review

review is a skill for Claude Code from yash-gadodia/claude-init. It costs 27 tokens per session (994 once invoked), scanned A, original, MIT.

A two-stage code-review workflow that first checks whether a change meets its requirements and then checks its code quality.

In plain words
What is it for?
Use it to review a branch or pull request against the requested specification, tests, recent changes, and the quality of each modified file.
Why use it?
It catches missing or unnecessary work before focusing on correctness, maintainability, and other quality concerns.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the claude-init plugin — 11 skills, 1 command, 7 agents shipped together

Good fit Use it to review a branch or pull request against the requested specification, tests, recent changes, and the quality of each modified file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yash-gadodia/claude-init/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 yash-gadodia/claude-init --skill review
Clone the repo
git clone --depth 1 https://github.com/yash-gadodia/claude-init

Made for: Claude Code.

Or install claude-init, the plugin that ships this one along with the rest of its 11 skills, 1 command, 7 agents.

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/yash-gadodia/claude-init/review/github.svg)](https://agentmods.dev/skills/yash-gadodia/claude-init/review)
Your own site
<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/review"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/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/yash-gadodia/claude-init/review"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 994 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 $0.00027 $0.00994
Opus 5 $0.00014 $0.00497
Sonnet 5 $0.00005 $0.00199
Haiku 4.5 $0.00003 $0.00099

Measured 11d ago against content hash 75077446f4cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 11d 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.

templates/skills/review/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review: Two-Stage Code Review

Review all changes in two passes: first check if the spec is met, then check code quality.

When This Triggers

Automatically after implementing any change. Also useful before committing or creating PRs.

Process

Stage 1: Spec Compliance

Does the code match what was requested?

Change summary (loaded fresh when this skill triggers):

!git diff --stat HEAD 2>/dev/null || git diff --stat

Recent commits on this branch:

!git log --oneline -5 2>/dev/null || echo "(no git history)"

Read the full diff for any file that shows up above before judging it — git diff HEAD -- <file> for unstaged + staged, git diff <base>...HEAD -- <file> when reviewing a PR. Never review from memory.

For each requirement/acceptance criterion from the plan or request:

  • Is there code implementing it?
  • Is there a test verifying it?
  • Does the implementation match the spec (not over-build, not under-build)?

Missing requirement? Flag it. Don't proceed to Stage 2 until spec is met. Extra code not in spec? Flag it. YAGNI — remove unless there's a clear reason.

Stage 2: Code Quality

For each changed file, check:

Correctness:

  • Does the logic do what it claims?
  • Edge cases handled (null, empty, boundary values)?
  • Off-by-one errors?
  • Async operations handle errors and race conditions?

Security:

  • User input validated and sanitized?
  • No SQL injection, XSS, or command injection?
  • No credentials or secrets in code?
  • Auth checks present where needed?

Conventions:

  • Matches existing patterns in the codebase?
  • Uses existing utilities instead of reinventing?
  • Follows naming conventions?

Tests:

  • New functionality has tests that followed TDD (test was written first)?
  • Tests assert exact expected values, not ranges?
  • Test names describe behavior?

Severity taxonomy

Label every finding — not all feedback is mandatory, and treating nits as blockers erodes trust in the review:

Severity Meaning Action
Critical Bug, security hole, data loss, spec violation Blocks approval
Important Wrong pattern, missing test, latent bug Should fix before merge
Nit Style, naming, minor cleanup Author may ignore
FYI Informational, no change requested No action

Read the full file on GitHub · 123 lines

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. 11d ago First seen · 123 lines · 27 tokens per session scan A 75077446f4cc

Subscribe to this mod's changes

review is a skill published in the GitHub repository yash-gadodia/claude-init (5 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 994 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.