SkillHub

agent-task-status

v1.1.0

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 re...

Sourced from ClawHub, Authored by Lu Yanqiang

Installation

Please help me install the skill `agent-task-status` from SkillHub official store. npx skills add lujohn74/agent-task-status

Agent Task Status

Use the bundled script to inspect OpenClaw session indexes and transcript files, then extract the latest assignment and structured report for each target agent.

Quick start

Run the script directly:

python3 /home/lyqadmin/.openclaw/workspace/skills/agent-task-status/scripts/check_agent_task_status.py --format summary

For more examples, read references/usage.md.

Workflow

  1. Decide which agents to inspect.
  2. Use --agents a,b,c for explicit targets.
  3. Use --agent-file when the list comes from a file.
  4. Use --discover when the deployment has many agents under the same root.
  5. Set the agent storage root.
  6. Default is ~/.openclaw/agents.
  7. Override with --base or OPENCLAW_AGENTS_BASE in non-default environments.
  8. Match the session shape.
  9. Default session key template is agent:{agent}:main.
  10. Override with --session-key-template if your target sessions use another pattern.
  11. Match the assignment/report language.
  12. Default assignment keyword is 正式任务分配：.
  13. Default report prefixes are 任务： / 状态： / 结果： / 风险：.
  14. Override these when the team uses different markers or another language.
  15. Filter the output when needed.
  16. --only-status filters by normalized status such as completed, blocked, accepted, no-assignment, assigned-no-report, error.
  17. --contains filters by keyword across assignment text, parsed task, result, and risk.
  18. Pick an output format.
  19. table: best for human inspection
  20. summary: compact overview
  21. json: structured automation output
  22. jsonl: line-oriented pipelines
  23. Use --strict for CI/automation.
  24. Exit 0: normal
  25. Exit 1: partial problem such as missing assignment/report or agent error
  26. Exit 2: script/runtime error
  27. Use --output-file to persist results for later review or downstream automation.

Human-readable table:

python3 /home/lyqadmin/.openclaw/workspace/skills/agent-task-status/scripts/check_agent_task_status.py --agents xiaocheng,xiaowen,xiaobian --format table

Only completed tasks:

python3 /home/lyqadmin/.openclaw/workspace/skills/agent-task-status/scripts/check_agent_task_status.py --discover --only-status completed --format summary

Filter by keyword:

python3 /home/lyqadmin/.openclaw/workspace/skills/agent-task-status/scripts/check_agent_task_status.py --discover --contains 自动化 --format table

Automation JSON:

python3 /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

What to inspect in the output

  • sessionKey: which session was used
  • sessionFile: exact transcript file path
  • assignedAt / assignText: when and what was assigned
  • reportAt: when the agent reported back
  • task / status_raw / status_normalized / result / risk: parsed structured fields
  • error: why the check failed for that agent

Limitations

  • This skill assumes an OpenClaw-style agent root with sessions/sessions.json and transcript sessionFile paths.
  • It only checks the target session pattern you specify; it does not automatically infer every possible routing form.
  • If the assignment keyword or report field prefixes change, you must override them.
  • It reports what is present in transcripts; it does not infer hidden work with no assignment/report markers.