Summary
A structured four-phase investigation workflow that forces you to find root causes instead of patching symptoms. It runs git archaeology to pinpoint when bugs were introduced, uses task tools to trace execution paths, and enforces hypothesis testing one change at a time. The audit mode is interesting: it sweeps codebases proactively for resource leaks, concurrency bugs, and edge cases before they bite. After three failed hypotheses, it escalates to architecture review instead of letting you flail. The hard constraint on single-hypothesis testing will feel slow at first, but it prevents the usual scatter-shot debugging that wastes hours. Ships with references for deadlock triage and multi-pass sweeps.
Install to Claude Code
npx -y skills add boshu2/agentops --skill bug-hunt --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
