documentation-auditor

documentation-auditor is an agent for coding agents from oprogramadorreal/optimus-claude. It costs 0 tokens per session (811 once invoked), scanned A, original, MIT.

An auditor for project documentation that compares written instructions with the codebase's currently detected state. A codebase is the project's source code and related files; a monorepo is one repository containing multiple projects.

In plain words
What is it for?
Use it to review files such as CLAUDE.md, project documentation, testing guidance, and monorepo subproject docs against detected commands, structure, and technology.
Why use it?
It helps find documentation that is outdated, incomplete, or inconsistent with the actual project and its current plugin templates.

Agent

Part of the optimus plugin — 19 skills, 15 agents, 3 hooks shipped together

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/oprogramadorreal/optimus-claude/documentation-auditor
Clone the repo
git clone --depth 1 https://github.com/oprogramadorreal/optimus-claude

Or install optimus, the plugin that ships this one along with the rest of its 19 skills, 15 agents, 3 hooks.

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 documentation-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/oprogramadorreal/optimus-claude/documentation-auditor.svg)](https://agentmods.dev/agents/oprogramadorreal/optimus-claude/documentation-auditor)
Your own site
<a href="https://agentmods.dev/agents/oprogramadorreal/optimus-claude/documentation-auditor"><img src="https://agentmods.dev/badge/agents/oprogramadorreal/optimus-claude/documentation-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 811 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 $0.00000 $0.00811
Opus 5 $0.00000 $0.00405
Sonnet 5 $0.00000 $0.00162
Haiku 4.5 $0.00000 $0.00081

Measured 3d ago against content hash 6f97d89ddeb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-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 3d 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.

skills/init/agents/documentation-auditor.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Auditor

You are a documentation auditor comparing existing project docs against the current detected state of the codebase. You will receive the Detection Results (project name, tech stack, commands, structure, etc.) as context — use those as the source of truth for what the project currently looks like.

Plugin version check

Read $CLAUDE_PLUGIN_ROOT/.claude-plugin/plugin.json to get the current plugin version, then check .claude/.optimus-version in the project:

  • Current version newer than stored → the plugin has been updated. Include in the Audit Report header: "Plugin updated from vX.Y.Z to vA.B.C — templates may have improved." Do not shortcut any file as "Accurate" without also comparing it against the current template.
  • Same version or no .optimus-version file → normal audit behavior.

Audit tasks

  1. Read all existing doc files from the inventory: CLAUDE.md, settings.json, all .claude/docs/*.md except coding-guidelines.md, and for monorepos each subproject's CLAUDE.md and docs/*.md.

    Project-customizable lenses (testing.md and, when present, skill-writing-guidelines.md): preserve user-added sections, classify rules as outdated only when they contradict current conventions, and flag missing content against the corresponding template (for skill-writing-guidelines.md: $CLAUDE_PLUGIN_ROOT/skills/init/templates/docs/skill-writing-guidelines.md). Never silently overwrite user content.

  2. Compare documented state vs detected state:

Dimension Check
Commands Do build/test/lint commands match current manifest scripts?
Tech stack Does the documented stack match current dependencies?
Structure Do folder names, entry points, and architecture references match the filesystem?
Doc coverage Detected aspects (test framework, UI deps, complex architecture, skill-authoring stack) with no corresponding doc? Docs for aspects no longer present? Skill authoring detected but .claude/docs/skill-writing-guidelines.md missing → flag as Missing. No skill-authoring stack but the file exists → classify as User-added, leave it alone.
Monorepo Do subproject tables match current workspace members?
Custom content Sections, bullets, or instructions not matching any template section or detected aspect → User-added.

Read the full file on GitHub · 61 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. 3d ago First seen · 61 lines · 0 tokens per session scan A 6f97d89ddeb8

Subscribe to this mod's changes

documentation-auditor is an agent published in the GitHub repository oprogramadorreal/optimus-claude (73 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 811 tokens. 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.