self-healing-orchestratorlisted

> **AI-consumed reference.** Optimized for Claude to read during execution. > Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md) > or [docs/getting-started/](../../../docs/getting-started/) depending on topic. # Self-Healing Orchestrator **STATUS — v3.7.0-rc.1.** Per-spec safety gates strictly enforced. ## Core Principle **Self-healing PROPOSES; the user APPLIES.** A proposal goes through the same approval gate as a manual replan — there is no autonomous patch. If you find this skill applying patches without a user yes, that's a bug. ## Hard constraints (per spec §22.1) ```toon constraints[6]{rule,enforcement}: "ONLY F2 (local-logic) or F3 (local-design)","Refuse if classifier returns F1/F4/F5/F6 — those need different paths" "ONLY proposes; NEVER applies","Output is always a proposal artifact; user runs /aura-frog:heal accept <id> to apply" "Confidence < 0.7 → don't propose","Surface raw findings only; user decides if a fix is even reachable" "Counts toward replan_budget","Same node-level budget enforcement as replanner (per replan-thresholds.md)" "Max 1 self-heal per task","Once a task accepts a self-heal patch, no further auto-proposals for that task" "Session cap: 5 proposals total","Anti-fatigue + anti-loop; after 5, defer to manual /aura-frog:plan-replan" ``` ## Disable mechanisms (per spec §22.3, §31.3) - **Per-session:** `/aura-frog:heal disable` — sets `.claude/logs/.s