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.
curl -O https://raw.githubusercontent.com/matteocervelli/llms/main/.claude/skills/review/SKILL.mdgit clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/skills/matteocervelli/llms/review)<a href="https://agentmods.dev/skills/matteocervelli/llms/review"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/matteocervelli/llms/review"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00084 | $0.03168 |
| Opus 5.5 | $0.00034 | $0.01267 |
| Sonnet 5.5 | $0.00017 | $0.00634 |
| Haiku 4.5 | $0.00008 | $0.00317 |
Grade B, and why
review scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat "$HOME/.claude/shared/companions/registry.json" | jq -r ".companions.$COMPANION.installed" 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--allruns--quick→ code review only (for changes: skip silent-failures/types/comments checks)
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.
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.
- 1mo ago First seen · 303 lines · 84 tokens per session scan B a66a8252eaaf
review is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 5mo ago), licensed MIT. It adds 84 tokens to every session and 3,168 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…