القائمة
Use after tdd has written RED tests and the contract is in team-context.md. Implements the minimum code to turn RED tests GREEN. Runs in a worktree with single-writer invariant.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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 | build |
| description | Use after tdd has written RED tests and the contract is in team-context.md. Implements the minimum code to turn RED tests GREEN. Runs in a worktree with single-writer invariant. |
Sprint 3 composable skill. Wraps the Builder phase. Builder is the only fan-out-incompatible phase — single worktree, single set of mutations.
tdd has produced RED teststdd or discover phase per cycle-state| Step | Action | Exit criteria |
|---|---|---|
| 1 | Read TDD contract from team-context.md | Contract loaded |
| 2 | Implement minimum code to turn RED → GREEN | Tests pass locally |
| 3 | Run regression suite (legacy/scripts/utility/run-all-regression-tests.sh) | No new regressions |
| 4 | Write <workspace>/build-report.md | Report present + fresh + token-bound |
Builder runs in a dedicated worktree. Concurrent builders are STRUCTURALLY blocked because:
git diff HEADphase-gate-precondition.sh allows only one active_agent per cycleThis is why Builder cannot fan-out even though Scout and Auditor can.
| Fact | Value |
|---|---|
| Phase | build (build archetype, mandatory) |
| Persona | agents/evolve-builder.md |
| Profile | .evolve/profiles/builder.json — CLI codex-tmux, tier balanced, single-writer |
| Inputs | scout-report.md · triage-report.md |
| Artifact | build-report.md (cycle workspace) |
build-report.md must declare:
## Changes (also accepted: ## Files Changed, ## Files Modified)Invoked by:
/evo:buildloop macro after /evo:tddagents/evolve-builder.md.evolve/profiles/builder.jsonskills/loop/phase3-build.md (legacy detailed workflow)