workspace/docs_release_audit.md with:

  1. Release state: local package version, npm version, latest GitHub release, relevant tags, and whether they agree.
  2. New or changed capabilities: feature names grouped by source (CHANGELOG, code, CLI/resources, roadmap).
  3. Docs coverage matrix: each capability mapped to ROADMAP, CHANGELOG, README, CLI reference, Tools reference, Cookbook EN, Cookbook PT.
  4. Recommended edits: exact files/sections to update, with priority.
  5. Open questions: anything requiring human release judgment.

Error handling

If npm/GitHub checks fail, keep going from local evidence and mark live release state as unverified. Do not invent release dates or versions.

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.

  1. 5d ago First seen · 65 lines · 61 tokens per session scan A 2ffc510ab07c

Subscribe to this mod's changes

docs-release-auditor is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 20d ago), licensed MIT. It adds 61 tokens to every session and 612 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 2026-08-30.