Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kimsanguine/hplan --skill metrics-designgit clone --depth 1 https://github.com/kimsanguine/hplanWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kimsanguine/hplan/metrics-design)<a href="https://agentmods.dev/skills/kimsanguine/hplan/metrics-design"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/metrics-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kimsanguine/hplan/metrics-design"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/metrics-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.04607 |
| Opus 5 | $0.00022 | $0.02303 |
| Sonnet 5 | $0.00009 | $0.00921 |
| Haiku 4.5 | $0.00004 | $0.00461 |
Grade A, and why
metrics-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
metrics-design
AI 에이전트의 메트릭 계층 설계 — North Star 정의 후 KPI 파생
Core Goal
- 단일 North Star 메트릭으로 팀 전략 정렬 — 운영 건강도와 비즈니스 임팩트를 동시에 반영하는 "하나의 숫자" 확립
- North Star를 KPI 대시보드의 최상위에 연결 — Leading/Lagging 지표 계층을 결정론적 공식으로 정의
- 의사결정 우선순위 명확화 — 충돌하는 지표 간 트레이드오프를 North Star 기준으로 일관성 있게 해결
Trigger Gate
Use This Skill When
- "북극성 메트릭 정의해줘" — North Star가 필요한 모든 상황
- "KPI 설정해줘" — 에이전트 성과 지표 체계 구축 시
- "에이전트 성과 측정 기준 잡아줘" — 메트릭 계층 전체가 필요할 때
- 새로운 에이전트 제품 론칭, 기존 KPI 충돌, 분기 OKR 연결 시
Route to Other Skills When
- portfolio --mode report --view scorecard → 정의된 KPI로 상대 비교 점수화
- ops-review --mode cost → North Star에 비용 효율 요소가 포함될 때
- 이 스킬의 코호트 분석 기법 → North Star 추이를 코호트별로 추적할 때 (아래 "관련 기법 — 코호트 분석" 섹션)
- reliability → A/B 테스트의 Primary 메트릭으로 North Star 사용 시
Boundary Checks
- 코드 배포해줘 → deliver 플러그인으로 라우팅
- UI 점검해줘 → deliver/ui-validate로 라우팅
- 메트릭 선택의 주관성 → 5가지 기준(Actionable · Measurable · Understandable · Leading · Composite) 충족 여부 점검
- Anti-metric 설정 → North Star 최적화로 인한 다른 지표 악화를 사전에 차단
개념
North Star Metric은 에이전트의 성공을 하나의 숫자로 표현한다. KPI는 그 숫자를 분해한 운영 건강도(잘 돌아가는가)와 비즈니스 임팩트(가치를 만드는가)의 두 축이다. 두 층을 함께 설계하지 않으면 "정확도만 높고 쓸모없는" 또는 "가치있지만 불안정한" 에이전트가 된다.
Instructions
You are designing metrics for: $ARGUMENTS
Parse --step from the arguments:
--step north-star→ Run Phase A only--step kpi→ Run Phase B only--step okr→ Run Phase C only (OKR 설계)--step allor no--stepflag → Run Phase A then Phase B then Phase C (default)
Phase A — North Star 정의 (--step north-star or --step both)
A1 — North Star Criteria 체크
좋은 North Star Metric은 다음 5가지를 충족해야 한다:
- Actionable: 팀이 직접 영향을 미칠 수 있는가
- Measurable: 자동으로 추적 가능한가
- Understandable: 누구나 설명할 수 있는가
- Leading: 미래 성공을 예측하는가 (과거 기록 아님)
- Composite: 품질과 임팩트를 동시에 반영하는가
A2 — 후보 생성
3~5개 후보를 다음 공식으로 생성한다:
North Star = f(Quality, Volume, Impact)
예시:
- "Successful agent actions per week" (volume × quality)
- "Hours saved per user per month" (impact × adoption)
- "Accurate outputs delivered within SLA" (quality × reliability)
- "Revenue-impacting decisions supported" (impact × quality)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 416 lines · 43 tokens per session scan A 177d9dd50068
metrics-design is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 24d ago), licensed MIT. It adds 43 tokens to every session and 4,607 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
feature-dev
Feature development workflow. Use when: implementing features, writing code, running dev loop. Not for: understanding code (use code-explore), reviewing code (use codex-code-review). Output: implemented feature + tests + review gate.