Menu
Find TODO comments in the codebase and add them to .llm/todo.md as tasks.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | markdown-sweep-todos |
| description | Find TODO comments in the codebase and add them to .llm/todo.md as tasks. |
Use the markdown-tasks skill for task format and script path rules.
Search the codebase for TODO comments. For each occurrence, capture:
Compose all TODO tasks before writing. Add the complete batch in one shell command by chaining one call per TODO with &&:
python <plugin-root>/scripts/task_add.py .llm/todo.md "Implement TODO from <file>:<line>: <todo text>" && \
python <plugin-root>/scripts/task_add.py .llm/todo.md "Implement TODO from <another-file>:<line>: <todo text>"
Never add a multi-TODO batch across separate shell commands. Keeping the writes together reduces the chance that concurrent sessions interleave their tasks.
Report how many TODO tasks were added.
Restore claude/codex agents from a tmux-reboot snapshot after tmux-resurrect reopens their windows.
Snapshot running tmux claude/codex agents immediately before a reboot so their sessions can be restored afterward.
Commit changes, run git-test precommit checks, and fix failures. Use when asked to fix build, test, lint, typecheck, or precommit failures.
Running precommit checks and build validation. ALWAYS use after ANY code changes.
This skill should be used after completing any task, before returning control to the user. Always run this skill — it handles the case where there's nothing to do.
Coordination guidelines for leading a team of task-executing agents