aidd-loop
/aidd-loop
Wymusza dyscyplinę trybu pętli dla etapów implement, review i qa: paczki, zakres, brak pytań i zasady ponowień.
- Autor
- grinrus ↗
- Repozytorium
- ai_driven_dev ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 08.09.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 21
- Skrypty
- 18
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 08.09.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 18 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: runtime/claude_stream_render.py, runtime/loop_block_policy.py, runtime/loop_pack.py, runtime/loop_pack_parts/__init__.py, runtime/loop_pack_parts/core.py, runtime/loop_run.py, runtime/loop_run_parts/__init__.py, runtime/loop_run_parts/core.py, runtime/loop_step.py, runtime/loop_step_parts/__init__.py, runtime/loop_step_parts/core.py, runtime/loop_step_policy.py, runtime/loop_step_stage_chain.py, r
Co robi i kiedy
Wymusza dyscyplinę trybu pętli dla etapów implement, review i qa: paczki, zakres, brak pytań i zasady ponowień.
Oryginalny opis (EN)
Enforces loop-mode discipline for implement/review/qa (packs, scope, no questions). Use when loop stages require bounded scope and retry policy. Do not use when direct stage execution belongs to `implement`, `review`, or `qa` stage skills.
Jak działa
- Loop discipline
- Preload matrix v2
- Canonical shared Python entrypoints
- Command contracts
- Additional resources
Podgląd SKILL.md
---
name: aidd-loop
description: Enforces loop-mode discipline for implement/review/qa (packs, scope, no questions). Use when loop stages require bounded scope and retry policy. Do not use when direct stage execution belongs to `implement`, `review`, or `qa` stage skills.
lang: en
model: inherit
user-invocable: false
---
Follow `feature-dev-aidd:aidd-core` for output contract and DocOps.
## Loop discipline
1. Read order: loop pack -> review pack (if any) -> fix_plan.json when verdict=REVISE -> rolling context pack.
2. Excerpt-first: do not read full PRD/plan/tasklist/spec when the loop pack excerpt covers Goal/DoD/Boundaries/Expected paths/Size budget/Tests/Acceptance.
3. No questions in loop-mode; record blockers/handoff instead.
4. REVISE: reuse the same scope, follow fix_plan.json, and do not widen boundaries.
5. Scope guard: out-of-scope -> WARN + handoff; forbidden -> BLOCKED. Never expand boundaries yourself.
6. Tests: follow loop pack or reviewer policy; do not invent new test requirements.
7. No large logs/diffs in chat; link to `aidd/reports/**`.
8. Block policy: `strict` fail-fast by default; `strict_recoverable_reason_codes` may explicitly enable bounded retries for selected reasons (for example `no_tests_hard`).
9. `ralph` uses policy matrix v2 (`hard_block|recoverable_retry|warn_continue`) with bounded retries for recoverable reasons.
10. For recoverable blocked retries, emit observability fields: `recoverable_blocked`, `recovery_path`, `retry_attempt`, plus `ralph_reason_class|strict_recoverable_reason_class`.
11. Scope mismatch fallback is telemetry-only (`scope_mismatch_non_authoritative=1`): emit `expected_scope_key`/`selected_scope_key`; do not treat mismatched fallback as authoritative transition input.
## Preload matrix v2
- Roles: `implementer`, `reviewer`, `qa`.
- This skill must not be preloaded for other subagents.
## Canonical shared Python entrypoints
- `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-loop/runtime/loop_pack.py`
- `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-loop/runtime/loop_step.py`
- `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-loop/runtime/loop_run.py`
- `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-loop/runtime/preflight_result_validate.py`
- `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-loop/runtime/output_contract.py`
- Preflight preparation is stage-chain-internal and not an operator command.
## Command contracts
### `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-loop/runtime/loop_pack.py`
- When to run: before loop stage execution to assemble bounded evidence input.
- Inputs: ticket/scope context and available stage artifacts (`readmap`, `review pack`, context pack).
- Outputs: deterministic loop pack summary for implement/review/qa orchestration.
- Failure mode: non-zero exit when required upstream artifacts are missing or malformed.
- Next action: repair missing prerequisites and rerun pack generation.
### `python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-loop/runtime/loop_run.py`
- When to run: stage-chain-orchestrated loop execution for bounded stage retries.
- Inputs: loop mode/profile, ticket/scope context, and stage-specific payloads.
- Outputs: loop execution status with deterministic retry/blocked metadata.
- Failure mode: non-zero exit on invalid loop payload, policy violation, or unrecoverable blocked condition.
- Next action: apply fix plan or handoff policy action, then rerun with unchanged scope.
## Additional resources
- Loop stage-chain reference: [reference.md](reference.md) (when: stage-chain path/fallback behavior needs clarification; why: confirm canonical chain and bounded recovery policy).
- Loop pack template source: [templates/loop-pack.template.md](templates/loop-pack.template.md) (when: loop pack format is unclear; why: confirm canonical sections seeded by init/runtime).
Pliki w paczce (21)
- SKILL.md 4 KB
- reference.md 1 KB
- runtime/claude_stream_render.py 6 KB
- runtime/loop_block_policy.py 7 KB
- runtime/loop_pack.py 1 KB
- runtime/loop_run.py 1 KB
- runtime/loop_step.py 1 KB
- runtime/loop_step_policy.py 8 KB
- runtime/loop_step_stage_chain.py 29 KB
- runtime/loop_step_stage_result.py 14 KB
- runtime/marker_semantics.py 3 KB
- runtime/output_contract.py 11 KB
- runtime/preflight_prepare.py 31 KB
- runtime/preflight_result_validate.py 10 KB
- runtime/loop_pack_parts/__init__.py 1 KB
- runtime/loop_pack_parts/core.py 39 KB
- runtime/loop_run_parts/__init__.py 1 KB
- runtime/loop_run_parts/core.py 113 KB
- runtime/loop_step_parts/__init__.py 1 KB
- runtime/loop_step_parts/core.py 98 KB
- templates/loop-pack.template.md 1 KB
Wersje
W bazie nie ma innych skilli o nazwie aidd-loop.
Migawka bazy z 13.11.2026 · wersja paczki bddcc763d955 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100aidd-policy
Definiuje wspólny kontrakt polityki dla formatu wyjścia, dyscypliny odczytu, formatu pytań i bezpieczeństwa pętli, stosowany w regułach przekrojowych etapów. - 90implement
Wykonuje pętlę etapu implementacji dla kolejnego zakresowego zadania w orkiestracji etapów. - 100aidd
Stosuje zasady repozytorium aidd przed każdą zmianą: poprawką, funkcją, refaktoryzacją, commitem, pushem lub pull requestem, zgodnie z trasą i regułami ryzyka. - 100code-review
Przegląda diff względem specyfikacji w repozytorium aidd, pomagając ocenić gotowość pull requesta do scalenia. - 90implement
Wdraża jedno zaplanowane zgłoszenie, opcjonalnie w ograniczonej pętli autonomicznej, jako jedną część zatwierdzonego planu. - 100review-loop
Sprawdza zmianę modelem od innego dostawcy w pętli, aż ją zatwierdzi, a także przed otwarciem pull requestu.