Summary
Most code reviews catch bugs in the diff. This one steps back and asks whether you should ship the diff at all. It starts by questioning intent and looking for simpler alternatives, then traces the actual runtime path end to end, not just the changed lines. Every finding comes with file-and-line evidence, a rationale, and a concrete fix. No LGTM stamps, no hedging. Trigger it with /scrutinize or whenever you need a cold read on a PR, plan, or design doc before you commit to the approach. Best used when you're close to the code and need an outsider sanity check.
Install to Claude Code
npx -y skills add thananon/9arm-skills --skill scrutinize --agent claude-codeInstalls into .claude/skills of the current project.
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Files
SKILL.md
Select a file.
Featured
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →First SeenJul 14, 2026
