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/task-bundlenpx skills add Jerrylalala/compound-engineering --skill task-bundlegit clone --depth 1 https://github.com/Jerrylalala/compound-engineeringWhat 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 | $0.00024 | $0.00491 |
| Opus 5 | $0.00012 | $0.00246 |
| Sonnet 5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
task-bundle 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 2d 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.
What it actually says
Task Bundle 管理
什么是 Task Bundle
Task Bundle 是任务的统一工件结构。每个任务由三个文件组成：
| 文件 | 职责 | 写入时机 |
|---|---|---|
plan.md |
目标、约束、验收标准 | 任务创建时 |
state.md |
当前步骤、阻塞点、状态机历史 | 执行过程中持续更新 |
review.md |
findings、证据、结论 | 审查阶段 |
创建新 Task Bundle
- 生成 task-id：
YYYY-MM-DD-<seq>-<kebab-description> - 创建目录
docs/tasks/<task-id>/ - 从模板复制三个文件，替换占位符
- 更新 frontmatter 中的 task_id、created_at、owner
状态转换规则
参见 Failure FSM 协议（docs/specs/failure-fsm.md）。
每次状态转换必须：
- 更新
state.md的statusfrontmatter 字段 - 在状态历史表追加一行（时间、从、到、原因、操作者）
- 更新
last_checkpoint时间戳
与现有工作流的关系
Phase 0 说明：当前 Task Bundle 是独立的文档协议，自身不含自动集成机制。 如需在 ce:work 执行时自动读写 state.md，需配合加载
ce-work-integrationoverlay（见 skills-custom/ce-work-integration/SKILL.md）。 Phase 2 将在上游合并后，将 Task Bundle 读写集成到 ce-work/ce-review 中。
手动使用方式：
/workflows:plan输出后，手动创建 Task Bundle 并链接 plan 文件/workflows:work执行中，手动更新 state.md/workflows:review完成后，手动填写 review.md
模板位置
skills-custom/task-bundle/templates/
├── plan.md.tpl
├── state.md.tpl
└── review.md.tpl
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 53 lines · 24 tokens per session scan A 2cb2fb4e7956
task-bundle is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 491 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
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…