원클릭으로
add-teammate
在现有 team 中增加一个 teammate:走简化版 spawn-team 流程(只处理单人)。 Team lead 可自主调用(用户自然语言同意后)。只在 team lead 上下文有效。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
在现有 team 中增加一个 teammate:走简化版 spawn-team 流程(只处理单人)。 Team lead 可自主调用(用户自然语言同意后)。只在 team lead 上下文有效。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Team lead invokes after session restart: reads TEAMMATE_INFO.json to rebuild the team by using the Agent tool to spawn fresh sessions for each active teammate (name must be <slug>-<role>; permission mode inherits the lead, not set per-teammate at spawn), guiding each to read its workstation's working-context.md (Part A snapshot + Part B work journal) to self-recover state. No-arg invocation wakes only active/idle and **skips benched** (temporarily offline); `/reactivate-team <name>` wakes back one specified (usually benched) teammate. This is the ONLY way to "recover a team across sessions" — Claude Code does not auto-respawn teammates.
Structured flow for a team lead to assemble a Claude Code agent team. 6 phases: task decomposition → lineup proposal (selected from role_archetypes) → plan-mode gating → adversarial check → user confirmation → spawn each teammate via the Agent tool (name must be <slug>-<role>; permission mode inherits the lead, not set per-teammate at spawn) + save team_recipe. After Phase 5 user confirmation, Phase 6 spawns immediately with no additional confirmation. The agent can invoke autonomously; if currently a flat workstation, it will first guide through /promote-to-team.
Team lead 在 session 重启后调用,读 TEAMMATE_INFO.json 重建 team: 为每个 active teammate 用 Agent 工具 spawn 新 session(name 必须为 <slug>-<role>;权限模式继承 lead,不在 spawn 时单设), 引导它读自己工位的 working-context.md(Part A 快照 + Part B 工作日志)恢复状态。 无参调用只唤醒 active/idle,**跳过 benched**(临时下线);`/reactivate-team <name>` 单独唤回指定的(通常是 benched)teammate。这是"跨 session 团队恢复"的唯一方式—— Claude Code 不会自动 respawn teammate。
Team lead 组建 Claude Code agent team 的结构化流程。6 阶段:任务分解 → 阵容提案 (从 role_archetypes 选) → plan-mode gating → 对抗性检查 → 用户确认 → 用 Agent 工具(name 必须为 <slug>-<role>;权限模式继承 lead,不在 spawn 时单设)逐一 spawn 每个 teammate + 保存 team_recipe。Phase 5 用户确认后直接 spawn,不再额外确认。Agent 可自主调用;若当前是扁平工位,会先引导 /promote-to-team。
Add a teammate to an existing team: runs a simplified spawn-team flow (single person only). Team lead can invoke autonomously (after natural-language user consent). Valid only in team lead context.
Temporarily take a teammate offline (benched): have it write a final checkpoint, close its session to free an online slot, but **keep its full record + workstation + docs**, and set its status to benched in TEAMMATE_INFO.json. Unlike /remove-teammate (permanent offboard), benched means "will come back" — wake it later with `/reactivate-team <name>`. Team lead invokes autonomously (after user consent). Only valid in team lead context.
| name | add-teammate |
| description | 在现有 team 中增加一个 teammate:走简化版 spawn-team 流程(只处理单人)。 Team lead 可自主调用(用户自然语言同意后)。只在 team lead 上下文有效。 |
| disable-model-invocation | false |
| allowed-tools | Read Write Edit Glob Grep |
/add-teammate — 向现有 team 增加一个 teammate先从对话 context 推断:你应该已经知道自己是 team lead。无法推断时:
_agent_team_work_zone/*_team/向用户或从对话 context 收集:
查阅:
resources/agents/):tracker / investigator / reviewer / devil-advocate / git-repo-managerresources/role_archetypes/):9 个<SELF>_team/teammates/)原则:
## 新 teammate 提案
- **name**: <slug>-<role>(**必须** `<slug>-<role>` 格式:slug = 本 team 工位名去 `_team`、单 token 无连字符;role 可含连字符。例 `architect-reviewer`。全局唯一)
- **角色来源**: <subagent 名 / role_archetype 路径 / 原创>
- **模型**: <haiku / sonnet / opus>
- **Plan-mode gating**: <YES / NO>
- **作用域**: <具体可碰的文件/目录>
- **禁区**: <不能碰的>
- **交付物**: <产出什么>
- **与现有 team 的协作**: <谁给它派活、它的产出给谁>
你同意加入这个 teammate 吗?
