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/team-modenpx skills add Jerrylalala/compound-engineering --skill team-modegit 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/team-mode)<a href="https://agentmods.dev/skills/jerrylalala/compound-engineering/team-mode"><img src="https://agentmods.dev/badge/skills/jerrylalala/compound-engineering/team-mode.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 | $0.00055 | $0.05193 |
| Opus 5 | $0.00028 | $0.02596 |
| Sonnet 5 | $0.00011 | $0.01039 |
| Haiku 4.5 | $0.00006 | $0.00519 |
Grade A, and why
team-mode 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Mode Overlay
核心理念：合约边界 + 单写者原则 + 独立验证者 = 问题在发生前被拦截。
各命令的实现层次不同：
ce:work [T]：真实 Claude Code Agent Teams（TeamCreate + 独立 context window + SendMessage）ce:brainstorm [P]：[P] 结束后自动触发探索者+挑战者收敛（无独立 [T] 参数，避免与 Claude Code Agent Teams 混淆）ce:plan [T]：同一 agent 多任务（有意设计，合约生成和追溯审查是顺序文档处理，不需要验证循环）ce:review [T]：规则引擎（有意设计，Patch Gate 是 deterministic whitelist check，零 token）
本 skill 是叠加在 ce:plan/ce:work/ce:review 之上的 overlay。各命令通过检测 [T]、[T+] token 激活对应的角色集和机制。ce:brainstorm 不支持 [T] 参数，结构化收敛已内置为 [P] 的自动后续行为。
参数变体
| Token | ce:work 实现 | ce:plan/review 实现 | 适用场景 |
|---|---|---|---|
[T] |
TeamCreate + verifier teammate（独立 context window）+ lead 扮演合约主+执行者 | 同一 agent（plan=合约生成，review=规则引擎） | 默认，大多数任务 |
[T+] |
在 [T] 基础上额外 spawn risk-guard teammate |
同 [T]（plan/review 无额外角色） |
auth/payment/migration 高风险路径 |
ce:brainstorm 不使用 [T] 参数：结构化收敛（探索者+挑战者）已内置为 [P] 结束后的自动行为，避免与 Claude Code 原生 Agent Teams 混淆。
角色定义
| 中文名 | 适用阶段 | 职责 | 生命周期 |
|---|---|---|---|
| 合约主 | plan, work | 执行前写边界合约（allowed_files/forbidden_surfaces/invariants），全程持有合约权威。.team-contract.md 作为团队章程（所有 teammate 启动时读取），不是通信介质 |
全程存活（文件持久化） |
| 执行者 | work | 唯一可写共享代码的角色（单写者原则）。遇越界暂停上报，不自行决策 | 按任务运行 |
| 验证者 | work | 独立 context window 的真实 teammate。等待 lead 发 SendMessage 通知，运行不变式检查，只读不写，回复 PASS/FAIL | 事件驱动（每 Unit 完成后收到 SendMessage） |
| 风险卫 | work（[T+]） | 独立 context window 的真实 teammate。等待 lead 发 Unit 开始通知，检测高风险关键词，回复拦截或通过，要求用户确认才继续 | 仅 [T+] 模式，Unit 开始前 |
| 追溯审查 | plan | 搜索 docs/solutions/ 查找历史相关案例，检查计划决策是否与已记录 gotcha 矛盾，将发现追加到计划 Open Questions 节 |
ce:plan Phase 4.5（只读） |
| 探索者 | brainstorm | 聚焦「这个想法在技术上可行吗？」，提出具体验证路径和可达条件 | ce:brainstorm [P] 结束后自动触发（非独立参数） |
| 挑战者 | brainstorm | 质疑假设，寻找边界条件和反例，防止过早收敛 | ce:brainstorm [P] 结束后自动触发（非独立参数） |
各阶段角色集
| 阶段 | 默认角色 | [T+] 追加 |
|---|---|---|
/ce:brainstorm [P] |
[P] 结束后自动收敛（探索者+挑战者，内置，无需 [T]） | — |
/ce:plan [T] |
合约主 + 追溯审查 | — |
/ce:work [T] |
合约主 + 执行者 + 验证者 | 风险卫 |
/ce:review [T] |
现有多个专业审查 agent + Patch Gate | — |
What ships with it
1 file 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.
- 5d ago First seen · 364 lines · 55 tokens per session scan A 28ae2a6b161f
team-mode is a skill published in the GitHub repository Jerrylalala/compound-engineering (5 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 5,193 once invoked, about $0.0003 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…