菜单
Cloud + LLM spend audit, right-sizing, unit economics. Use before scaling decisions, after bill shock, or when cost per user/request is unknown. RULE: every recommendation quantified in $/month — never "cheaper". NOT for performance — use /perf.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/bpmforge/attest-claude --skill cost-engineer命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Gauntlet loop — multi-agent quality harness: a lead sets a real reference bar (a named product, test suite, or baseline to match or beat), splits the goal into gradeable units, builders produce artifacts in clean context, and blind fresh-per-round critics grade each artifact against the bar with evidence; failures loop until every unit passes, two rounds stall, or budget runs out. NOT /challenge (verifies factual claims); NOT /review (one-pass verdict) — this rebuilds until the work beats something real.
Claude-Design-style visual iteration loop — render the running UI, screenshot at 375/768/1440, critique against docs/design/tokens.json and design principles, apply fixes, re-capture until clean (cap 3 iterations). Also extracts a token baseline from an existing codebase (--sync) and audits real logged-in browsers (--real). NOT a one-pass review — use /ux --review for findings-only; NOT functional conformance — use /ui-verify.
Project intelligence steward — audits CLAUDE.md / AGENTS.md alignment with actual codebase, captures session learnings, updates project docs. Use after major sessions or when docs feel stale.
基于 SOC 职业分类
正在显示 SKILL.md
| name | Cost Engineer |
| trigger | /cost |
| description | Cloud + LLM spend audit, right-sizing, unit economics. Use before scaling decisions, after bill shock, or when cost per user/request is unknown. RULE: every recommendation quantified in $/month — never "cheaper". NOT for performance — use /perf. |
| agent | cost-engineer |
| arguments | [{"name":"--audit","description":"Full spend review","required":false},{"name":"--rightsize","description":"Compute right-sizing from observed p95 utilization","required":false},{"name":"--unit","description":"Unit-economics model (cost per user/request/job)","required":false}] |
Triggers the cost-engineer subagent.
Cloud and LLM spend analysis — audit, right-size, unit economics. Use before scaling decisions or after bill shock. Every recommendation quantified in dollars per month.
Usage: /cost (--audit default), /cost --rightsize, /cost --unit.