원클릭으로
ship
Use after audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use after audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when the user invokes /evo:loop or asks to run autonomous improvement cycles, self-evolving development, compound discovery, or multi-cycle code improvement with research, build, audit, and learning phases
Use after build has produced build-report.md. Validates the build via four parallel sub-auditors (eval-replay, lint, regression, build-quality) and produces ALL-PASS verdict. Adversarial mode default-on per CLAUDE.md.
Use when the user asks to explain how a feature/subsystem works and how the loops built it, or what the concurrent loops/lanes/cycles did and why. Default output = per-FEATURE HTML explainer pages (two movements — how it works today, then how it got built, with verified file:line claims and drift callouts) under docs/explain/; per-batch/per-lane story pages are the fallback framing. Derived from geoffreylitt/explain-diff-html, customized for evolve-loop.
Use when writing or changing any production code or tests — new features, bug fixes, refactors, or test authoring, in any language, by any model on any CLI.
Use when running any LLM agent below Fable 5 — Claude (Opus/Sonnet/Haiku), GPT via codex, Gemini via agy, or local models via ollama — to adopt Fable 5's operating discipline — evidence-first investigation, premise verification, root-cause-only fixes, adversarial self-review, calibrated autonomy, and honest failure reporting. Load at session start or as a persona overlay for phase agents on any CLI.
Use after ship completes. Three sub-reflectors (instinct, gene, failure) run in parallel to extract lessons, update gene pool, and analyze any failures. Off the latency-critical path.
| name | ship |
| description | Use after audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out. |
Sprint 3 composable skill. Wraps the Ship phase. The atomic commit at the end of every successful cycle.
audit returns Verdict PASS (or WARN with explicit override)audit phase, transitioning to ship--class cycle, --class manual, or --class release explicitly)| Step | Action | Exit criteria |
|---|---|---|
| 1 | Verify audit verdict = PASS via gate_audit_to_ship | Gate passes |
| 2 | Run legacy/scripts/utility/release.sh <version> for consistency check | Markers consistent |
| 3 | Run legacy/scripts/lifecycle/ship.sh "<commit message>" | Atomic commit + tag created |
| 4 | Verify ledger entry added | kind: "ship" with cycle binding |
Ship is ATOMIC by design — even if other phases fan out, Ship cannot. There is one git commit per cycle. Concurrent ship attempts on the same cycle are blocked by phase-gate-precondition.sh (only one active_agent: orchestrator at ship phase).
legacy/scripts/lifecycle/ship.sh refuses to ship if the current tree-state SHA differs from the SHA captured at audit time (in the auditor's ledger entry). Prevents "audit cycle 50, ship cycle 51" exploits. This guarantee is preserved through Sprint 3's tri-layer refactor.
| Fact | Value |
|---|---|
| Phase | ship (control archetype, mandatory) |
| Persona | agents/evolve-orchestrator.md |
| Profile | .evolve/profiles/orchestrator.json — CLI claude-tmux, tier balanced, single-writer |
| Inputs | audit-report.md |
Invoked by:
/evo:ship (user-driven)loop macro after /evo:auditlegacy/scripts/lifecycle/ship.sh (atomic commit + tag)legacy/scripts/release-pipeline.sh (full release lifecycle for publish operations)docs/release-protocol.md (vocabulary: push / tag / release / propagate / publish / ship)