메뉴
Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table
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
Ruflo is a multi-agent orchestration platform for AI coding agents (Claude Code, Cursor, Codex, Copilot, Gemini, Amp, +12 more). Use this skill when the user wants to (1) install/init ruflo in a project, (2) run multi-agent swarms with hierarchical coordination, (3) use ruflo's 314+ MCP tools for memory, routing, hooks, sub-agents, or workflows, (4) check ruflo status/version/doctor health, or (5) discover which of ruflo's 30+ plugins fits their task.
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
Build or rebuild the ADR index + dependency graph by running scripts/import.mjs (handles v3-style and plugin-style ADR formats; one Bash call vs hundreds of MCP round-trips)
Reconcile the ADR index against a DELETED ADR file or relation line by dropping and rebuilding adr-patterns + adr-edges from scratch (scripts/reindex.mjs). Use when adr-index alone leaves stale rows behind.
Review code changes against accepted ADRs for compliance violations
Read back adr-patterns + adr-edges namespaces, surface dangling refs / supersede cycles / status mismatches; exit 1 on cycles
| name | cost-benchmark |
| description | Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table |
| argument-hint | [--llm] [--anthropic] |
| allowed-tools | Bash |
Runs scripts/bench.mjs against the structural+adversarial corpus and writes per-case + summary results to docs/benchmarks/runs/. This is the verification gate that backs every measurable claim in cost-booster-edit / cost-booster-route.
bench/booster-corpus.json — confirm new cases route correctly.BENCH_ANTHROPIC=1.Run the bench from v3/ (where agent-booster resolves):
( cd v3 && node ../plugins/ruflo-cost-tracker/scripts/bench.mjs ) # booster only — free, ~85 ms
( cd v3 && BENCH_LLM_BASELINE=1 node ../plugins/ruflo-cost-tracker/scripts/bench.mjs ) # + Gemini 2.0 Flash (cheap)
( cd v3 && BENCH_LLM_BASELINE=1 BENCH_ANTHROPIC=1 \
node ../plugins/ruflo-cost-tracker/scripts/bench.mjs ) # + Sonnet 4.6 + Opus 4.7
Inspect the markdown summary printed to stdout. The gate metric is winRate (Tier 1 cases). Adversarial cases are tracked separately as escalationRate.
Persisted output lands at:
docs/benchmarks/runs/latest.json — pointer to the most recent rundocs/benchmarks/runs/<ISO-timestamp>.json — historical recordRead it back in subsequent skills (e.g. cost-report step 2 reads latest.json for live tier-spend numbers).
winRate ≥ 0.80 on Tier 1 cases (smoke step 23). Lower the threshold by editing scripts/smoke.sh.escalationRate is reported but ungated — adversarial cases are diagnostic.| Env var | Default | Purpose |
|---|---|---|
BENCH_LLM_BASELINE | unset | =1 runs the OpenAI-compat baseline |
BENCH_LLM_MODEL | models/gemini-2.0-flash | Override the OpenAI-compat model |
BENCH_LLM_BASE_URL | Gemini OpenAI shim | Override endpoint |
BENCH_ANTHROPIC | unset | =1 runs Anthropic baseline (Sonnet 4.6 + Opus 4.7) |
BENCH_ANTHROPIC_MODELS | claude-sonnet-4-6,claude-opus-4-7 | Comma-separated Claude IDs |
BENCH_OUT | timestamped file | Override output path |
BENCH_QUIET=1 | unset | Suppress markdown summary |
API keys auto-pulled from gcloud secrets (GOOGLE_AI_API_KEY, ANTHROPIC_API_KEY); override with BENCH_LLM_API_KEY / BENCH_ANTHROPIC_API_KEY.
ADR-0002 §"Decision 1" / §"Riskiest assumption" · cost-booster-edit/SKILL.md (verification table consumes this skill's output) · cost-report/SKILL.md step 2 (reads runs/latest.json).