oh-my-agent
Don't trust AI runs? It gates on artifacts, logs append-only, and uses independent judges—across 10+ runtimes.
What does this skill do?
The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.
Why is it worth installing?
Unlike log-only harnesses, it gates on artifacts with independent judges and append-only trails—the only one that makes agents.
How do you install it?
git clone --depth 1 https://github.com/first-fluke/oh-my-agent.git Then point your agent at the skill directory.
Where does it come from?
Repository: first-fluke/oh-my-agent 1226 stars on GitHub at the time of listing. The repository ships 94 skills in total. Homepage: https://firstfluke.com/oh-my-agent/