review

review is a skill for Claude Code, Codex from Bidiche49/claude-conf. It costs 11 tokens per session (495 once invoked), scanned A, original, MIT.

A pre-commit review checklist that examines staged and unstaged code changes and checks rules for common technology stacks.

In plain words
What is it for?
Use it to review changes in projects using technologies such as Flutter, iOS, React, Next.js, Node.js, and other supported stacks.
Why use it?
It helps catch dead code, debug output, missing framework-specific safeguards, secrets, and unrelated edits before a commit.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review changes in projects using technologies such as Flutter, iOS, React, Next.js, Node.js, and other supported stacks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bidiche49/claude-conf/review
Install

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.

Any agent
npx skills add Bidiche49/claude-conf --skill review
Clone the repo
git clone --depth 1 https://github.com/Bidiche49/claude-conf

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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/skills/bidiche49/claude-conf/review/github.svg)](https://agentmods.dev/skills/bidiche49/claude-conf/review)
Your own site
<a href="https://agentmods.dev/skills/bidiche49/claude-conf/review"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/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/bidiche49/claude-conf/review"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 495 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 $0.00011 $0.00495
Opus 5 $0.00005 $0.00247
Sonnet 5 $0.00002 $0.00099
Haiku 4.5 $0.00001 $0.00049

Measured 8d ago against content hash abc41cf0842f, 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 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.

setup-project/skills/review/SKILL.md · 47 lines

What it actually says

Review all staged and unstaged changes before commit. Follow these steps:

Step 1 — Read Changes

Run git diff --stat and git diff to see what changed. If there are staged changes, also run git diff --cached.

Step 2 — Detect Stack

Check project root for: package.json, pubspec.yaml, go.mod, Cargo.toml, pyproject.toml, composer.json, Gemfile, *.xcodeproj, Package.swift, Makefile.

Step 3 — Universal Checklist (all stacks)

For every modified file, verify:

  • Names reveal intent (variables, functions, classes)
  • No dead code (commented-out code, unused variables)
  • No debug statements (print, console.log, debugPrint, pp, var_dump)
  • Diff is coherent — no out-of-scope changes
  • No secrets or credentials in the diff

Step 4 — Stack-Specific Checklist

Stack Additional checks
Flutter/Dart No print() (use Logger), Freezed generated files up to date, barrel imports
iOS/Swift [weak self] in async closures, deinit present where needed, no dynamic force unwrap
React/Next Hooks deps arrays complete, no direct state mutation, server/client boundary respected
Node/Express Error handling middleware, async/await (no raw callbacks), input validation
Go Errors wrapped/returned (not ignored), goroutines with context, defer for cleanup
Python Type hints on functions, async/await coherent, no bare except:
Rust Result/Option handled (no unwrap() in prod code), ownership clear

Step 5 — Report

  • If problems found → list each with file:line and a suggested fix
  • If all clear → print Review OK — ready to commit and show git diff --stat

Rules — NON-NEGOTIABLE

  • The review LISTS problems — it does NOT auto-fix. The user decides.
  • Review ALL changed files, not just the first few.
  • Be specific: file, line number, what's wrong, what to do instead.
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. 8d ago First seen · 47 lines · 11 tokens per session scan A abc41cf0842f

Subscribe to this mod's changes

review is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 495 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.

Related

Other skills, from other repositories

pr-triage

4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…

FlorianBruniaux/claude-code-plugins · 86 tokens

audit-agents-skills

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.

FlorianBruniaux/claude-code-plugins · 41 tokens

review-pr

Perform a comprehensive code review of a pull request.

FlorianBruniaux/claude-code-plugins · 12 tokens

atomic-review

Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.

damusix/atomic-claude · 63 tokens

ralphctl-code-review-and-quality

Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when you are the evaluator assessing a generator's output, and when reviewing any change before signalling…

lukas-grigis/ralphctl · 76 tokens

validate-changes

Evaluate staged changes using LLM-as-a-Judge before committing.

FlorianBruniaux/claude-code-plugins · 16 tokens