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/ce-work-integrationnpx skills add Jerrylalala/compound-engineering --skill ce-work-integrationgit 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-work-integration)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/ce-work-integration"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/ce-work-integration.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 | $0.00075 | $0.01462 |
| Opus 5 | $0.00037 | $0.00731 |
| Sonnet 5 | $0.00015 | $0.00292 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
ce-work-integration 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 5d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ce:work 集成 Overlay — Task Bundle + FSM
基础层:上游
ce:work负责任务执行、质量检查、提交工作流。本 Overlay 增量:Task Bundle 持久化(state.md 读写)+ Failure FSM 状态转换。
何时使用本 Overlay
当满足以下条件时,在运行 ce:work 前/后应用本 overlay:
- 任务有对应的 Task Bundle:
docs/tasks/<task-id>/目录存在 - 或者任务预期超过 1 小时(值得持久化上下文)
- 或者任务涉及多个子代理
Phase 0: 任务恢复(新增,在 ce:work Phase 1 之前)
当重新进入一个任务时,在执行 ce:work Phase 1 之前:
1. 检查 docs/tasks/<task-id>/state.md 是否存在
2. 如果存在,读取:
- current_step / total_steps
- status (active/blocked/debugging/replanned/resumed)
- blocked_by(阻塞原因)
- last_checkpoint 时间戳
3. 从 current_step 继续,不重新执行已完成步骤
4. 更新 state.md: status → active, updated_at → 当前时间
如果 state.md 不存在(新任务),从 plugins/compound-engineering/skills-custom/task-bundle/templates/state.md.tpl 创建:
cp plugins/compound-engineering/skills-custom/task-bundle/templates/state.md.tpl \
docs/tasks/<task-id>/state.md
# 填写 task_id、total_steps、started_at
FSM 状态转换(替换 ce:work 的隐式 STOP 处理)
原 ce:work 行为(隐式)
ce:work 遇到阻塞时会停下来询问用户,没有状态记录。
本 Overlay 增强(显式状态机)
active → blocked: 遇到任何阻塞(依赖缺失、CI 失败、需求不清)
blocked → debugging: 开始排查阻塞原因
debugging → replanned: 需要修改原计划
debugging → active: 阻塞自行解除(如 CI 通过)
replanned → resumed: 新计划就绪,等待用户确认重启(⚠️ 必须等用户确认)
resumed → active: 用户确认后,按新计划重新开始(AI 执行)
active → reviewed: 实现完成,进入 ce:review
reviewed → compounded: 经验沉淀完成
任何状态 → cancelled: 任务被主动取消
replanned → resumed 用户确认门(强制):
当状态进入 resumed 时,必须展示新计划摘要并等待用户确认,禁止自动进入 active:
📋 计划已更新,重启前需要你确认:
原阻塞原因:[blocked_by 值]
新计划摘要:[更新后的关键步骤]
确认后将从步骤 [N] 重新开始。继续吗?(y/n)
用户确认后才将 state.md 的 status 更新为 active。
每次状态转换写入 state.md:
## 状态历史
| 时间 | 从 | 到 | 原因 |
|------|-----|-----|------|
| 2026-04-08 10:00 | created | active | 开始执行 |
| 2026-04-08 14:30 | active | blocked | 等待 upstream merge 完成 |
阻塞触发条件(替换隐式 STOP)
以下情况触发 active → blocked,写入 state.md 并告知用户:
| 触发条件 | blocked_by 值 |
|---|---|
| 依赖任务未完成 | depends_on: <task-id> |
| CI/测试持续失败(≥3 次) | ci_failure: <test-name> |
| 需求不清无法继续 | unclear_requirement: <描述> |
| Rate limit / 工具不可用 | tool_unavailable: <tool-name> |
| 需要人工决策 | human_decision_required: <描述> |
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.
- 5d ago First seen · 160 lines · 75 tokens per session scan A 321d2cd1baf0
ce-work-integration is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 1,462 once invoked, about $0.0004 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…