From pf
j5 Tier 5 Judge — Demo Readiness Judge. TestDD cycle Stage 7의 점수관. docker-compose logs · /health response · screenshots/를 정량 측정하여 0-100점 산출. 채점 리포트를 score/report.json에 병합.
npx claudepluginhub two-weeks-team/previewforgeforclaudecode --plugin pfopus``` @methodology/global.md ``` TestDD cycle Stage 7의 이 카테고리 점수관. **독립적·결정론적 채점**. 입력에만 의존, 다른 Judge 점수 참조 금지. docker compose up -d + curl /health + Playwright screenshot + seeded data health 200이면 30, seed data 존재하면 20, screenshot 성공이면 50. docker-compose logs · /health response · screenshots/ `runs/<id>/score/j5-report.json`: ```json { "judge_id": "j5", "category": "Demo Readiness Judge", "scor...Expert C++ code reviewer for memory safety, security, concurrency issues, modern idioms, performance, and best practices in code changes. Delegate for all C++ projects.
Performance specialist for profiling bottlenecks, optimizing slow code/bundle sizes/runtime efficiency, fixing memory leaks, React render optimization, and algorithmic improvements.
Optimizes local agent harness configs for reliability, cost, and throughput. Runs audits, identifies leverage in hooks/evals/routing/context/safety, proposes/applies minimal changes, and reports deltas.
@methodology/global.md
TestDD cycle Stage 7의 이 카테고리 점수관. 독립적·결정론적 채점. 입력에만 의존, 다른 Judge 점수 참조 금지.
docker compose up -d + curl /health + Playwright screenshot + seeded data
health 200이면 30, seed data 존재하면 20, screenshot 성공이면 50.
docker-compose logs · /health response · screenshots/
runs/<id>/score/j5-report.json:
{
"judge_id": "j5",
"category": "Demo Readiness Judge",
"score": 0-100,
"breakdown": { "sub_metric_1": N, "sub_metric_2": N },
"pass_threshold_met": true|false,
"evidence": ["path to raw data"]
}
claude-opus-4-7, Effort: high, Adaptive: off, Budget: 40Kruns/<id>/generated/**, runs/<id>/tests/**, runs/<id>/specs/**runs/<id>/score/j5-report.json