메뉴
Use this skill when choosing, upgrading, or comparing models for a harness lane. Runs the same task set across candidate model profiles and reports pass rate, latency, token cost, intervention count, and failure class movement before changing defaults.
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
Build a lightweight skill index and load full skill instructions only on demand to reduce startup context pressure.
Select and run a multi-agent workflow pattern for work that exceeds one agent's reliable scope. Use for parallel research, independent reviews, cross-domain changes, or high-risk implementation planning.
Select and run a multi-agent workflow pattern for work that exceeds one agent's reliable scope. Use for parallel research, independent reviews, cross-domain changes, or high-risk implementation planning.
Use composable middleware behaviors for provider/tool execution: retry, caching, timeout, telemetry, and budget guards.
Use this skill whenever the agent makes a mistake, the user observes an avoidable failure, a pattern recurs, or someone says "the agent keeps doing X". Files an "Engineer the Harness" entry — Mitchell Hashimoto's discipline: every failure becomes a permanent prevention mechanism. Always invoke this instead of just fixing the immediate symptom.
Use composable middleware behaviors for provider/tool execution: retry, caching, timeout, telemetry, and budget guards.
| name | model-profile |
| description | Use this skill when choosing, upgrading, or comparing models for a harness lane. Runs the same task set across candidate model profiles and reports pass rate, latency, token cost, intervention count, and failure class movement before changing defaults. |
| allowed-tools | Read, Write, Bash(node .harness/scripts/model-routing-report.mjs:*), Bash(node .harness/scripts/bench-runner.mjs:*), Bash(node .harness/scripts/bench-compare.mjs:*), Bash(node .harness/scripts/regression-runner.mjs:*), Bash(node .harness/scripts/regression-compare.mjs:*) |
.harness/scripts/model-routing-report.mjs --json to inspect current
lane/model attribution and identify overpowered or underpowered calls.### Model profile
**Lane:** <lane>
**Baseline:** <model/profile>
**Candidate:** <model/profile>
**Decision:** keep baseline | switch candidate | rerun with broader set
**Evidence:** pass rate, cost, latency, interventions
**Scope:** <where this recommendation applies>