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.
npx agentmods add skills/rainflashpoint/capital-agent-skills/cap-implementnpx skills add RainFlashPoint/capital-agent-skills --skill cap-implementgit clone --depth 1 https://github.com/RainFlashPoint/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-implement)<a href="https://agentmods.dev/skills/rainflashpoint/capital-agent-skills/cap-implement"><img src="https://agentmods.dev/badge/skills/rainflashpoint/capital-agent-skills/cap-implement.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 | $0.00254 | $0.08087 |
| Opus 5 | $0.00127 | $0.04043 |
| Sonnet 5 | $0.00051 | $0.01617 |
| Haiku 4.5 | $0.00025 | $0.00809 |
Grade A, and why
cap-implement 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 today.
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 — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cap-implement — 先测后码(Test-first red → Implement green)
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。
你是研发主线的实现工。职责:把 plan.md 里已批准的任务,一个一个用 TDD 落成可工作、被测试覆盖的
代码;其间任何 bug 都走系统化调试子循环。核心心法两条铁律:
铁律 1(TDD): 没有先失败的测试,就不写生产代码。
铁律 2(调试): 没有根因,就不写修复。
知识与状态全在纯文件,引擎 = 一个能 Read/Edit/Bash/Grep 的模型。可移植:Claude / Codex 都能跑(§0)。 单写者原则:本阶段不直接写
STATE.md;进度由 cap-flow 在阶段结束时写回(见 §7 交接)。
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、roles/<role>.md、collaboration-discipline.md、receiving-feedback.md、divergence-frames.md、runtime-adapters/codex.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,别当相对本目录去 Read。
继承编排器的两条降级范式,本阶段照用:
0.1 交互降级 —— 纯文本编号选项
凡需向用户提问(确认分叉、确认 blast-radius、3-strike 升级),优先用纯文本编号列表,不硬依赖富交互控件:
我需要你选一个:
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。STOP 点就是 STOP:停下等用户,不要自作 主张续跑。
0.2 执行模型 —— wave 并行 / 串行 inline
源码协作纪律(本阶段部分):提交守 Conventional Commits;波内并行执行守 plan 的「同 wave 不碰同一 文件」。分支模型 / worktree 决策 / 并行前置合约 / 收敛安全网由 cap-flow 跨阶段加载,见
cap-flow/references/collaboration-discipline.md。
先分清两个层次:
- 任务内(一个任务的 TDD):永远串行,一个写手——red→green 是连贯推理,且不得两个写手同改一处。
- 任务间:可并行,且"哪些能并行"已由
plan.md的 wave / depends_on 算好。关键保证:plan 的硬 规则「同 wave 不碰同一文件」使得同一 wave 内并行写代码是构造上安全的。
逐 wave 执行,每个 wave 二选一(探测决定):
进入 wave N(plan 已保证 wave 内无文件冲突):
├─ 先做 write-set preflight:从 plan.md 读取本 wave 各 phase/task 的 files 集合
│ 若任意两个 phase 的 files 有交集 → 不 fan-out;降级串行或回 cap-plan 修 wave
├─ 有并行能力 且 本 wave ≥2 个独立**阶段(phase)**
│ → fan-out:**一阶段一分支**,各自跑完该阶段的所有任务(每任务完整 TDD)、各写各自文件、各写各自笔记
│ 主流程收集结果 → 合并 → **单写 STATE**
└─ 无并行能力 或 本 wave 仅 1 个阶段
→ 串行 inline 逐阶段→逐任务(无子代理、单会话)
> 粒度:**并行单元 = 阶段(phase)**(plan 在 phase 上标 wave / depends_on)。一个阶段内的多个任务通常有 TDD
依赖(测试→实现),**阶段内仍串行**;并行发生在**同 wave 的不同阶段之间**。
↓
wave 屏障:本 wave 全部 green + 出口门过,才进 wave N+1(后波依赖前波产物)
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.
- today Changed · +2 lines b521dc6340cf
- 4d ago First seen · 468 lines · 254 tokens per session scan A 7c6a76fd72a3
cap-implement is a skill published in the GitHub repository RainFlashPoint/capital-agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 254 tokens to every session and 8,087 once invoked, about $0.0013 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…