Adonis0123/adonis-skills / skills/agent-dispatch
agent-dispatch
FlaggedChoose the lightest agent setup for a coding, review, drafting or design-research task: do it yourself, fan out to 2-3 workers with independent parts across the Claude Code, Codex, Grok Build, Cursor or other CLIs and accounts on this machine, run a scoped architecture loop, or send one brief to independent researchers; pick a cross-model reviewer, test budget and cleanup; track dispatched work, external waits and user decisions on a Run Board. Use when work may need delegation, or the user asks to dispatch, fan out, parallelize, run several agents or accounts, get another AI's review or independent design opinions, or asks how dispatched work is going. Chinese triggers: 派活、并行、要不要多开几个 agent、分给多个 Claude 账号 / codex / grok、找另一个 AI 审、对比优秀设计、多方意见、进度看板、派出的任务进行到哪了。Not for unrelated read-only questions, trivial edits, research with no delegation, a single review of an existing diff (agentic-review-handoff), or the machine-wide session list (sideby sessions). Inside another named workflow, only size its workers.
GLOSSARY.md
View on GitHub# Agent Dispatch
How one coordinating session splits a task across agent sessions and lets the user see where each part stands.
These terms are for agents, the ledger and the docs. With the user, speak plain words instead (任务, 外部等待, 问题, 账号额度); the _Avoid_ lists below apply to agent-facing text only.
## Language
**Run**:
One dispatch of a task: the set of Lanes started by one Coordinator decision.
_Avoid_: job, batch (a batch is a group of Lanes integrated together inside a Run)
**Lane**:
One independent piece of work inside a Run, with its own task; write Lanes also get their own branch and worktree.
_Avoid_: task, part, slot
**Worker**:
A session (one product on one account) that carries out one Lane. A review is its own Lane that names the Lane it reviews.
_Avoid_: agent (too broad), peer
**Subagent**:
A child task spawned inside a session, shown under the session that spawned it.
_Avoid_: worker, teammate
**Coordinator**:
The single session that starts Lanes, integrates their results, decides and reports to the user.
_Avoid_: orchestrator, lead, host
**Side Session**:
A separate session the Coordinator opens for a request unrelated to the current task. It belongs to no Run and has no Lane; its result goes to the user, not into the Coordinator's task.
_Avoid_: Lane, Worker, background task
**Board**:
The milestone report of one Run, written only at milestones and served by no process: what each Lane produced, decisions, outputs and open Asks. Live status belongs to sideby's Panel, not the Board.
_Avoid_: dashboard, monitor, status page
**Wait**:
An outside process the Run is waiting on that has no Worker, such as a deploy, CI run, build or background shell.
_Avoid_: job, task, background thing
**Ask**:
One question waiting on the user, always with a recommended answer, the evidence behind it and what it blocks.
_Avoid_: confirmation, todo, pending item
**Standing Grant**:
A permission the user gave for repeated use ("以后都这样"), recorded with its exact scope; outward actions stay limited to the current Run.
_Avoid_: preference, default, blanket approval
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |