A workflow that sends code, pull requests, documents, or design questions to other AI systems for an independent review.

Use it to review code changes, check pull-request readiness, assess a document, solve a design problem, or compare implementation status with a specification.

It provides a second opinion on changes, architecture, documentation, types, comments, or implementation progress.

How matteocervelli/llms configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to matteocervelli/llms. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/matteocervelli/llms/main/.claude/skills/review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/matteocervelli/llms

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/matteocervelli/llms/review.svg)](https://agentmods.dev/skills/matteocervelli/llms/review)

Your own site

<a href="https://agentmods.dev/skills/matteocervelli/llms/review"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/review.svg" alt="Measured on agentmods" height="20"></a>

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,168 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.03168
Opus 5	$0.00042	$0.01584
Sonnet 5	$0.00017	$0.00634
Haiku 4.5	$0.00008	$0.00317

Measured 3d ago against content hash a66a8252eaaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

review scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat "$HOME/.claude/shared/companions/registry.json" | jq -r ".companions.$COMPANION.installed"

.claude/skills/review/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review — Companion-Dispatched Reviews & Analysis

Unified skill for all companion AI reviews. Dispatches structured prompts to external AIs (Codex, Gemini, Claude) via runner.sh for independent second opinions.

For Claude-native code quality checks (no external AI), use /code-review.

Usage

/review                              # Auto-detect: uncommitted changes → changes review
/review changes                      # Full review: code + silent-failures + types + comments
/review changes --quick              # Code review only (skip silent-failures/types/comments)
/review pr [--pr N]                  # PR merge readiness (MERGE/BLOCK verdict)
/review doc <file>                   # PRP/PRD/RFC/Design completeness review
/review solve "problem"              # Architecture/design second opinion
/review status <spec>                # Implementation progress vs spec
/review frontend <url>               # Delegates to /frontend review
/review silent-failures [file|diff]  # Error handling audit
/review types [file]                 # Type design analysis
/review comments [file]              # Comment accuracy check
/review gate                         # Lightweight pre-commit gate (critical bugs + security only)
/review adversarial                  # Adversarial review: challenge design choices (Codex gpt-5.5 xhigh)

All subcommands support: [companion] (codex/gemini/claude), --model MODEL, --all, --exclude-self

Workflow

Step 1: Parse Arguments

Parse $ARGUMENTS for subcommand and flags:

First positional arg → subcommand (changes, pr, doc, solve, status, frontend, silent-failures, types, comments, gate, adversarial)
If no subcommand: check for uncommitted changes → default to changes, else show usage
Companion name: codex, gemini, or claude (optional, resolved from registry defaults)
--model MODEL → override default model
--base BRANCH → diff against branch (for changes/pr)
--pr NUMBER → GitHub PR mode (for pr subcommand)
--context FILE → attach context files (for solve)
--type PRP|PRD|RFC|DESIGN → doc type override (for doc)
--issue NUMBER → GitHub issue (for status)
--timeout SECS → override default timeout
--all → dispatch to all installed companions in parallel
--exclude-self → exclude claude from --all runs
--quick → code review only (for changes: skip silent-failures/types/comments checks)

Read the full file on GitHub · 303 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 303 lines · 84 tokens per session scan B a66a8252eaaf

Subscribe to this mod's changes

review is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 3,168 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Code review

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens

llms: Skill for Claude Code