github-code-review

Comprehensive GitHub code review with AI-powered swarm coordination.

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

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,644 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown 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 $0.00015 $0.06644
Opus 5 $0.00008 $0.03322
Sonnet 5 $0.00003 $0.01329
Haiku 4.5 $0.00002 $0.00664

Measured today against content hash 6ed59c79ed71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-code-review scanned grade A 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 today.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

const { execSync } = require('child_process');
.claude/skills/github-code-review/SKILL.md · 1,141 lines

How it starts

The opening of the file, as written. The whole thing — 1,141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Code Review Skill

AI-Powered Code Review: Deploy specialized review agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis.

🎯 Quick Start

Simple Review

# Initialize review swarm for PR
gh pr view 123 --json files,diff | npx ruv-swarm github review-init --pr 123

# Post review status
gh pr comment 123 --body "🔍 Multi-agent code review initiated"

Complete Review Workflow

# Get PR context with gh CLI
PR_DATA=$(gh pr view 123 --json files,additions,deletions,title,body)
PR_DIFF=$(gh pr diff 123)

# Initialize comprehensive review
npx ruv-swarm github review-init \
  --pr 123 \
  --pr-data "$PR_DATA" \
  --diff "$PR_DIFF" \
  --agents "security,performance,style,architecture,accessibility" \
  --depth comprehensive

📚 Table of Contents

Read the full file on GitHub · 1,141 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. today First seen · 1,141 lines · 15 tokens per session scan A 6ed59c79ed71

Subscribe to this mod's changes

github-code-review is a skill published in the GitHub repository spencermarx/open-code-review (352 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 6,644 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.