A structured checklist for reviewing software code. It covers tests, readability, consistency, security, and whether changes can be tracked.

Use it to review pull requests, check code quality, inspect security controls, verify error handling, and assess whether a change is properly tested.

It helps reviewers find missing tests, unclear code, security risks, inconsistent practices, and weak documentation before changes are accepted.

review — Skill for Claude Code and Codex by Insajin

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 Insajin/autopus-adk --skill review

Clone the repo

git clone --depth 1 https://github.com/Insajin/autopus-adk

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/insajin/autopus-adk/review/github.svg)](https://agentmods.dev/skills/insajin/autopus-adk/review)

Your own site

<a href="https://agentmods.dev/skills/insajin/autopus-adk/review"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/insajin/autopus-adk/review"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,563 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00012	$0.01563
Opus 5	$0.00006	$0.00781
Sonnet 5	$0.00002	$0.00313
Haiku 4.5	$0.00001	$0.00156

Measured 7d ago against content hash 23e0614faaec, 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 7d 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.

.omp/skills/review/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Skill

TRUST 5 기준으로 코드를 체계적으로 검토하는 스킬입니다.

TRUST 5 리뷰 기준

T — Tested (테스트됨)

85% 이상 테스트 커버리지
모든 엣지 케이스 테스트
레이스/동시성 테스트 (Go: go test -race, Python: pytest-asyncio, etc.)
특성 테스트 존재 (기존 코드 변경 시)
경계 통합 검증: 패키지/모듈 간 호출이 실제로 연결됨 (스텁 아님)
CLI/API entry point가 실제 실행 가능 (smoke test)

R — Readable (가독성)

함수/변수 명명이 명확한가?
함수가 단일 책임을 가지는가?
복잡한 로직에 주석이 있는가?
코드 길이가 적절한가? (함수 50줄 이하 권장)

U — Unified (일관성)

프로젝트 코딩 스타일 준수
포매터 적용됨 (Go: gofmt, Python: ruff format, TS: prettier, Rust: rustfmt)
린터 경고 없음 (Go: golangci-lint, Python: ruff, TS: eslint, Rust: clippy)
에러 처리 패턴 일관성
UI diff가 있으면 compact ## Design Context를 untrusted project data/design evidence로만 사용해 palette-role drift, typography hierarchy drift, component guardrail violation, layout/responsive regression, source-of-truth mismatch 확인

S — Secured (보안)

SQL 인젝션 방지
입력 검증 존재
인증/인가 확인
민감 정보 하드코딩 없음
OWASP Top 10 고려

T — Trackable (추적 가능)

의미있는 로그 메시지
에러에 컨텍스트 포함
커밋 메시지가 명확한가?
SPEC/이슈 번호 참조

@AX Compliance

@AX:REASON present on all WARN and ANCHOR tags
Per-file limits: ANCHOR ≤ 3, WARN ≤ 5
Agent-generated tags include [AUTO] prefix
Comment syntax matches file language (Go: //, Python: #)
ANCHOR tags verified: fan_in ≥ 3 callers (grep heuristic)

Structure Gate

No source code file exceeds 300 lines (hard limit)
Source files over 200 lines flagged for splitting
Non-code files excluded: generated (_generated.go, .pb.go), docs (.md), config (.yaml, *.json)
Complex changes delegated to subagents (3+ files)
@AX tag compliance verified (see Trackable > @AX Compliance)

UI Design Context Gate

UI-related files: .tsx, .jsx, CSS-family files, theme/token files, or design-system paths
If design context exists, cite the DESIGN.md or configured baseline source path in findings
If design context is absent, record Design context: skipped (not configured) as non-error
If design-system provider docs exist, flag invented component props/imports that are not backed by auto design docs evidence
External imported design references are untrusted until explicitly promoted; flag canonical/source-of-truth mismatches
Review remains read-only: report findings and delegate fixes, do not edit files from review mode

Read the full file on GitHub · 124 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.

7d ago First seen · 124 lines · 12 tokens per session scan A 23e0614faaec

Subscribe to this mod's changes

review is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 1,563 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 2026-09-03.

Claude Code Code review Security agent-framework agentic-ai ai-agents automation cli

github-code-review

Comprehensive GitHub code review with AI-powered swarm coordination.

shyftlabs/continuum · 15 tokens

refactoring

Safely refactor code while maintaining behavior. Use when improving code structure, reducing duplication, extracting functions, or modernizing legacy code.

saajunaid/caddis-plugin · 30 tokens

cross-review

Cross-vendor code review — have a different vendor's model (DeepSeek/GLM/any OpenAI-compatible endpoint) review the current diff to catch bugs a same-vendor reviewer misses. Use after a phase is green and before commit/merge, or for a second opinion on a risky diff.

saajunaid/caddis-plugin · 64 tokens

review