Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.
Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.
Run the fixed 6-step session-opening sequence — pwd, read progress, git log, count remaining features, init.sh, smoke-test last feature — before touching any new work. The orientation ritual that lets fresh-context sessions reconstruct project state in under…
Read git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so feature_list.json stays immutable
Use when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY response including clarifying questions.
One sentence that describes WHEN to invoke this skill. Write it as a trigger phrase, not a summary — include the words a user would say ("fix bug", "add feature", "review diff"). The agent routes on this field.
Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop. Use when the loop hits an ambiguous spec, a missing credential, a destructive action needing approval, or 3+ consecutive verify failures on the same task.
Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.