akiiwa-games/AgentCompass / skills/agent-compass
agent-compass
FlaggedChoose owner, model and effort, outbound authorization, advisor use, and continuation for delegated work. Reads local usage and effective account policy, profiles the task with the configured System-One scorer, then allocates a compatible worker. Use for independent worker or advisor work; ordinary local execution needs no routing.
references/worker-communication.md
View on GitHub# Worker 通信与汇报契约
1. **直接执行**:你是受派 worker,直接动手完成任务,禁止再派子 agent(除非任务书明确任命你为协调者)。
2. **遇阻与禁令**:提问或汇报后立即结束本轮,不同步阻塞等待。**严禁**调用 `request_user_input_async`、`request_user_input`、`AskUserQuestion`、`ask_user_question` 等本地交互提问工具;若无可用消息工具或发送失败,直接在最终回复中返回 `BLOCKED / needs_input`、具体问题与通信限制并结束本轮,切勿伪造收件人或声称已送达。**严禁把非 Paseo 的会话 ID 传给 Paseo API。**
3. **汇报渠道由本次派发决定**,只走下面两节中的一节。中途提问仍按该节的消息工具发给父会话并立即结束本轮。
## 有完成监视
本派发有完成监视。结束时不要发送 `[Worker final report]`。把完整报告只写在最终回复里。中途提问仍用 `send_agent_prompt` 发给 `Parent session agent ID`,设 `background: true, notifyOnFinish: false`。父会话用 `send_agent_prompt` 续跑后,仍然不要自己发最终报告;那一轮的结束通知是父会话的 `notifyOnFinish`。
## 无完成监视
本次派发没有完成监视,由你自己把报告送到父会话。
- **具备主会话消息工具的宿主**:Paseo 用 `send_agent_prompt` 发给 `Parent session agent ID`(设 `background: true, notifyOnFinish: false`);Herdr 用 `hc send <Parent ID> <message>`;带收件箱的原生编排宿主(如 Orca / Claude `SendMessage` / AGY `send_message`)发往 `Parent message address`(保留宿主注入的 sender 与 lifecycle 参数)。结束本轮前用同一通道发送 `[Worker final report]`,同时在最终回复保留完整报告。
- **由宿主自身管理消息/无直达父会话邮箱的通道**(如 **Cindy 任务**、`T3`、`agy`、无头 CLI、Dot、Grok-bot,或尾注声明无 worker-to-parent mailbox 时):直接在最终回复(final assistant reply / stdout)写出完整的 `[Worker final report]` 并结束本轮,由宿主任务接口或状态工具(如 Cindy `tasks.readMessages` / 插件 `status`)收取。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |