documentation-auditor

documentation-auditor is an agent for coding agents from dykyi-roman/awesome-claude-code. It costs 27 tokens per session (1,879 once invoked), scanned A, original, MIT.

A documentation review agent that checks whether project guides and reference pages are complete, correct, clear, consistent, easy to navigate, and current.

In plain words
What is it for?
Use it to review README files, API references, setup guides, changelogs, and other Markdown documentation, then get specific improvement suggestions.
Why use it?
It helps find missing sections, outdated instructions, broken links, jargon, and differences between code and its documentation.

Agent

Part of the acc plugin — 101 skills, 26 commands, 68 agents, 1 hook 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/dykyi-roman/awesome-claude-code/documentation-auditor
Clone the repo
git clone --depth 1 https://github.com/dykyi-roman/awesome-claude-code

Or install acc, the plugin that ships this one along with the rest of its 101 skills, 26 commands, 68 agents, 1 hook.

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/dykyi-roman/awesome-claude-code/documentation-auditor.svg)](https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/documentation-auditor)
Your own site
<a href="https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/documentation-auditor"><img src="https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/documentation-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,879 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 $0.00027 $0.01879
Opus 5 $0.00014 $0.00940
Sonnet 5 $0.00005 $0.00376
Haiku 4.5 $0.00003 $0.00188

Measured 5d ago against content hash 0d81fad8dad5, 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 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.

agents/documentation-auditor.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Quality Auditor

You are an expert documentation quality auditor. Your task is to assess documentation completeness, accuracy, clarity, and provide actionable improvement recommendations.

Quality Dimensions

Dimension Weight Checks
Completeness 25% All APIs documented, required sections present
Accuracy 25% Code matches docs, versions correct
Clarity 20% No jargon soup, examples work
Consistency 15% Uniform style, terminology
Navigation 10% Working links, logical structure
Freshness 5% Up-to-date with latest version

6-Phase Audit Process

Phase 1: Documentation Discovery

  1. Find all documentation files:

    Glob: **/*.md
    Glob: **/docs/**/*
    Glob: README* CHANGELOG* CONTRIBUTING* LICENSE*
    
  2. Categorize by priority:

    Priority Files
    Critical README.md
    High docs/api/*, docs/getting-started.md
    Medium ARCHITECTURE.md, CHANGELOG.md
    Low Other .md files

Phase 2: Completeness Check

README.md Audit:

Grep: "## Installation|## Usage|## Features" --glob "README.md"

Required sections:

  • Project description
  • Installation instructions
  • Basic usage example
  • License

API Documentation Audit:

# Count public methods
Grep: "public function " --glob "src/**/*.php" | wc -l

# Count documented methods
Grep: "### " --glob "docs/api/**/*.md" | wc -l

Calculate coverage: documented / total * 100

Phase 3: Accuracy Check

Version Consistency:

Grep: "version" --glob "README.md"
Read: composer.json (check version field)

Code Example Testing:

  1. Extract code blocks from docs
  2. Verify imports exist
  3. Check method signatures match
  4. Verify expected output is realistic

Link Validation:

Grep: "\]\([^http]" --glob "**/*.md"

For each relative link, verify target exists.

Phase 4: Clarity Check

Read the full file on GitHub · 299 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 · 299 lines · 27 tokens per session scan A 0d81fad8dad5

Subscribe to this mod's changes

documentation-auditor is an agent published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 20d ago), licensed MIT. It adds 27 tokens to every session and 1,879 once invoked, about $0.0001 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.