Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add RainFlashPoint/capital-agent-skills/plugin install capital-agent-skillsWrote 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/rainflashpoint/capital-agent-skills/cap-define)<a href="https://agentmods.dev/skills/rainflashpoint/capital-agent-skills/cap-define"><img src="https://agentmods.dev/badge/skills/rainflashpoint/capital-agent-skills/cap-define.svg" alt="Measured on agentmods" 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 | $0.00208 | $0.08454 |
| Opus 5 | $0.00104 | $0.04227 |
| Sonnet 5 | $0.00042 | $0.01691 |
| Haiku 4.5 | $0.00021 | $0.00845 |
Grade A, and why
cap-define 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 2d 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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cap-define — 收敛阶段:模糊点子 → 获批规格
入口先执行
../cap/SKILL.md的“研发上下文门禁”:.cap检查不可跳过,知识库注入失败可记录后离线继续。
全程契约:开始实质工作前读取并执行
../cap-flow/references/progress-protocol.md与../cap-flow/references/task-reconnaissance.md。先播报当前动作和下一步;新任务没有新鲜.cap/task-context.md时,先调查当前仓库代码,不能只依赖 PROFILE。
把"想做点什么"变成一份获批的、无歧义、能被 cap-plan 直接吃进去的规格。
铁律(HARD-GATE):spec 拿到用户批准之前,不写任何实现代码、不搭脚手架、不调任何实现类阶段。 需求看起来越简单越危险——"简单"往往是没被检视的假设,返工最多都出在这。规格可以很短(简单需求几句话), 但必须呈现并获批。
本阶段是 cap-flow 派来的收敛器:知识与状态都是纯文件,引擎 = 一个能 Read/Edit/Bash/Grep 的模型。 唯一的终态 = 产出获批
spec.md+ 把交接写回 STATE,由 cap-flow 路由到cap-plan。
0. 可移植前置(每次入口先做)
共享 references 的位置:本文引用的
role-routing.md、divergence-frames.md、roles/<role>.md、web-review/playbook.md物理上都在编排器目录cap-flow/references/下,不在本阶段目录里。解析路径一律 指向cap-flow/references/...(相对 skills 根)或经软链接定位,别当相对本目录读。
本阶段要在 Claude 和 Codex 上都能跑。两条降级范式贯穿始终:
0.1 交互降级 —— 纯文本编号选项(默认)
凡向用户提问(澄清、选方案、确认范围、过门),默认用纯文本编号列表,不硬依赖任何富交互控件:
需要你定一个点:
1) 选项 A —— 说明 / 取舍
2) 选项 B —— 说明 / 取舍
3) 其它(你来描述)
回个编号即可(或直接补充文字)。
宿主有结构化提问控件可以用,但回退路径永远是上面这种编号文本。若用户选"其它"又没填内容 → 输出一行 "你想补充什么?" 然后停下等,别重问、别自答。
0.2 并行降级 —— 能并行就并行,不能就串行
本阶段的外部研究(§3 可选)若要多源调研:探测宿主有无并行能力——有 → fan-out 子调研,各写各的临时
笔记;无 → 串行 inline 跑同一份 playbook。任何时候不得两个写手同写 STATE.md / spec.md(单写者)。
1. 入口条件
进入本阶段应满足(cap-flow 保证;独立调用时自检):
| 条件 | 要确认的事 |
|---|---|
有 <target-repo>/.cap/PROFILE.md,或确认是 greenfield |
有 PROFILE 即可;brownfield 缺 PROFILE 应先 cap-understand |
STATE.stage 为 shape,或这是一个全新特性的开始 |
读 .cap/STATE.md;无 STATE = 新特性,本阶段初始化一份 |
| 手头有一个待澄清的"点子 / 需求 / 变更意图" | 来自用户原话 |
入口动作:先看一眼 <target-repo>/.cap/ 有没有 PROFILE / STATE / 既有 spec,再:
- 读
PROFILE.md→ 拿技术栈、约定、surface-map(模块 / glob / 默认角色 / 验证项),当 Explore 的地图。 - 读
STATE.md(若有)→ 看Decisions log里有没有相关旧决策,别重复问已定的事。
1.0 入口先做:改动面 → 角色 + 验证项 预解析
即便本阶段还没真动代码,也要先定本特性"打算动哪块 surface",因为它决定:
- 要不要在 spec 里前置 eval 契约(动 AI / 模型 / 策略 → 必须,见 §5);
- 后续 build / verify / review 会装哪些角色卡、跑哪些验证项。
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.
- 2d ago Changed · +2 lines 27d1c082d63c
- 5d ago First seen · 462 lines · 208 tokens per session scan A 192bb303aff9
cap-define is a skill published in the GitHub repository RainFlashPoint/capital-agent-skills (2 stars, last pushed yesterday), licensed MIT. It adds 208 tokens to every session and 8,454 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…