بنقرة واحدة
agent-task
List and run agent tasks defined in _module/agent_tasks/ directories across the repo
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
List and run agent tasks defined in _module/agent_tasks/ directories across the repo
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Build the Meadow Electron app and launch it in test mode to verify it starts cleanly
Safely clean up the current worktree after verifying no unmerged work would be lost
Run the end-to-end test suite, automatically diagnose and fix failures
Finish a worktree development session - commit, merge to main, and clean up
Understand and extend the regenerable canonical scenario artifact in the e2e report viewer — used for iterating on the viewer's UI against stable, self-documenting data without running real tests
Merge a worktree branch into main - handle conflicts, run full checks, auto-fix issues
| name | agent-task |
| description | List and run agent tasks defined in _module/agent_tasks/ directories across the repo |
Run agent tasks defined in _module/agent_tasks/ directories throughout the
repo using the tools/agent_task/run_agent_task runner.
/agent-task)Scan for all agent task markdown files and list them:
find . -path '*/_module/agent_tasks/*.md' -not -path '*/node_modules/*' | sort
Display the results as a list showing the full paths so the user can see where each task lives.
/agent-task <name> [options])Resolve the task file — match the user's <name> against the discovered
agent task files. Use fuzzy/substring matching (e.g. "pagespec" matches
pagespec_chaos_check.md). If the match is ambiguous, ask the user to
clarify.
Determine run count — look for a number in the user's request (e.g. "run pagespec chaos 30 times", or "-n 30"). Default to 1 if not specified.
Run it — execute the runner, which invokes claude --print in a loop:
./tools/agent_task/run_agent_task -n <count> -v <resolved_task_file>
Run this in the background since agent tasks are long-running. The runner
logs to tools/agent_task/run_agent_task.log — tell the user they can
tail -f that file to watch progress.
Use the -v (verbose) flag by default so tool calls are visible in the log.