Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/RainFlashPoint/capital-agent-skillsnpx agentmods add skills/rainflashpoint/capital-agent-skills/cap-planWrote 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-plan)<a href="https://agentmods.dev/skills/rainflashpoint/capital-agent-skills/cap-plan"><img src="https://agentmods.dev/badge/skills/rainflashpoint/capital-agent-skills/cap-plan.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 | $0.00224 | $0.07768 |
| Opus 5 | $0.00112 | $0.03884 |
| Sonnet 5 | $0.00045 | $0.01554 |
| Haiku 4.5 | $0.00022 | $0.00777 |
Grade A, and why
cap-plan 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 4d 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 — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cap-plan — 把已批准的 spec 拆成可执行的 plan.md
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。
你的唯一职责:读已批准的 spec.md,产出一份 <target-repo>/.cap/plan.md,把需求两级贯通:
spec(已批准) → 阶段 phase(含 depends_on + wave 波次) → 任务 task(含三必填字段)
产物必须满足两条铁律(贯穿全文):
- No-Placeholder(无占位红线):任何任务的
action必须含真实可执行内容(具体文件路径、具体值、 具体命令),不许出现 "TBD / 待定 / 实现细节后补 / 加适当的错误处理 / v1 先这样"。 - 100% Traceability(全覆盖追溯):spec 里每一条需求 / 决策都能指到至少一个任务;反向每个任务都能指回 它实现的需求。靠 Source Audit + Coverage Gate 双向核验(§6)。
引擎 = 一个能 Read/Edit/Bash/Grep 的模型。 不依赖任何后台服务 / 子代理运行时 / 特定目录约定 / 富交互 控件。所有交互用纯文本编号列表,所有产物落纯文件。
0. 入口条件(先验,未满足就停)
进入本阶段前确认:
<target-repo>/.cap/spec.md存在。- spec 已获批(
cap-define的出口门控已过;STATE 里 spec 状态为 approved)。
硬前置:没有获批的 spec 就拆 plan,等于在没对齐的设计上排兵布阵。两条都满足才往下走。
-
无 spec.md → 停。用编号文本提示用户先走
cap-define:没找到 .cap/spec.md。规划需要一份已批准的 spec 作输入。 1) 现在去跑 cap-define 产出并批准 spec(推荐) 2) 我手动指给你一个已有的 spec 文件路径 回个编号。 -
spec 存在但未确认获批 → 不静默继续。用编号文本让用户确认:
找到 spec.md,但 STATE 里没看到"已获批"标记。规划会把 spec 当作锁定决策来拆。 1) spec 已经批了,继续规划 2) 还没批,我先回 cap-define 走批准门控 回个编号。
本阶段不做需求讨论 / questioning。 那是
cap-define的事。这里把 spec 当作锁定的输入。若发现 spec 有歧义 / 缺口,不是自己拍板补——而是记进 STATE 的 Decisions log 并按 §6 的 MISSING 流程上报,让用户 决定(加任务 / 拆阶段 / 显式 defer)。
1. 可移植前置(每次入口一次性)
共享 references 的位置:本文引用的
role-routing.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。
与编排器同源的两条降级范式:
1.1 交互降级 —— 纯文本编号选项
凡需用户确认(复杂度分级、MISSING 项处置、最终 plan 确认),优先纯文本编号列表:
需要你定一个:
1) 选项 A —— 说明
2) 选项 B —— 说明
回个编号即可。
宿主有结构化提问控件可用,但回退路径必须是上面这种编号文本。默认按编号文本写。
1.2 并行降级 —— 能并行就并行,不能就串行
规划本身通常单会话串行即可(拆任务是连贯推理,不强求并行)。若 spec 覆盖多个独立子系统且环境有
并行能力,可一子系统一分支并行起草分计划;无并行能力 → 串行逐子系统拆。不论哪种,最终合并成一份
plan.md,且单写者写 plan.md / STATE.md(不并发写同一文件)。
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.
- 4d ago Changed · +2 lines f60267b451f5
- 8d ago First seen · 470 lines · 224 tokens per session scan A 48d8161cf11d
cap-plan is a skill published in the GitHub repository RainFlashPoint/capital-agent-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 224 tokens to every session and 7,768 once invoked, about $0.0011 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…