ops-review

ops-review is a skill for Claude Code from kimsanguine/hplan. It costs 141 tokens per session (5,253 once invoked), scanned A, original, MIT.

A skill for weekly or monthly operational reviews of AI agents, covering token spending, weekly metrics, cost comparisons, anomalies, budgets, and stakeholder updates.

In plain words
What is it for?
Use it for cost tracking, weekly roll-ups, full reviews, executive summaries, team updates, partner briefs, and exports formatted for an internal wiki such as Confluence.
Why use it?
It turns scattered operating data into regular reports and highlights cost changes or budget risks that need attention.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; positional $N argument.

Part of the operate plugin — 6 skills shipped together

Good fit Use it for cost tracking, weekly roll-ups, full reviews, executive summaries, team updates, partner briefs, and exports formatted for an internal wiki such as Confluence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kimsanguine/hplan/ops-review
Install

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.

Any agent
npx skills add kimsanguine/hplan --skill ops-review
Clone the repo
git clone --depth 1 https://github.com/kimsanguine/hplan

Made for: Claude Code.

Or install operate, the plugin that ships this one along with the rest of its 6 skills.

Wrote 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.

agentmods badge for ops-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimsanguine/hplan/ops-review/github.svg)](https://agentmods.dev/skills/kimsanguine/hplan/ops-review)
Your own site
<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.

agentmods 80×15 button for ops-review

Your own site · 80×15
<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>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,253 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash fed586bbfd44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

operate/skills/ops-review/SKILL.md · 482 lines

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 COGS 예측 → cogs-sentinel (hplan plugin). 이 스킬은 배포 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 full or no --mode flag → 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 (--source 필요)

Cost Review (--mode cost or --mode full)

Read the full file on GitHub · 482 lines

Changes

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.

  1. 9d ago First seen · 482 lines · 141 tokens per session scan A fed586bbfd44

Subscribe to this mod's changes

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.

Related

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…

longsizhuo/openInvest · 261 tokens

invest-setup

A first-time setup workflow for openInvest, a system for tracking investments and running portfolio analysis.

longsizhuo/openInvest · 105 tokens

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…

longsizhuo/openInvest · 202 tokens

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.

sd0xdev/sd0x-harness · 49 tokens

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…

stakekit/agentkit · 75 tokens

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…

stakekit/agentkit · 124 tokens