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 skills add Jerrylalala/compound-engineering --skill ce-ideasgit 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/ce-ideas)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/ce-ideas"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/ce-ideas.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 | $0.00028 | $0.01413 |
| Opus 5 | $0.00014 | $0.00707 |
| Sonnet 5 | $0.00006 | $0.00283 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
ce:ideas scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideas 管理命令
Note: The current year is 2026. Use this when dating new entries added to IDEAS.md.
ce:ideas 是想法停车场的统一入口:
- 无参数:展示 IDEAS.md,推荐优先方向,引导进入 brainstorm
- 有参数:针对该方向生成新改进建议(原 ideate 行为),结束时询问是否存入 IDEAS.md
IDEAS.md 路径:IDEAS.md(项目根目录)
Interaction Method
使用平台的阻塞问答工具(Claude Code 中为 AskUserQuestion)。每次只问一个问题,优先使用单选。
Focus Argument
<focus_argument> #$ARGUMENTS </focus_argument>
Execution Flow
Phase 0: 路由检测
检测 $ARGUMENTS 是否有实质内容(去除空格后为空 = 无参数):
- 无参数 → 进入 Phase 1A(停车场路径)
- 有参数 → 进入 Phase 1B(生成路径)
Phase 1A: 停车场路径(无参数)
目标:展示 IDEAS.md,帮用户从已有想法中选一个方向。
1A.1 读取 IDEAS.md
读取项目根目录的 IDEAS.md。
- 若文件不存在 → 提示「IDEAS.md 还没有内容,帮你生成第一批想法」→ 跳转 Phase 1B(无 focus_argument,open-ended)
- 若文件存在但无未完成条目(
- [ ]= 0)→ 提示「IDEAS.md 的所有想法都已完成,帮你生成新方向」→ 跳转 Phase 1B
1A.2 展示并推荐
展示所有未完成条目(- [ ]),格式:
IDEAS.md 中有 N 个待执行方向:
1. **[想法标题]** — [简短描述]
来源:[来源链接]
2. **[想法标题]** — [简短描述]
来源:[来源链接]
...
推荐优先探索(前 2-3 个):
⭐ [序号]. [理由,1 句话]
⭐ [序号]. [理由,1 句话]
推荐排序逻辑(简单启发式):
- 来源文件近期(近 30 天)且仍存在 → 优先级高
- 来源文件明确标记
active→ 优先级高 - 其余按出现顺序
1A.3 AskUserQuestion
使用 AskUserQuestion 询问:
「IDEAS.md 中有 [N] 个待执行方向。你想怎么做?」
选项:
- 选择一个方向(输入序号或名称)→ 进入 Phase 2(handoff),以选中方向为目标
- 生成新想法 → 跳转 Phase 1B
- 退出
Phase 1B: 生成路径(有参数,或从 1A 跳转)
目标:针对给定方向生成新改进建议,参考 ce-ideate 的生成逻辑。
1B.1 准备 focus
- 若从 Phase 1A 跳转(原本无参数)→ 用
AskUserQuestion询问:「你想探索哪个方向?描述一下」 - 若有原始 focus_argument → 直接使用
1B.2 快速仓库扫描
派发一个 haiku model 子代理(快速扫描,省 token):
读取项目的 AGENTS.md 或 CLAUDE.md,再扫描顶层目录结构(Glob pattern
*和*/*)。返回不超过 20 行的简报:项目形态(语言/框架/目录布局)、明显痛点和杠杆点。 Focus: {focus}
1B.3 生成候选方向
基于扫描结果,针对 focus 生成 5-8 个有根据的改进方向候选,每个包含:
- 标题(简短)
- 1-2 句描述(说清楚做什么、为什么有价值)
- 关键风险或依赖
1B.4 批判过滤
对候选列表批判筛选:
- 去除重复现有功能的
- 去除与已有 IDEAS.md 条目高度重叠的(读取 IDEAS.md 对比)
- 去除当前阶段不现实的(依赖缺失、工作量极大且收益低)
保留 3-5 个最有价值的,按「价值 / 实现成本」排序输出。
1B.5 展示结果
针对「[focus]」的改进方向建议:
🥇 [标题]
[描述]
风险:[简要]
🥈 [标题]
[描述]
风险:[简要]
...
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.
- 6d ago First seen · 167 lines · 28 tokens per session scan A 5bdacff29149
ce:ideas is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 1,413 once invoked, about $0.0001 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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…