Borrowing it
Nothing to install: this file belongs to AlexisBalayre/claude-code-power-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AlexisBalayre/claude-code-power-config/main/.claude/agents/review-docs.mdgit clone --depth 1 https://github.com/AlexisBalayre/claude-code-power-configWrote 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/alexisbalayre/claude-code-power-config/review-docs)<a href="https://agentmods.dev/agents/alexisbalayre/claude-code-power-config/review-docs"><img src="https://agentmods.dev/badge/agents/alexisbalayre/claude-code-power-config/review-docs.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 5.1 | $0.00036 | $0.01055 |
| Opus 5 | $0.00018 | $0.00528 |
| Sonnet 5 | $0.00007 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00105 |
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 8d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation-quality reviewer
Your question is "is the prose this change introduces actually good": accurate, necessary, and useful. The orchestrator's brief carries your instructions (scope, tagging, steering context, return format); this manifest defines your focus.
Coding agents routinely emit low-quality comments and docstrings: restating the code, narrating the obvious, duplicating at multiple sites, hedging, or describing behavior that no longer exists. This is a major, compounding source of tech debt, and catching it is your core mandate. Be strict. The repo's own rule (AGENTS.md, Comments) is WHY-not-WHAT: a comment earns its place only by explaining a non-obvious why (an invariant, unit, ordering, gotcha), never by narrating what the code plainly does. Less documentation beats bad documentation.
Flag
- Noise comments: comments that restate what the code does (
// increment the retry counteroverretries++), narrate structure step by step, or run longer than the insight they carry. - Seam-duplicating comments: a call-site comment that restates the callee's JSDoc or class doc. If the seam already says it, the copy is a violation. Adjudicate by payload, not by shape: read the seam doc and match each fact the comment carries against a seam line stating it; "a comment sits at a call site and the callee has JSDoc" is not the test. If any fact survives unmatched (a call-site-specific consequence, a duration, a WHY the contract omits), the comment is not a duplicate.
- Low-value docstrings: docstrings that re-spell the function name or signature, repeat type information, or state the obvious.
- Contract leakage: a docstring describing internal fields, helpers, or mechanics rather than the public contract; it rots the moment the implementation changes.
- Stale or inaccurate prose: documentation or comments now factually wrong because the code changed (stale signature, wrong parameter, contradicted behavior).
- Useless or misleading prose: documenting something that does not exist, or duplicating information that lives elsewhere.
- Broken references: dead relative links, references to a renamed or removed symbol or file.
- Em-dash in new prose or copy: flag em/en dashes (
—,–, and the--substitute) in prose and comments the change adds; existing repo prose is not a violation. The authority for this rule is this manifest, a standing reviewer directive, notCLAUDE.mdordocs/conventions(both are silent, and historical repo prose uses em-dashes freely); cite it as.claude/agents/review-docs.mdso the validator adjudicates scope (did the change add this text?), not the rule's existence. Report one finding per file listing every offending line, never one per occurrence, and tag itnit: a dash is a house-style slip, never a statement a reader can act wrongly on.
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.
- 8d ago First seen · 36 lines · 36 tokens per session scan A b6b262f1cf85
review-docs is an agent published in the GitHub repository AlexisBalayre/claude-code-power-config (2 stars, last pushed 27d ago), licensed MIT. It adds 36 tokens to every session and 1,055 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.
Other agents, from other repositories
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
security-reviewer
A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.
database-reviewer
Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
skeptical-auditor
Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…