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/jerrylalala/compound-engineering/workflows-brainstormnpx skills add Jerrylalala/compound-engineering --skill workflows-brainstormgit clone --depth 1 https://github.com/Jerrylalala/compound-engineeringWrote 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/jerrylalala/compound-engineering/workflows-brainstorm)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/workflows-brainstorm"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/workflows-brainstorm.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 | $0.00032 | $0.02842 |
| Opus 5 | $0.00016 | $0.01421 |
| Sonnet 5 | $0.00006 | $0.00568 |
| Haiku 4.5 | $0.00003 | $0.00284 |
Grade A, and why
workflows-brainstorm 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
workflows-brainstorm
用于在实现前澄清做什么,而不是直接进入编码。
这是 Codex 中的 brainstorm 主入口。它不尝试复刻 Claude Code 的完整运行时,而是用明确状态机保留高价值能力:
[P]触发 3 个核心视角的多轮讨论,并模拟party-mode的 emoji + 角色名 + 相互质疑体验[P+]触发 8-12 个视角的深度发散和挑战收敛[R]强制历史经验检索;未传[R]时,Standard/Deep 场景自动做历史检索- 每轮都纳入胶水编程:复用机会、胶水代码边界、必须自研的部分
- 每轮后等待用户选择继续、换视角或收敛
- 写出带 P1-P4 优先级和 Reuse / Build Boundary 的 brainstorm 文档
不要调用 Codex CLI。 不要调用 Gemini CLI。
目标
通过协作对话、轻量仓库研究、历史经验检索和方案比较,产出一份可继续规划的 brainstorm 文档:
docs/brainstorms/YYYY-MM-DD-<topic>-brainstorm.md
输入
- 功能想法
- 问题描述
- 改进方向
- 可选参数:
[P]:3 个核心视角,适合普通复杂度[P+]:8-12 个视角,适合模糊、高风险或架构性问题[R]:强制检索docs/solutions/历史经验
如果用户没有给出清晰主题,先追问,不要直接写文档。
如果用户传入旧的外部 AI 咨询标记,只说明本 Codex brainstorm 入口不处理外部 AI 咨询,清洗掉该标记后继续主流程。
参数解析
开始时先解析参数,并向用户回显:
PARTY_MODE = none|quick|deepHISTORICAL_RESEARCH = auto|force|skip- 清洗后的功能描述
规则:
- 包含
[P+]->PARTY_MODE = deep - 包含
[P]->PARTY_MODE = quick - 包含
[R]->HISTORICAL_RESEARCH = force - 未包含
[R]时,先按 Phase 0 判断范围;Standard/Deep 软件或仓库改动场景使用HISTORICAL_RESEARCH = auto - Lightweight 且无历史相关信号时可设为
skip - 解析后从功能描述中移除所有参数标记
- 如果检测到用户把一长段对话历史、系统标签或工具输出粘进参数里,要先让用户重新给出一句简洁描述
Phase 0: 范围判断
先判断是否真的需要 brainstorm:
- Lightweight:目标清楚、范围小、低风险;可以短讨论后直接写简短文档或建议进入
$workflows-plan - Standard:正常功能、流程、体验或工具改进;需要完整覆盖矩阵
- Deep:跨模块、架构、工作流、运行时适配、高风险或需求模糊;建议自动提升到
[P+]级别,即使用户只传[P]
如果需求已经非常清晰,不要硬拖长讨论;但仍要确认是否需要持久化 brainstorm 文档。
Phase 1: 本地上下文与历史检索
1.1 仓库上下文
先做轻量研究,了解:
- 是否已有相近实现
- 项目里是否已有类似模式
- 是否有现成约束或历史决策
- 本次改动可能影响哪些文档协议或工作流入口
如果 $repo-research-analyst 可用,优先使用它。
如果不可用,直接用本地搜索完成同等最小研究:rg 查主题关键词、相关 skill、相关 docs、相关 tests。
1.2 历史经验检索
[R] 的含义是:强制查历史经验。它不是联网搜索,也不是外部 AI 咨询。
历史检索来源:
docs/solutions/docs/brainstorms/docs/plans/
执行规则:
HISTORICAL_RESEARCH = force:必须检索HISTORICAL_RESEARCH = auto:Standard/Deep 场景自动检索HISTORICAL_RESEARCH = skip:只在 Lightweight 或明显无历史价值时跳过
如果 $learnings-researcher 可用,自动运行 $learnings-researcher。
如果不可用,用 rg 搜索 docs/solutions/ 和相关文档,提炼 3-5 条历史约束、坑点或可复用经验。
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 First seen · 288 lines · 32 tokens per session scan A a90d0b799729
workflows-brainstorm is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 2,842 once invoked, about $0.0002 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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…