Hand off the current task to another agent with full context. Use when the user says "handoff", "hand off", "hand this to", or wants to pass work to another agent.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Transfer the current task — context, decisions, failed attempts, constraints — to a fresh agent. The receiving agent starts with zero context, so the handoff prompt must be a self-contained briefing.
User's arguments: $ARGUMENTS
Read the paseo skill. Call list_profiles before choosing the receiving agent. Do not create it until you have read the configured profiles and their notes.
notes best match the work. Materialize it into create_agent as described by the paseo skill. If no profile fits, use Paseo's provider discovery fallback.isolation: "worktree", using a short branch name derived from the task.The receiving agent has zero context. Include:
## Task
[Imperative description.]
## Context
[Why this task exists, required context.]
## Relevant files
- `path/to/file.ts` — [what it is and why it matters]
## Current state
[What's done, what works, what doesn't.]
## What was tried
- [Approach] — [why it failed or was abandoned]
## Decisions
- [Decision — rationale]
## Acceptance criteria
- [ ] [Criterion]
## Constraints
- [Must-not / must-preserve]
Preserve task semantics. Investigate-only → "DO NOT edit files." Fix → "implement the fix." Refactor → "refactor, not rewrite." Carry the user's exact intent.
Prepare the handoff in a dedicated workspace:
create_workspace with the requested isolation.create_agent with a [Handoff] <task> title, the briefing as initial prompt, and the selected workspaceId when explicit placement is needed.Do not encode independence as a create mode and do not invoke CLI or wire-level detach operations. Detach is a user gesture in the subagents track.
Do not wait or poll for the agent to finish.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Quick-save the last assistant response as a verbatim note in the 2ndBrain Obsidian vault (~/2ndBrain/quick-notes/<year>/). Use when the user asks to quick-save/save the last response to 2ndBrain, or invokes $2ndbrain or /skill:2ndbrain.
The English summary is being prepared. Showing the original description.
Write commit messages under the agent-commits convention - a Conventional Commits fork with no chore catch-all, intent-only type tokens, facts in trailers, and legally-grounded AI provenance (Assisted-by, never Co-authored-by). Use when composing a commit in a repo whose commitlint.config.js extends agent-commits, when deciding between feat/fix/refactor/perf, or when recording AI participation.
The English summary is being prepared. Showing the original description.
Coordinate multi-agent work through durable artifacts in git instead of chat. Use this whenever a task involves sending a message to another agent, agent mailboxes or handoffs, claiming work from a shared queue, notifying another agent or crew (OpenClaw, Grok Bot, Claude Code, Codex, Gas Town/Gas City workers) that work is ready, or whenever the user mentions the artifact bus, message bus, agent mail, beads mail, doorbells, or pings between agents — even if they don't say "bus" explicitly.
The English summary is being prepared. Showing the original description.
Use aven to find tasks, update status, and leave durable handoff context.
The English summary is being prepared. Showing the original description.
Plan, order and deliver a batch of backlog items (e.g. every High item) in a Conventional Docs repo, one decision, branch, worktree, draft PR, review and merge per item. Use when asked to work through the backlog, implement all items of a priority, or sequence several backlog items end to end.
The English summary is being prepared. Showing the original description.
Codex workflow tips from Boris Cherny and the Codex team. Use when setting up Codex or optimizing workflows: parallel sessions, worktrees, plan mode, AGENTS.md, skills, subagents, hooks, MCP, permissions, and sandboxing.
The English summary is being prepared. Showing the original description.