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 portfoliogit 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/portfolio)<a href="https://agentmods.dev/skills/kimsanguine/hplan/portfolio"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/portfolio/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/portfolio"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/portfolio.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 | $0.00079 | $0.03047 |
| Opus 5 | $0.00039 | $0.01523 |
| Sonnet 5 | $0.00016 | $0.00609 |
| Haiku 4.5 | $0.00008 | $0.00305 |
Grade A, and why
portfolio 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 9d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portfolio
에이전트 포트폴리오 관리 — T1~T5 티어링, 5축 스코어카드 비교, 주간 롤업 브리프
Core Goal
- N개 에이전트를 사업 임팩트·신뢰성·운영 비용 기준으로 T1~T5 5단계 티어링한다.
- 티어 × 인시던트 가중치로 운영 주의력을 분배해 "어디부터 손볼지" 결정한다.
- 5축 가중 루브릭으로 에이전트 간 단일 비교 점수 생성 — 투자·일몰 의사결정을 객관 데이터로 지원.
- 포트폴리오 헬스를 한 화면에서 — 총 N개, 활성 비율, T1 우선순위 리스트.
Trigger Gate
Use This Skill When
- 단일 에이전트의 현재 상태 카드가 필요할 때 (
--mode single) - 포트폴리오 전체 5축 스코어카드 또는 주간 롤업이 필요할 때 (
--mode report) - 포트폴리오 전반의 헬스 스코어와 운영 주의력 분배가 필요할 때 (
--mode health) - 운영 중인 에이전트가 5개를 넘어서 단일 에이전트 KPI 뷰로는 우선순위가 안 보일 때
- 분기/월간 포트폴리오 리뷰 미팅 준비할 때
- 예산 삭감 요구가 와서 어떤 에이전트를 sunset 할지 결정할 때
Route to Other Skills When
- 개별 에이전트 KPI 정의가 우선이면 →
metrics-design - 신뢰도 SLO 설계는 →
reliability - 비용 단독 분석이 우선일 때 →
ops-review --mode cost - 이상치 에이전트에 대한 깊은 장애 분석이 필요할 때 →
incident
Boundary Checks
- 이 스킬은 포트폴리오 메타 뷰이지 개별 에이전트 진단이 아니다.
- 에이전트 수 < 5면 과중 —
metrics-design으로 충분하다. - 티어링은 사업 영향을 기준으로 한다. "내가 좋아하는 에이전트"가 아니다.
- Scorecard 가중치 기본값은 3분 결정 한정. 본격 운영은 가중치 명시 필요.
개념
Tier 정의 (T1~T5)
| 티어 | 정의 | 운영 주의력 | 예시 |
|---|---|---|---|
| T1 | 사업 핵심·실시간·고객 직접 노출 | 24/7 모니터, 인시던트 즉시 대응 | 결제 라우터, 고객 응대 1차 |
| T2 | 사업 중요·매일 실행·내부 의존 | 매일 헬스체크, 4시간 SLA | 데일리 브리핑, 비용 모니터 |
| T3 | 운영 효율·주기적·내부용 | 주 1회 리뷰 | 주간 회고, 콘텐츠 큐레이션 |
| T4 | 실험·신규·검증 단계 | 격주 리뷰 + 자체 평가 | 신규 카피라이팅 에이전트 |
| T5 | 레거시·sunset 후보 | 월 1회 점검, 삭제 후보군 | 사용 빈도 < 월 1회 |
5축 스코어카드
| 축 | 정의 | 기본 가중치 |
|---|---|---|
| Accuracy | 출력이 사양을 충족하는가 (LLM-as-judge / 사람 평가 0~100) | 25 |
| Reliability | 실행 성공률 × P95 latency 충족률 | 25 |
| Cost | (목표 CPE / 실측 CPE) × 100, 상한 100 | 20 |
| Velocity | 정규화 호출 수 × TTV 충족률 | 15 |
| User Satisfaction | NPS/CSAT 정규화 점수 (0~100) | 15 |
합계 100. 사업 컨텍스트에 맞게 재배분 가능.
Instructions
You are managing the portfolio for: $ARGUMENTS
Parse --mode from the arguments:
--mode single→ Run Single Agent Status Card only--mode report→ Run Portfolio Report (Scorecard or Rollup)--mode health→ Run Portfolio Health + Tier distribution- no
--modeflag → Default to--mode health
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.
- 9d ago First seen · 276 lines · 79 tokens per session scan A 466026073658
portfolio is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 23d ago), licensed MIT. It adds 79 tokens to every session and 3,047 once invoked, about $0.0004 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…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…
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.