github-deep-review

github-deep-review is a skill for Claude Code, Codex from katalalab/katala-os. It costs 55 tokens per session (453 once invoked), scanned A, original, MIT.

A detailed review process for a GitHub pull request or commit, which is a proposed or recorded set of code changes. It follows how changed code is used, checks risks, and examines whether tests cover important cases.

In plain words
What is it for?
It helps assess correctness, affected callers, security, destructive operations, race conditions, and missing tests before code is merged.
Why use it?
It can reveal problems that are easy to miss when only reading the changed lines, including regressions, security issues, data loss risks, and concurrency bugs.

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/katalalab/katala-os/github-deep-review
Any agent
npx skills add katalalab/katala-os --skill github-deep-review
Clone the repo
git clone --depth 1 https://github.com/katalalab/katala-os

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 github-deep-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/katalalab/katala-os/github-deep-review.svg)](https://agentmods.dev/skills/katalalab/katala-os/github-deep-review)
Your own site
<a href="https://agentmods.dev/skills/katalalab/katala-os/github-deep-review"><img src="https://agentmods.dev/badge/skills/katalalab/katala-os/github-deep-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 453 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 $0.00055 $0.00453
Opus 5 $0.00028 $0.00227
Sonnet 5 $0.00011 $0.00091
Haiku 4.5 $0.00006 $0.00045

Measured 5d ago against content hash 2a74ee95b176, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-deep-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 5d 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/github-deep-review/SKILL.md · 58 lines

What it actually says

github-deep-review — comprehensive PR/commit analysis

Performs a multi-layer review: diff reading → call-path tracing → risk assessment → test coverage check.

When to use

  • "この PR を深くレビューして"
  • "マージ前に regression リスクを確認して"
  • "セキュリティ観点で見てほしい"
  • "テストが十分か確認して"

Do not use for:

  • Quick style or formatting checks (use /code-review instead)
  • Reviewing your own just-written code (too much context bias)

Review layers

1. Diff surface

gh pr diff <pr-number>
gh pr view <pr-number> --json title,body,files,reviews,checksums

2. Call-path impact

Use code_mapper subagent or rg to trace callers of changed functions.

3. Risk dimensions (report each separately)

  • Correctness: logic errors, off-by-one, null handling
  • Regressions: changed behavior in existing callers
  • Security: injection, auth bypass, secret exposure, SSRF
  • Data loss: destructive ops, migration safety, rollback path
  • Concurrency: race conditions, lock order, shared state mutation
  • Test coverage: uncovered branches, missing edge cases

4. Verdict

APPROVE / REQUEST_CHANGES / NEEDS_DISCUSSION
Confidence: high | medium | low
Blockers: [list]
Non-blockers: [list]

Hard-rule reminders

  • Report confidence level for each finding.
  • Distinguish "blocking" from "non-blocking" issues.
  • Check if CI passed before calling coverage adequate.
  • Destructive PRs (migrations, schema changes) require multi-agent consensus per CLAUDE.md.
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. 5d ago First seen · 58 lines · 55 tokens per session scan A 2a74ee95b176

Subscribe to this mod's changes

github-deep-review is a skill published in the GitHub repository katalalab/katala-os (2 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 453 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens