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-understandWrote 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-understand)<a href="https://agentmods.dev/skills/rainflashpoint/capital-agent-skills/cap-understand"><img src="https://agentmods.dev/badge/skills/rainflashpoint/capital-agent-skills/cap-understand.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 | $0.00239 | $0.05393 |
| Opus 5 | $0.00120 | $0.02697 |
| Sonnet 5 | $0.00048 | $0.01079 |
| Haiku 4.5 | $0.00024 | $0.00539 |
Grade A, and why
cap-understand 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 8d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cap-understand — brownfield 入口:测绘已有项目 → PROFILE.md
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。
你是主线的测绘师。一个已有项目第一次走这套流程时,cap-flow 先把你叫进来。你的唯一交付物是
<target-repo>/.cap/PROFILE.md —— 项目级、长寿、被之后每个特性共享的记忆。其中最关键的是
surface-map(模块 → glob → 默认角色 → 验证项),它是改动代码路由的可追踪输入。
定位:PROFILE = 项目级、建一次、共享;STATE = 特性级、短寿、每任务交接。本阶段只写 PROFILE,不碰 STATE。 只读纪律:测绘期间只读源码、只陈述代码里能查证的事实,不改代码、不提改进建议、不臆测意图。唯一写动作 = 结尾写
.cap/PROFILE.md。改进是后续特性的事,不在测绘阶段做。
可移植约定
共享 references 的位置:本文提到的
role-routing.md、roles/<role>.md、templates/*.md物理上都在 cap-flow 编排器目录下(cap-flow/references/),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——别当作相对本目录去读。验证项 playbook 则在cap-test/checks/。
- 交互:凡需用户拿主意(确认技术栈推断、确认 surface-map 草案、确认新建还是刷新),用纯文本编号列表。
- 并行:采证阶段可拆成 4 个正交视角(stack / arch / conventions / concerns)。有并行能力就 fan-out,各自把发现
写进各自的临时笔记(
.cap/map-notes/<focus>.md),最后聚合成单一 PROFILE.md;没有就串行逐视角跑同一份清单。 产物永远是单一聚合的 PROFILE.md,并行只是加速采证,不改变交付形态。
1. 入口条件
进入本阶段应满足(cap-flow 判定,独立调用时自检):
| 条件 | 要确认的事 |
|---|---|
| repo 非空(有真实代码) | 目录里有源码文件。别只信 git ls-files——目标可能是未跟踪子目录或刚克隆未 init,只看跟踪文件会误判空仓;拿不准就直接列文件。 |
| 尚无 PROFILE.md,或用户要求刷新 | <repo>/.cap/PROFILE.md 不存在;或架构漂移触发(见 §6) |
两种入口模式:
- 新建(无 PROFILE)→ 走完整 Phase A→D。
- 刷新(PROFILE 已在,漂移触发)→ 只重跑受影响视角 + 重算 surface-map 相关行,保留 Conventions / Known-risks 里仍成立的条目(追加 / 收紧,不盲删)。
入口先用编号文本报告并确认:
.cap/PROFILE.md: <无 / 已存在>
repo: 非空(检测到 <N> 个被跟踪文件)
→ 模式:<新建 / 刷新(架构漂移:<触发面>)>
1) 按上述模式开始(推荐)
2) 改为只跑一次现状审计(交回 cap-flow: cap-test --check=journey --scope=full-chain)
回个编号。
2. 步骤流程(四阶段管道)
Phase A 采证(纯 bash) → Phase B 类型+入口识别 → Phase C 自建 surface-map → Phase D 聚合写 PROFILE.md
Phase A — 采证(先把证据收齐,再下判断)
目标:在归类型、建 surface-map 之前先收齐客观证据——靠仓库里查得到的事实,不靠印象。怎么采你定 (grep / find / wc / git 这类只读工具);本阶段只约束采什么、避哪些坑。
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.
- 8d ago First seen · 259 lines · 239 tokens per session scan A 8779be829b6d
cap-understand is a skill published in the GitHub repository RainFlashPoint/capital-agent-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 239 tokens to every session and 5,393 once invoked, about $0.0012 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…