review

review is a skill for Claude Code from Jose-Ribeir/claude-code-review-gate. It costs 70 tokens per session (5,755 once invoked), scanned A, original, Apache-2.0.

An AI code-review workflow that examines changed files, staged changes, unpushed commits, or whole files and reports findings with a verdict.

In plain words
What is it for?
Use it to review working diffs, staged changes, unpushed work, or an entire repository, with optional path filters and machine-readable JSON output.
Why use it?
It provides a structured check for problems in code before changes are committed or pushed.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the review-gate plugin — 1 skill, 1 command, 2 agents, 3 hooks shipped together

Good fit Use it to review working diffs, staged changes, unpushed work, or an entire repository, with optional path filters and machine-readable JSON output.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Jose-Ribeir/claude-code-review-gate
Claude Code
/plugin install review-gate

Made for: Claude Code.

Or install review-gate, the plugin that ships this one along with the rest of its 1 skill, 1 command, 2 agents, 3 hooks.

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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/skills/jose-ribeir/claude-code-review-gate/review/github.svg)](https://agentmods.dev/skills/jose-ribeir/claude-code-review-gate/review)
Your own site
<a href="https://agentmods.dev/skills/jose-ribeir/claude-code-review-gate/review"><img src="https://agentmods.dev/badge/skills/jose-ribeir/claude-code-review-gate/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/skills/jose-ribeir/claude-code-review-gate/review"><img src="https://agentmods.dev/badge/skills/jose-ribeir/claude-code-review-gate/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,755 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.05755
Opus 5 $0.00035 $0.02877
Sonnet 5 $0.00014 $0.01151
Haiku 4.5 $0.00007 $0.00575

Measured 4d ago against content hash 22ef508ce088, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review 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.

skills/review/SKILL.md · 456 lines

How it starts

The opening of the file, as written. The whole thing — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-gate — orchestrator

You are orchestrating an AI code review. Follow these steps exactly.

0. Parse arguments ($ARGUMENTS)

  • --staged — review staged changes only (git diff --staged).
  • --unpushed — review all commits not yet pushed to the upstream branch. File list: git diff -M @{u}..HEAD --name-status; falls back to git diff -M origin/main..HEAD --name-status if no upstream tracking branch is set. Per-file diff: git diff -M @{u}..HEAD -- <path> (or the fallback ref).
  • --range <A>..<B> — review exactly that range. Takes precedence over --unpushed. The pre-push gate passes it, because git tells a pre-push hook precisely what is being sent and where (<local ref> <local sha> <remote ref> <remote sha> on stdin), and that is a different question from "is HEAD ahead of its own upstream". They diverge whenever you push to a ref that is not your upstream — git push origin mybranch:main with mybranch already pushed has nothing unpushed by the @{u} reading, so deriving the range here would review nothing while five commits reached main.
  • --scan — full-file scan of the repo (or of paths if given) instead of a diff review.
  • --json — print ONLY the machine-readable JSON output object (no prose). The push gate relies on this. Without it, print a human-readable report.
  • --rule <path> — explicit rule file (highest precedence).
  • --summary — also produce a project summary (implied by --scan).
  • Any non-flag arguments are treated as path filters (files or directories).

Read the full file on GitHub · 456 lines

Files

What ships with it

7 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.

  1. 4d ago Changed · +13 lines 22ef508ce088
  2. 9d ago First seen · 443 lines · 70 tokens per session scan A 34d0e48a2ff1

Subscribe to this mod's changes

review is a skill published in the GitHub repository Jose-Ribeir/claude-code-review-gate (3 stars, last pushed 7d ago), licensed Apache-2.0. It adds 70 tokens to every session and 5,755 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

rami-code-review

Run the Rami review loop on a PR — fetch findings, fix or rebut each by severity, push, repeat until readyforreview is true. Invoked by /rami:review and auto-triggered when the user asks for "rami review", "review my PR", "fix all rami issues", or similar.

rami-code-review/claude-code-marketplace · 72 tokens

rami-rebut-finding

Use when the user wants to challenge, rebut, or dispute a Rami code review finding — phrases like "rebut this", "this is a false positive", "Rami is wrong about X", "tell Rami this is intentional". Walks through the right MCP tool to use, the four valid rebut reasons, and what to do when Rami rejects the rebuttal.

rami-code-review/claude-code-marketplace · 84 tokens

rami-review-status

Check the current Rami review status without triggering a new review. Use when the user asks whether a Rami review is finished, ready, blocked, queued, or in progress.

rami-code-review/claude-code-marketplace · 41 tokens

java-cache

Use when the user asks to add caching, configure Redis or Caffeine cache, use @Cacheable/@CacheEvict/@CachePut, optimize repeated database or API calls, or review existing Spring Boot cache configuration.

ducpm2303/claude-java-plugins · 46 tokens

java-jpa

Reviews Spring Data JPA for N+1 queries, fetch strategies, projections, and Specifications. Use when user asks to "review JPA", "check for N+1", "JPA performance", "review my entities", "check fetch strategy", or "review my repositories".

ducpm2303/claude-java-plugins · 57 tokens

java-health

Runs a holistic code health check scoring Security, Tests, Performance and Quality with A-F grades. Use when user asks to "check health", "score this project", "health check", "how good is this code", "overall assessment", or "code quality score".

ducpm2303/claude-java-plugins · 54 tokens