ccc-looplisted

# $ccc-loop — Loop Integration Guide Claude Code has **four loop primitives**, not one. This skill is the entry point for all of them — pick the right primitive before you reach for `/loop` by habit. ## The 4 loop types | Type | Trigger | Stop criteria | CC Commander primitive | Best for | |---|---|---|---|---| | **Turn-based** | A user prompt | Claude judges "done" itself | Just run the skill directly; encode your manual verification steps as a `SKILL.md` so Claude can self-check | Short one-off tasks | | **Goal-based** | A manual prompt, real-time | Goal achieved OR max turns reached — an evaluator model checks your condition each time Claude tries to stop | `/goal` | Tasks with a verifiable exit criterion (test count, score threshold, build passing) | | **Time-based** | An interval | You cancel it, or the work completes (PR merged, queue empty) | `/loop` (local) + `/schedule` (cloud) | Recurring work, polling external systems | | **Proactive** | An event or schedule, no human in real time | Each task exits on its own goal; the routine runs until you turn it off | `/schedule` (heartbeat) + `/goal` (define done) + dynamic Workflow (orchestrate) + auto mode (no confirmation stops) | Recurring streams of well-defined work — bug triage, migrations, dependency upgrades | Deterministic, quantitative checks beat vague ones for every type above — "tests pass" and "score ≥ 90" are checkable; "looks good" is not. ## Should this be a loop? (gate before you build one) All four mu