Command
Lock the autonomy-loop control plane read-only so a bypassed gate cannot disable itself (v0.8 Ring 1).
Claude Code terminals pass a git baton through an adversarial, frozen-invariant review gate. Composable builder / reviewer / planner / researcher roles, rigor on by default.
Command
Lock the autonomy-loop control plane read-only so a bypassed gate cannot disable itself (v0.8 Ring 1).
Command
Scaffold + tune the two-terminal autonomy loop into THIS repo (run once, then approve).
Command
Upgrade an existing autonomy-loop install to the current schema (safe, idempotent, run after a plugin update).
Command
Terminal 1 - Builder/Ideator autonomy-loop tick (run on a /loop interval).
Command
Launch an autonomy-loop terminal inside the srt OS sandbox (allow-only writes + an egress allowlist that also bounds the researcher web-fetch).
Command
Terminal 3 - Planner autonomy-loop tick (grill-to-goal spec engine; the feeder in front of the self-feeding loop; run on a /loop interval).
Command
Terminal 3 - Researcher autonomy-loop tick (4-terminal OPT-IN; fills the idea pool; run on a /loop interval).
Command
Terminal 2 - Reviewer/Fixer autonomy-loop tick (effort-scaled critic panel; run on a /loop interval).
Command
ORCHESTRATOR. Run the autonomy loop as subagents in ONE terminal (coordination.mode=single-cli; default OFF; fail-closed). Re-runs decideCoordination, refuses if no independent verification remains, then drives a sequential builder/reviewer baton where the deterministic gate BINDS and the LLM critique is ADVISORY.