Do not hand-write workspace paths in normal usage. Let the script resolve the current workspace and discover registered workspaces from OpenClaw.
Notes
Single-workspace mode works out of the box after install.
Multi-agent routing is opt-in: it only matters when you call dispatch.
setup-heartbeat --all --write appends or updates a managed block for every discovered workspace instead of overwriting the full file.
report generates different output shapes for forum sources and direct chat sources.
1---2name: case-004203description: agent-todo Skill4---56# agent-todo Skill78Use this skill as an execution queue, not as a passive reminder list.910核心原则:每个 agent 只维护并消费自己 workspace 下的任务队列;需要跨 agent 分发时,再按 OpenClaw 已注册的 workspace 进行发现和投递。1112## Core commands1314```bash15bash ./script.sh add "Publish release" \16 --task-type publish \17 --source "forum:#19/reply:88" \18 --next-action "Push main to GitHub and publish ClawHub version" \19 --success-criteria "GitHub and ClawHub are both updated"2021bash ./script.sh dispatch "Review release" \22 --to-agent reviewer \23 --task-type review \24 --source "chat:direct" \25 --next-action "Review release artifacts" \26 --success-criteria "Feedback delivered"2728bash ./script.sh run-pending --claim29bash ./script.sh done <id> --note "what was completed"30bash ./script.sh report <id>31bash ./script.sh block <id> --reason "why blocked"32bash ./script.sh setup-heartbeat --write33bash ./script.sh setup-heartbeat --all --write34```3536## Workflow37381. Add tasks with enough execution context:39 - `task_type`40 - `next_action`41 - `success_criteria`42 - `source`432. For composite goals, prefer `plan` to split them into concrete steps.443. During heartbeat, run:45 - `bash ./script.sh run-pending --claim`464. If it returns `EXECUTE_NOW`, do the task immediately.475. Prefer continuing a `running` task before opening a fresh `pending` one.486. To assign work to another agent, use `dispatch --to-agent <agent_id>`.497. After execution:50 - success → `done`51 - generate reply text → `report`52 - cannot continue → `block`53 - no longer needed → `cancel`5455## Storage model5657- Current workspace queue: `.agent-todo/tasks.json`58- Optional local identity: `.agent-todo/local.json`59- Workspace discovery source: `~/.openclaw/openclaw.json`60- Heartbeat wiring: managed block in `HEARTBEAT.md`6162Do not hand-write workspace paths in normal usage. Let the script resolve the current workspace and discover registered workspaces from OpenClaw.6364## Notes6566- Single-workspace mode works out of the box after install.67- Multi-agent routing is opt-in: it only matters when you call `dispatch`.68- `setup-heartbeat --all --write` appends or updates a managed block for every discovered workspace instead of overwriting the full file.69- `report` generates different output shapes for forum sources and direct chat sources.
Run npx skillmds@latest add knownasnaffy/case-00420 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
agent-todo Skill It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
knownasnaffy (@knownasnaffy) published this skill. Their other Agent Skills are listed on their SkillMD profile.