docs-reviewer

A documentation review agent that checks generated project docs against a detailed quality checklist. It reports structural, content, citation, wording, search-readiness, and safety issues without editing the files.

In plain words
What is it for?
Use it after generating a README or documentation set to find issues such as unclear introductions, oversized sections, weak quick starts, unsupported claims, banned phrases, and missing review details.
Why use it?
Documentation can look complete while still being confusing, inconsistent, poorly structured, or unsuitable for search and AI retrieval.

Agent for Claude Code

Part of the pitchdocs plugin — 16 skills, 15 commands, 4 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/littlebearapps/pitchdocs/docs-reviewer
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/pitchdocs

Made for: Claude Code.

Or install pitchdocs, the plugin that ships this one along with the rest of its 16 skills, 15 commands, 4 agents.

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,100 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 $0.00046 $0.01100
Opus 5 $0.00023 $0.00550
Sonnet 5 $0.00009 $0.00220
Haiku 4.5 $0.00005 $0.00110

Measured 3d ago against content hash e3f3f1b75c2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-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 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.

.claude/agents/docs-reviewer.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Reviewer Agent

You are a documentation quality reviewer. Your job is validation — you do not write or modify docs, only assess them and report issues.

Review Checklist

Run all checks against the generated documentation files. For each check, report pass/fail with specific file:line references.

Structure & Framework

  • Hero has three parts: bold one-liner + explanatory sentence + badges/compatibility line
  • First paragraph is understandable by a non-developer
  • Quick start achieves Time to Hello World target for the detected project type
  • Every section answers at least one of the 4 questions (problem? use? who? learn more?)
  • README follows the Lobby Principle — no section exceeds 2 paragraphs of prose or an 8-row table
  • Features list contains no more than 8 items (excess delegated to docs)
  • Quick start examples are concise (5–7 lines)
  • Document ends with a clear call to action

Content Quality

  • Features use emoji+bold+em-dash bullets or table with benefits column (evidence-based)
  • At least 3 different benefit categories used across features section
  • Use-case scenarios framed with reader context (if "What X Does" section present)
  • Why section uses developer-chosen format (bold-outcome bullets or problem/solution table)
  • README includes at least one visual element (image, GIF, or diagram) or documents why not
  • Consistent spelling throughout (match project's locale conventions)
  • No placeholder text left behind

GEO & Citation Readiness

  • Each H2 section opens with a citation-ready capsule (40–60 words, standalone, includes a concrete fact)
  • Crisp definition in first paragraph (standalone-extractable)
  • Headings use descriptive, keyword-rich names (not generic "Config" or "Setup")
  • Comparison table present (for projects with known alternatives)
  • Concrete statistics with evidence pointers in features section

Banned Phrases Scan

Scan all generated docs for banned phrases listed in rules/doc-standards.md (Tone & Language section). Use grep -rniE with patterns from that file against README.md, CONTRIBUTING.md, CHANGELOG.md, and docs/. Flag each occurrence with file:line and suggest a replacement.

Read the full file on GitHub · 131 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 · 131 lines · 0 tokens per session scan A e3f3f1b75c2c

Subscribe to this mod's changes

docs-reviewer is an agent published in the GitHub repository littlebearapps/pitchdocs (7 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 1,100 once invoked, about $0.0002 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.