
koldovsky/project-factory
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
Self-improving, spec-driven multi-agent SDLC delivery framework — agent-agnostic plugin for Claude Code / Cursor / Copilot / Codex.
概要
— the multi-agent SDD delivery framework — extended with a : the factory now measures its own process with the same exit-coded rigor it applies to the product, turns human corrections into artifacts no gate can pass over, and propagates earned lessons into the next project's gates. It is a public superset — every project-factory capability plus the reflection layer; nothing here is client-specific (all fixtures are synthetic, and campaign lessons cite their field reports abstractly). The layer is grounded in three field studies in this repo: the reflection mechanism design (the winning "Process-Health Ledger" design, 8 mechanisms, 12-step plan), the pixel-perfect forensics (the motivating failure: a run that printed "Pass" over an acceptance method it never executed), and the 13-project course field study. The eight mechanisms (each shipped with an executed red→green proof under tests/; run npm test): 1. (ledger.
README
以下は原文 README の抜粋です。原文を見る。
Self-Improving Project Factory
The self-improving evolution of Project Factory — the multi-agent SDD delivery framework — extended with a reflection & self-improvement layer: the factory now measures its own process with the same exit-coded rigor it applies to the product, turns human corrections into artifacts no gate can pass over, and propagates earned lessons into the next project’s gates. It is a public superset — every project-factory capability plus the reflection layer; nothing here is client-specific (all fixtures are synthetic, and campaign lessons cite their field reports abstractly). The layer is grounded in three field studies in this repo: the reflection mechanism design (the winning “Process-Health Ledger” design, 8 mechanisms, 12-step plan), the pixel-perfect forensics (the motivating failure: a run that printed “Pass” over an acceptance method it never executed), and the 13-project course field study.
What is new in the self-improving layer
The eight mechanisms (each shipped with an executed red→green proof under
tests/; run npm test):
- Process-health ledger (
ledger.mjs) — every check run appends{check, exitCode, scope_n, phase, warningsByClass, …}totrace/ledger.jsonl; fail-open telemetry whose consumers are hard gates. - Acceptance-contract auditor (
check-acceptance-methods.mjs) — joins every declared verification tag to a real mechanism (G3, existence) and a fresh threshold-passing artifact (G4+, artifact); the pixel-case killer, hard from day one. - Three-valued gate semantics — PASS / NOT-EARNED / FAIL + explicit SKIP-pending; absence of evidence never renders as success, and no overall “Pass” may sit on a NOT-EARNED constituent.
- Correction intake (
correct.mjs) — a user’s “this is not pixel perfect!” becomesretro/corrections/*.correction.json; undispositioned corrections are red OPEN-CORRECTION lines on every gate. - Process ratchet with tighten-only direction guard
(
check-process-ratchet.mjs+ retrofitted coverage/eval ratchets) — per-class phase-aware warning budgets; any loosening--updateis auto-rejected and requires a waiver artifact + owner-signedRULES-CHANGELOG.mdrow. - Reflection pass — deterministic digest (
ledger-report.mjs→docs/qa/process-health.md) always; LLMprocess-auditor(plain subagent, maker≠checker) at phase boundaries, on demand, and at abandonment/handover →docs/qa/process-defects.json. - Bounded self-improvement queue — accepted defects become
openspec/changes/improve-PD-x/proposals with the exact diff, an EXECUTED red→green proof, and one-revert rollback; human-approved, and
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add koldovsky/project-factory