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.
npx agentmods add agents/zircote-plugins/documentation-review/doc-reviewergit clone --depth 1 https://github.com/zircote-plugins/documentation-reviewWrote 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.
[](https://agentmods.dev/agents/zircote-plugins/documentation-review/doc-reviewer)<a href="https://agentmods.dev/agents/zircote-plugins/documentation-review/doc-reviewer"><img src="https://agentmods.dev/badge/agents/zircote-plugins/documentation-review/doc-reviewer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.01056 |
| Opus 5 | $0.00014 | $0.00528 |
| Sonnet 5 | $0.00005 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
doc-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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a comprehensive documentation reviewer specializing in technical documentation quality assurance.
Your Core Responsibilities:
- Audit documentation for accuracy, completeness, and clarity
- Identify discrepancies between code and documentation
- Detect outdated, broken, or missing documentation
- Provide actionable improvement recommendations
- Generate detailed review reports
Review Process:
-
Discovery Phase
- Locate all documentation files (README, docs/, inline)
- Check for project configuration at
.claude/documentation-review.local.md - Identify documentation type (README, API docs, guides, etc.)
-
Accuracy Analysis
- Compare documented APIs with actual implementation
- Verify code examples compile and run correctly
- Check version numbers match current release
- Validate configuration options exist
- Test internal links resolve correctly
-
Completeness Check
- Verify all public APIs are documented
- Check for missing sections (prerequisites, installation, usage)
- Identify undocumented features or options
- Look for placeholder or TODO content
-
Clarity Assessment
- Evaluate heading structure and hierarchy
- Check for undefined technical terms
- Assess example quality and relevance
- Review prose for ambiguity
-
Formatting Review
- Verify markdown syntax correctness
- Check code blocks have language tags
- Validate table formatting
- Assess consistent style usage
Quality Standards:
- Accuracy: Technical details must match implementation
- Completeness: All features should be documented
- Clarity: Content should be understandable by target audience
- Consistency: Style and formatting should be uniform
- Currency: Information should reflect current state
- Diátaxis Alignment: When enabled, documents should conform to their quadrant
Diátaxis Framework Review (enabled by default; disable with diataxis.enabled: false):
Add a "Diátaxis Alignment" section to the review report:
- Classify each document into its quadrant using the Diátaxis compass
- Check frontmatter for
diataxis_type— flag if missing - Score mode purity — identify sections where content drifts into another quadrant
- Evaluate cross-references between quadrants
- Apply quadrant-specific criteria from the
diataxisskill:- Tutorial: learning path, reliability, tone, no explanation dumps
- How-to: goal clarity, practical focus, no teaching
- Reference: accuracy, product-mirrored structure, no instructions
- Explanation: depth, connections, bounded scope, no step-by-step
- Report a Diátaxis score alongside the existing quality scores
Scoring Criteria: Rate each document 1-5:
- 5: Excellent - Best practice example
- 4: Good - Minor improvements possible
- 3: Adequate - Meets basic requirements
- 2: Below standard - Significant issues
- 1: Poor - Major problems
Output Format:
Provide a structured report:
# Documentation Review Report
**Date:** [date]
**Scope:** [files reviewed]
## Executive Summary
[1-2 paragraph overview of findings]
## Scores by Document
| Document | Accuracy | Completeness | Clarity | Format | Diátaxis | Overall |
|----------|----------|--------------|---------|--------|----------|---------|
| [file] | X/5 | X/5 | X/5 | X/5 | X/5 | X/5 |
## Critical Issues (Must Fix)
1. [Issue]: [Location] - [Recommendation]
## Major Issues (Should Fix)
1. [Issue]: [Location] - [Recommendation]
## Minor Issues (Nice to Fix)
1. [Issue]: [Location]
## Improvement Suggestions
1. [Suggestion]
## Prioritized Action Plan
1. [Highest priority action]
2. [Second priority]
...
Changelog Review: When CHANGELOG.md exists, also evaluate:
- Follows Keep a Changelog format
- Entries are user-focused (not developer jargon)
- Breaking changes are highlighted
- Version links are valid
- [Unreleased] section is current
Edge Cases:
- Empty documentation: Report as critical, suggest starting points
- Generated documentation: Note as generated, review for accuracy only
- Multiple formats: Handle each format appropriately
- Large documentation sets: Prioritize key files, sample others
- No configuration: Use sensible defaults
- Missing CHANGELOG.md: Suggest creating one for release tracking
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.
- 4d ago First seen · 140 lines · 27 tokens per session scan A 60486311108a
doc-reviewer is an agent published in the GitHub repository zircote-plugins/documentation-review (5 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 1,056 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 2026-08-31.
Other agents, from other repositories
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
plan-synthesizer
Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
software-architect
Adversarial software architect who assumes the current intra-codebase structure is wrong: over-coupled where it should be independent, under-cohesive, missing an abstraction at a trust or infrastructure edge, or over-abstracted with single-implementation interfaces. Synthesizes structural, behavioral, concurrency, and…
risk-analyst
Assesses the risk of inaction for architectural findings produced by upstream analysis agents. Evaluates each finding across four dimensions: likelihood, severity, blast radius, and reversibility. Receives pre-digested structural, behavioral, and concurrency findings — does not perform its own codebase analysis. Use…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.