{"skill":{"slug":"agent-task-status","displayName":"Agent Task Status","summary":"Verify whether named OpenClaw agents actually received formal task assignments and replied with execution status, using transcript-backed audit checks. Use w...","description":"---\nname: agent-task-status\ndescription: Verify whether named OpenClaw agents actually received formal task assignments and replied with execution status, using transcript-backed audit checks. Use when auditing real delegation, confirming assignment delivery to specific agents, reviewing recent task completion, checking whether an agent replied after being assigned work, or troubleshooting multi-agent routing from session transcripts. Especially useful for requests like “检查小程/小文/小编有没有收到任务”, “确认任务有没有真正派到 agent 本人”, “看看这些 agent 执行到哪一步”, “汇总最近派单情况”, or “排查多 agent 调度是否真的落到本人并形成回报闭环”.\n---\n\n# Agent Task Status\n\nUse the bundled script to inspect OpenClaw session indexes and transcript files, then extract the latest assignment and structured report for each target agent.\n\n## Quick start\n\nRun the script directly:\n\n```bash\npython3 /home/lyqadmin/.openclaw/workspace/skills/agent-task-status/scripts/check_agent_task_status.py --format summary\n```\n\nFor more examples, read `references/usage.md`.\n\n## Workflow\n\n1. Decide which agents to inspect.\n   - Use `--agents a,b,c` for explicit targets.\n   - Use `--agent-file` when the list comes from a file.\n   - Use `--discover` when the deployment has many agents under the same root.\n2. Set the agent storage root.\n   - Default is `~/.openclaw/agents`.\n   - Override with `--base` or `OPENCLAW_AGENTS_BASE` in non-default environments.\n3. Match the session shape.\n   - Default session key template is `agent:{agent}:main`.\n   - Override with `--session-key-template` if your target sessions use another pattern.\n4. Match the assignment/report language.\n   - Default assignment keyword is `正式任务分配：`.\n   - Default report prefixes are `任务：` / `状态：` / `结果：` / `风险：`.\n   - Override these when the team uses different markers or another language.\n5. Filter the output when needed.\n   - `--only-status` filters by normalized status such as `completed`, `blocked`, `accepted`, `no-assignment`, `assigned-no-report`, `error`.\n   - `--contains` filters by keyword across assignment text, parsed task, result, and risk.\n6. Pick an output format.\n   - `table`: best for human inspection\n   - `summary`: compact overview\n   - `json`: structured automation output\n   - `jsonl`: line-oriented pipelines\n7. Use `--strict` for CI/automation.\n   - Exit `0`: normal\n   - Exit `1`: partial problem such as missing assignment/report or agent error\n   - Exit `2`: script/runtime error\n8. Use `--output-file` to persist results for later review or downstream automation.\n\n## Recommended commands\n\nHuman-readable table:\n```bash\npython3 /home/lyqadmin/.openclaw/workspace/skills/agent-task-status/scripts/check_agent_task_status.py --agents xiaocheng,xiaowen,xiaobian --format table\n```\n\nOnly completed tasks:\n```bash\npython3 /home/lyqadmin/.openclaw/workspace/skills/agent-task-status/scripts/check_agent_task_status.py --discover --only-status completed --format summary\n```\n\nFilter by keyword:\n```bash\npython3 /home/lyqadmin/.openclaw/workspace/skills/agent-task-status/scripts/check_agent_task_status.py --discover --contains 自动化 --format table\n```\n\nAutomation JSON:\n```bash\npython3 /home/lyqadmin/.openclaw/workspace/skills/agent-task-status/scripts/check_agent_task_status.py --agent-file ./agents.txt --format json --strict --output-file ./agent-status.json\n```\n\n## What to inspect in the output\n\n- `sessionKey`: which session was used\n- `sessionFile`: exact transcript file path\n- `assignedAt` / `assignText`: when and what was assigned\n- `reportAt`: when the agent reported back\n- `task` / `status_raw` / `status_normalized` / `result` / `risk`: parsed structured fields\n- `error`: why the check failed for that agent\n\n## Limitations\n\n- This skill assumes an OpenClaw-style agent root with `sessions/sessions.json` and transcript `sessionFile` paths.\n- It only checks the target session pattern you specify; it does not automatically infer every possible routing form.\n- If the assignment keyword or report field prefixes change, you must override them.\n- It reports what is present in transcripts; it does not infer hidden work with no assignment/report markers.\n","tags":{"latest":"1.1.0"},"stats":{"comments":0,"downloads":550,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":2},"createdAt":1773652056809,"updatedAt":1778491943830},"latestVersion":{"version":"1.1.0","createdAt":1773652879649,"changelog":"Add filtering, output-file support, status normalization, and stronger transcript-audit positioning.","license":"MIT-0"},"metadata":null,"owner":{"handle":"lujohn74","userId":"s173593jppckb1wjjtf10x1v8n83kevw","displayName":"Lu Yanqiang","image":"https://avatars.githubusercontent.com/u/17892763?v=4"},"moderation":null}