等用户明确同意后进入 Phase 4。
路径:_agent_team_work_zone/<SELF>_team/teammates/<teammate-name>/
创建 5 个文件(Rule 13 规定的 teammate 自维护 5 文件):
README.md — 角色定义:写 Phase 3 里收集的昵称、模型、作用域、禁区、交付物、plan-mode gating 说明,以及(可选)一个空的 ## Checkpoint Instructions 段位供后续定制working-context.md — 初始占位:
# Working Context — <teammate-name>
_Initialized at spawn. Run /checkpoint to populate._
completed.md — 空文件(append-only 日志,由 /checkpoint 的 task_completed trigger 追加)TODO.md — 空文件commitments.md — 空文件在 _agent_team_work_zone/<SELF>_team/TEAMMATE_INFO.json 的 active_teammates 数组尾部追加一条(如果文件不存在,先按 schema v1 初始化 — 参见 docs/teammate_info_schema.md):
{
"name": "<teammate-name>",
"role_source": {
"type": "archetype" | "subagent" | "tier2" | "inline",
"path": "..." // 或 subagent_name 或 inline_description
},
"model": "<haiku|sonnet|opus>",
"plan_mode_gating": <true|false>,
"scope": "<作用域简述>",
"spawned_at": "<ISO8601 当前时间>",
"last_checkpoint_at": null,
"revived_count": 0,
"status": "active"
}
同时更新顶层 updated_at 为当前时间。
jq 示例(如果可用):
jq --argjson entry '<json 对象>' --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
'.active_teammates += [$entry] | .updated_at = $ts' \
_agent_team_work_zone/<SELF>_team/TEAMMATE_INFO.json > /tmp/info.json && \
mv /tmp/info.json _agent_team_work_zone/<SELF>_team/TEAMMATE_INFO.json
我要向现有的 <SELF> team 增加一个新的 teammate:
<昵称>(模型:<model>)
角色定义:<引用或填入内容>
任务:<细节>
Plan-mode gating: <YES/NO + 批准标准>
你的工位在 _agent_team_work_zone/<SELF>_team/teammates/<昵称>/(README/working-context/
completed/TODO/commitments 5 个文件已由 lead 初始化)。按 Rule 13 维护它:进入 idle 前、
收到 checkpoint 提醒时、任务完成后调用 /checkpoint 更新 working-context.md。
它的产出写到 _agent_team_work_zone/<SELF>_team/roundtable/,和其他 teammate 通过 mailbox 协作。
请 spawn 这个新 teammate 加入现有 team。
不新建 recipe 文件(那是 /spawn-team 的事)。而是:
<SELF>_team/team_recipes/ 下按时间倒序第一个)---
## Amendment — YYYY-MM-DD HH:MM — add-teammate
### 新增 teammate
<Phase 3 的提案内容>
### 原因
<Phase 1 收集的需求>
### Spawn Prompt
<Phase 4 生成的 prompt>
这样后续 /evaluate-team 或下次 /spawn-team 能看到完整 team 演化历史。
在下一条消息把 Phase 5 的 prompt 发出,Claude Code 内置机制识别并 spawn。
✅ teammate 工位骨架已创建(5 文件)
✅ TEAMMATE_INFO.json 已追加新条目
✅ team_recipes/<latest>.md 已追加 Amendment
下一步发送 spawn prompt 给 Claude Code agent-team 机制
<SELF>_team/roundtable/