菜单
Run commands to explore the current state of mngr and any relevant running agents. Use this skill when you need to debug issues with mngr tasks, or understand what tasks are currently running and their states.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Submit a bug report to libraries within the `mngr` project (eg, `mngr`, its plugins, `minds`, etc). Use to report bugs you encounter while running that seem to be issues with the `mngr` code itself, rather than with your own code or configuration.
Handle events from the mngr/agent_states source about sub-agent state transitions (finished, waiting, done, etc). You **MUST** use this skill (and *carefully follow the process in this doc*) whenever you receive a message from the "mngr/agent_states" source!
Clean up old agents, their output directories, and other historical data. Use during nightly cleanup or when the system has accumulated stale data.
Handle unexpected situations where the Minds system does not appear to be working as expected. Use when you encounter behavior that seems to contradict what your docs and prompts and skills say should happen, or when something seems broken and you are unsure how to proceed.
Create a sub-agent to perform a task. Use when you need to delegate work to another agent, for example, a working agent (for actually accomplishing some task) or a verifying agent (for deciding what to do about the output of a working agent).
Handle events from the messages source about user or assistant messages in conversations. You **MUST** use this skill (and *carefully follow the process in this doc*) whenever you receive a message from the "messages" source!
| name | debugging-mngr-tasks |
| description | Run commands to explore the current state of mngr and any relevant running agents. Use this skill when you need to debug issues with mngr tasks, or understand what tasks are currently running and their states. |
If something seems to have gone wrong with a given task, mngr provides a variety of commands that can make it easier to see what is happening.
You can always learn more about mngr and its commands by running mngr --help or mngr <command> --help for a specific command.
mngr list --exclude "has(labels.archived_at)" --exclude "id == \"$AGENT_ID\"" --format jsonl - see all running agents and their states (and exclude all archived agents and yourself from the list so you can focus on the agents that matter)mngr message <agent> -m "..." - send a follow-up message to an agentmngr archive <agent> - stop an agent and remove it from the list of agents (note that an agent's logs and data will still be accessible after this)mngr exec <agent> "command" - run a shell command on an agent's hostmngr events <agent> - see the logs or events for a given agentmngr capture <agent> - effectively calls tmux capture-pane on the agent's tmux pane, so you can see the most recent output from that agentStart by running mngr list --exclude "has(labels.archived_at)" --exclude "id == \"$AGENT_ID\"" --format jsonl to see all currently running agents (besides yourself) and their states, or mngr capture <agent> --full to see the full output from a given agent.
This can often give you a good sense of what is happening and where things might be going wrong.
NEVER run commands on any agents other than those that you created yourself!