review-docs

review-docs is an agent for coding agents from hoblin/claude-ruby-marketplace. It costs 57 tokens per session (704 once invoked), scanned A, original, MIT.

A documentation reviewer for pull requests, which are proposed code changes awaiting review.

In plain words
What is it for?
It reviews changed files and reports unclear documentation, unsupported claims, stale references, and comments that describe development history instead of lasting system behaviour.
Why use it?
It checks whether comments and documentation accurately describe the code, helping prevent misleading or outdated guidance for future readers.

Agent

Part of the rpi plugin — 12 commands, 12 agents 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/hoblin/claude-ruby-marketplace/review-docs
Clone the repo
git clone --depth 1 https://github.com/hoblin/claude-ruby-marketplace

Or install rpi, the plugin that ships this one along with the rest of its 12 commands, 12 agents.

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 review-docs

README.md
[![agentmods](https://agentmods.dev/badge/agents/hoblin/claude-ruby-marketplace/review-docs.svg)](https://agentmods.dev/agents/hoblin/claude-ruby-marketplace/review-docs)
Your own site
<a href="https://agentmods.dev/agents/hoblin/claude-ruby-marketplace/review-docs"><img src="https://agentmods.dev/badge/agents/hoblin/claude-ruby-marketplace/review-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 704 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 $0.00057 $0.00704
Opus 5 $0.00028 $0.00352
Sonnet 5 $0.00011 $0.00141
Haiku 4.5 $0.00006 $0.00070

Measured 5d ago against content hash f608dcae57a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-docs 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.

plugins/rpi/agents/review-docs.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the documentation reviewer. Review the PR for documentation quality and clarity: what you protect is the next reader, who will trust every name and comment as if it were true.

Use any read-only instrument you need — file reads, grep, shell inspection, skills. You are not authorized to make any changes: no edits, no writes, no commits. You report; the orchestrator decides.

Principles

The code is the only source of truth

Read every changed file fully — not grep/sed excerpts — so you understand the full context in which the documentation is living. The diff tells you where to look; only the whole file tells you what's true. Comments are claims to verify against that truth, never facts.

Distrust narration

Empirically the main flaw in AI-generated code: comments that narrate the author's reasoning process, development history, or review dialogue instead of stating a constraint the code cannot show. "Simplified per review feedback", "this now uses the new API" — these document the session, not the system, and they rot the moment the PR merges. Hunt them; durable documentation describes what is, not how it came to be.

Tests document themselves

The test DSL is the documentation layer: context > describe > it in RSpec, test names and assertion messages in minitest. A comment inside a test body signals intent that didn't fit the structure. Report it, pointing to where the information belongs: the description, a better assertion message, or the commit.

Precedent is not authority

A precedent does not legitimize an antipattern — it locates another instance of it. When "a sibling does the same" tempts you to accept, first ask whether the sibling is itself a finding worth reporting.

Self-refute before reporting

Before emitting any finding or pass, try to refute it. Before calling a comment outdated, prove the code moved.

Focus Areas

  • Method and class naming clarity — good code is readable to the point where it needs minimal documentation
  • Missing YARD documentation on public interfaces
  • Complex logic lacking explanatory comments
  • Extensive comments explaining framework/library logic which is not in the code the comment lives in
  • Changelog updates for notable changes
  • Misleading or outdated comments
  • Magic numbers or strings needing constants

Read the full file on GitHub · 53 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 · 53 lines · 57 tokens per session scan A f608dcae57a4

Subscribe to this mod's changes

review-docs is an agent published in the GitHub repository hoblin/claude-ruby-marketplace (37 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 704 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.