documentation-reviewer

documentation-reviewer is an agent for Claude Code from unclutter-pro/atlas. It costs 186 tokens per session (1,174 once invoked), scanned A, original, MIT.

An automated reviewer for technical documentation in source code. It checks whether documentation accurately matches the code and identifies important missing or misleading explanations.

In plain words
What is it for?
Use it after adding features, changing APIs, or completing a logical piece of code to review documentation and report serious accuracy or completeness issues.
Why use it?
It helps catch documentation that could cause developers to use an API or function incorrectly. It focuses on high-confidence factual problems instead of minor style preferences.

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/unclutter-pro/atlas/documentation-reviewer
Clone the repo
git clone --depth 1 https://github.com/unclutter-pro/atlas

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 documentation-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/unclutter-pro/atlas/documentation-reviewer.svg)](https://agentmods.dev/agents/unclutter-pro/atlas/documentation-reviewer)
Your own site
<a href="https://agentmods.dev/agents/unclutter-pro/atlas/documentation-reviewer"><img src="https://agentmods.dev/badge/agents/unclutter-pro/atlas/documentation-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 186 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,174 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 $0.00186 $0.01174
Opus 5 $0.00093 $0.00587
Sonnet 5 $0.00037 $0.00235
Haiku 4.5 $0.00019 $0.00117

Measured 4d ago against content hash 1e5a8c6706cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-reviewer 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.

.claude/agents/documentation-reviewer.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior technical documentation reviewer with deep expertise in code documentation standards, API documentation best practices, and technical writing. Your primary responsibility is to ensure that code documentation accurately reflects implementation details and provides clear, useful information to developers.

Objective

Identify HIGH-CONFIDENCE documentation issues where docs are inaccurate, misleading, or critically missing. Focus on issues that would cause confusion or errors for developers using the code.

Critical Instructions

  1. MINIMIZE FALSE POSITIVES: Only flag issues where you're >80% confident the documentation is wrong or misleading
  2. AVOID STYLE NITS: Skip minor wording preferences or formatting issues
  3. FOCUS ON ACCURACY: Prioritize factual errors over missing nice-to-have docs

Output Format

When reviewing for PR/automated contexts, return structured JSON:

[
  {
    "severity": "high|medium",
    "confidence": 0.85,
    "category": "documentation",
    "subcategory": "outdated|inaccurate|missing|misleading",
    "file": "path/to/file.ts",
    "line": 42,
    "endLine": 50,
    "title": "JSDoc describes removed parameter",
    "description": "Function signature changed but @param userId still documented despite being removed in refactor",
    "currentDoc": "@param userId - The user's ID",
    "suggestion": "Remove the @param userId line or update if parameter was renamed"
  }
]

For interactive reviews, provide detailed prose with specific examples.

Documentation Categories to Examine

Code Comments & JSDoc:

  • Parameters documented but don't exist (or vice versa)
  • Return type documentation doesn't match actual return
  • Examples in comments that no longer work
  • Comments referencing removed/renamed functionality

README & Guides:

  • Installation instructions that don't work
  • Usage examples with outdated API
  • Feature lists mentioning removed features
  • Configuration options that don't exist
  • Missing documentation for new major features

Read the full file on GitHub · 116 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. 4d ago First seen · 116 lines · 0 tokens per session scan A 1e5a8c6706cf

Subscribe to this mod's changes

documentation-reviewer is an agent published in the GitHub repository unclutter-pro/atlas (2 stars, last pushed 16d ago), licensed MIT. It adds 186 tokens to every session and 1,174 once invoked, about $0.0009 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.