Analyze a Harny 0.5 run from run.json v4, audit events, normalized attempt transcripts, ChangeSets, and provider usage. Use after failed, retried, slow, costly, paused, mixed-provider, or otherwise surprising runs.
Walk a repo through the harny readiness checklist. Score 10 dimensions Red/Yellow/Green, surface anti-signals, output a scorecard + prep checklist. Use when adopting harny in a new repo, or troubleshooting why it struggles in a familiar one.
Onboard and route users through Harny's declarative Claude/Codex workflows, local run state, provider configuration, human review, PR delivery, inspection, and cleanup. Use when someone is new to Harny, asks how it works, or needs help choosing the right…
Operate a release cycle across Harny 0.5 runs and draft PRs. Use when coordinating multiple scoped changes, choosing feature-dev versus feature-pr, reviewing run evidence and usage, fixing PR feedback, running release gates, merging with explicit approval, or…
Triage accumulated learnings from the local harny inbox into GitHub Issues, AGENTS.md edits, or discards. Walks one entry at a time, verifies claims against current code, opens issues with provenance. Sister of /learn.
Append a one-line learning to the local harny inbox. Fast, non-analytical capture — copies text verbatim, no analysis, no follow-ups. Use when the user wants to note something about harny adoption mid-conversation without breaking flow.