Agent task confirm
Use when confirming whether a dispatched agent task was actually received, activated, and progressing after sessions_send or other task handoff actions.From its SKILL.md
npx -y skills add aAAaqwq/AGI-Super-Team --skill agent-task-confirmAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.0 KB, 618 tokens by cl100k_base, as published. Nobody here has run it
Agent 任务派发与确认机制
确保每次派发任务后，agent 确实收到并在执行。
触发条件
- 每次通过 sessions_send 派发任务后自动执行
- "检查员工状态"、"任务确认"
派发后确认流程
Step 1: 派发任务
sessions_send(sessionKey="agent:<id>:telegram:group:-1003890797239", message="【CEO指令】...")
Step 2: 立即确认送达（30秒内）
sessions_list(activeMinutes=5, kinds=["agent"], messageLimit=0)
检查目标 agent 的 session 是否 active（updatedAt 在最近 60 秒内）。
Step 3: 判断状态
| 状态 | 判断条件 | 处理 |
|---|---|---|
| ✅ 已接收 | session active, updatedAt 刚更新 | 等汇报 |
| ⚠️ 可能卡住 | session active 但 5min+ 无新消息 | 发催促消息 |
| ❌ 未接收 | session 不在 active 列表 | 重发一次，仍失败则报告 Daniel |
Step 4: 超时催促（5分钟无汇报）
如果 agent 5 分钟内没有发群里汇报，发催促：
sessions_send(sessionKey="agent:<id>:...", message="【催促】你的任务完成了吗？立即用 message 发群里汇报进度。")
Step 5: 死亡判定（10分钟无响应）
如果催促后 5 分钟仍无反应：
- 检查 agent 的 session 是否报错（abortedLastRun）
- 报告 Daniel："小X 可能卡住了，需要检查"
- 考虑重新派发给其他 agent
每次派发的标准模板
任务消息必须包含：
- 【CEO指令】开头
- 具体任务描述
- 文件写在哪里
- 完成后的 message 汇报指令（含 accountId）
- "不发群里 = 任务没完成"
批量检查命令
快速检查所有 agent 状态：
sessions_list(activeMinutes=10, kinds=["agent"], messageLimit=1)
看每个 agent 的 updatedAt 和最后一条消息判断是否在工作。
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most context ai engineering skills give in 618 tokens
Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06
- Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
- Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
- Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
- Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
- Use the least powerful model capable of the taskin 33 of 1328, across 26 files
- Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
- Perform a task review after each implementationin 31 of 1328, across 24 files
- Extract all tasks and context from the planin 29 of 1328, across 20 files
- Provide full task text to subagentsin 28 of 1328, across 20 files
- Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
- Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
- Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files
Said here and by no other author read
- Verify agent session is active after task dispatch
- Check session updatedAt within sixty seconds
- Send reminder if no progress after five minutes
- Report to supervisor if no response after ten minutes
- Include task details and reporting instructions in messages
- Check for abortedLastRun status on unresponsive agents
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.