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 ops-reviewgit 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/ops-review)<a href="https://agentmods.dev/skills/kimsanguine/hplan/ops-review"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/ops-review/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/ops-review"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/ops-review.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 | $0.00141 | $0.05253 |
| Opus 5 | $0.00071 | $0.02627 |
| Sonnet 5 | $0.00028 | $0.01051 |
| Haiku 4.5 | $0.00014 | $0.00525 |
Grade A, and why
ops-review 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 — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ops Review
주간/월간 운영 리뷰 — 비용 추적과 주간 지표 롤업 통합
Core Goal
- 에이전트 토큰 비용을 가시화하고 제어 — 선형 증가하는 비용을 데이터 기반으로 최적화하는 기초 구축
- 주간 지표를 단일 롤업으로 압축 — 운영팀이 5분 안에 신호만 받게 함
- 비용-성능 트레이드오프 의식화 — 모델 선택, 프롬프트, 컨텍스트 전략의 경제학적 영향 정량화
- 예산 중심의 운영 틀 수립 — 월간 비용 상한선과 알림 전략으로 재정 예측 가능성 확보
Trigger Gate
Use This Skill When
- 에이전트의 월간 토큰 비용을 추적하거나 최적화해야 할 때 (
--mode cost) - 주간 지표 요약과 운영 신호를 빠르게 확인해야 할 때 (
--mode weekly) - 비용 리뷰 + 주간 롤업을 한 번에 수행해야 할 때 (
--mode full) - 모델 선택(Claude Sonnet vs Haiku vs Opus)이 비용에 미치는 영향을 정량화해야 할 때
- 월간 예산을 초과했거나 초과할 위험이 있을 때
- "진행 상황 임원 보고서 만들어줘" →
--mode exec-summary - "이번 주 팀 업데이트 작성해줘" →
--mode weekly-update - "파트너에게 진행상황 요약 보내야 해" →
--mode partner-brief - "Confluence/사내 위키에 올릴 수 있는 형식으로 변환해줘" →
--mode confluence-export
Route to Other Skills When
- incident → 일일 비용이 갑자기 2배 이상 폭등했을 때 (즉시 긴급 대응)
- metrics-design → 비용 효율(Cost per Execution)을 North Star/KPI에 통합할 때
- portfolio → 비용 데이터를 에이전트 포트폴리오 헬스 스코어로 집계할 때
- sprint --step status → 보고서에 필요한 진행 데이터 수집
- ticket-bridge --mode status → 티켓에 상태 코멘트
- ask-team → 팀원에게 보고서 직접 전달 (ops-review는 산문 생성까지, 발송은 ask-team)
Boundary Checks
- 일반 비용 추적과의 구분 — 서버, 인프라 비용은 별도. 토큰 비용(API 호출 기반)에만 집중
- 최적화 과도 — 품질 저하 없이 비용 절감이 가능한 범위 확인 (Guardrail 지표 확인 필요)
- 배포 전 COGS 예측 →
cogs-sentinel(hplan plugin). 이 스킬은 배포 후 추적.
개념
에이전트 비용의 60-90%는 LLM 토큰 비용이다. 토큰 사용을 가시화하고 최적화하지 않으면 비용이 사용량에 비례해 선형 증가하며, 비즈니스 모델을 파괴할 수 있다.
주간 롤업은 비용 데이터를 포함하여 운영 신호를 5분 안에 소화하는 단일 브리프다.
Instructions
You are running an ops review for: $ARGUMENTS
Parse --mode from the arguments:
--mode cost→ Run Cost Review only--mode weekly→ Run Weekly Rollup only--mode fullor no--modeflag → Run both (default)--mode exec-summary→ 임원 1-pager 보고서 (Stakeholder Updates 섹션)--mode weekly-update→ 팀 주간 업데이트 보고서--mode partner-brief→ 외부 파트너 요약 보고서--mode confluence-export→ 기존 보고서를 Confluence/사내 위키 포맷으로 변환 (--source필요)
Cost Review (--mode cost or --mode full)
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 · 482 lines · 141 tokens per session scan A fed586bbfd44
ops-review is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 23d ago), licensed MIT. It adds 141 tokens to every session and 5,253 once invoked, about $0.0007 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
invest
First-time fork users: run the invest-setup skill first to initialize. The main flow lives in this skill (the AI agent uses the CLI/MCP to view the portfolio / run the committee / replay decision history). The Web GUI has been retired (2026-07) — every capability is exposed via CLI subcommands / MCP tools. The backend…
invest-setup
A first-time setup workflow for openInvest, a system for tracking investments and running portfolio analysis.
invest-backup
Back up / restore openInvest's local state — memory/ (holdings, strategy, user profile, committee records, dream logs) + db/ (trade ledger, job run history, market-data cache) + .env (SMTP/API credentials) + userprofile.json. All of this data is .gitignore'd with no historical versions in git, so a single accidental…
portfolio
Portfolio system knowledge base. Use when: position queries, routing strategy questions, provider integration. Not for: general code exploration (use code-explore), code review (use codex-code-review). Output: domain-specific analysis + recommendations.
yield-xyz-agentkit-builder
Build applications that integrate with the Yield.xyz APIs — staking, lending, vaults, and RWA across 80+ networks. Generates code covering REST API integration, transaction signing, wallet connection, and fee monetization. Use when user wants to build an app, integrate yield, generate code, or set up a project using…
yield-xyz-agentkit-privy
The Privy connector for the Yield.xyz AgentKit — signs and broadcasts via Privy agentic wallets. Extends the yield-xyz-agentkit skill — that skill discovers yields and builds the unsigned transactions; this one adds Privy wallet creation, policy enforcement, signing, and broadcasting, in autonomous and semi-autonomous…