code-review

A code-review skill that uses several helper agents with different viewpoints to examine the changes on a branch, then combines their findings into a review report.

In plain words
What is it for?
Use it to review a branch or pull request, summarize what changed and why, identify findings, and produce reports for both people and other agents.
Why use it?
It reduces the chance that one reviewer misses bugs, security concerns, or changes that do not match the stated purpose of a pull request. A pull request is a proposed set of code changes for review before merging.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/vaayne/agent-kit/code-review
Any agent
npx skills add vaayne/agent-kit --skill code-review
Clone the repo
git clone --depth 1 https://github.com/vaayne/agent-kit

Made for: Claude Code, Codex.

Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,980 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00201 $0.03980
Opus 5 $0.00101 $0.01990
Sonnet 5 $0.00040 $0.00796
Haiku 4.5 $0.00020 $0.00398

Measured yesterday against content hash 784e3e4d3173, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 yesterday.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/render-review.mjs, scripts/review-lib.mjs, scripts/update-review.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/code-review/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review — Multi-Perspective Adversarial Debate

Review the current branch's changes using parallel subagents with distinct expertise, then consolidate findings through debate into a review bundle: review.json for agents, events.jsonl for audit history, and rendered report.html / summary.md for humans.

Process

Phase 1: Gather Context

  1. Determine the base branch (default: main or master). If the user provides a PR number, use gh pr diff <number> instead.
  2. Run:
    git log --oneline $(git merge-base HEAD <base>)..HEAD
    git diff $(git merge-base HEAD <base>)..HEAD
    
  3. If the diff is empty, stop and tell the user there are no changes to review.
  4. Identify the languages, frameworks, and key files touched.
  5. Capture the PR's intent for the overview: read the commit messages, the PR description (gh pr view <number> when a PR number is given), and any goal the user stated. Note the claimed purpose and whether the diff actually matches it.
  6. Offer a scout pass. Before going further, ask the user once whether they want a scout pass (the scout skill) to map the PR's territory first — where the changed area sits in the codebase, prior art and conventions around it, domain vocabulary, and common potholes. Recommend it when the diff touches an area the user seems unfamiliar with; note it overlaps little with Phase 2, which explains the change itself rather than the territory around it. Skip the question when the user explicitly asked for review-only output, or when rerunning the same branch and they already answered. If they say yes, run the scout skill (typically its blindspot pass, scoped to the diff's territory), deliver its output, then continue with Phase 2.

Phase 2: Explain the Change Before Reviewing

Before spawning subagents, explain the PR or branch changes to the user in plain language. This gives the user a shared mental model before the adversarial review starts; do not skip it unless the user explicitly asks for review-only output.

Read the full file on GitHub · 252 lines

Files

What ships with it

5 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. yesterday First seen · 252 lines · 201 tokens per session scan A 784e3e4d3173

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository vaayne/agent-kit (53 stars, last pushed 5d ago), licensed MIT. It adds 201 tokens to every session and 3,980 once invoked, about $0.0010 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 2026-08-30.

Related

Other skills, from other repositories

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

agentmail

Use when an agent needs AgentMail CLI email inboxes.

NousResearch/hermes-agent · 15 tokens

skill-template

Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.

muratcankoylan/Agent-Skills-for-Context-Engineering · 24 tokens

Agent Development

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…

anthropics/claude-code · 80 tokens

skill-creator

Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.

yologdev/yoyo-evolve · 46 tokens

subagent-delegation

Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.

toonight/get-shit-done-for-antigravity · 42 tokens