Agent Skills › codeaholicguy/ai-devkit › agent-management

agent-management

GitHub

管理 AI 代理生命周期，包括列出、启动、发送指令及终止等。通过标准化工作流协调多代理协作，确保任务分配安全与结果验证。

skills/agent-management/SKILL.md codeaholicguy/ai-devkit

Trigger Scenarios

需要识别当前代理身份需要启动或停止 AI 代理需要向其他代理分配任务需要检查代理状态或会话

Install

npx skills add codeaholicguy/ai-devkit --skill agent-management -g -y

More Options

Use without installing

npx skills use codeaholicguy/ai-devkit@agent-management

指定 Agent (Claude Code)

npx skills add codeaholicguy/ai-devkit --skill agent-management -a claude-code -g -y

安装 repo 全部 skill

npx skills add codeaholicguy/ai-devkit --all -g -y

预览 repo 内 skill

npx skills add codeaholicguy/ai-devkit --list

SKILL.md

Frontmatter

{
    "name": "agent-management",
    "description": "AI DevKit · Manage running AI agents with ai-devkit agent commands. Use when an agent needs to identify itself, list agents, start workers, inspect agent detail, assign work, group agents, resume sessions, stop agents, or delegate work to other agents."
}

Agent Management

Use ai-devkit agent ...; if unavailable, use npx ai-devkit@latest agent ....

Workflow

List agents: ai-devkit agent list --json.
Identify self: compare your current session id to sessionId from list --json
Inspect before acting: ai-devkit agent detail --id <name> --json --tail 20.
Reuse idle agents when suitable; otherwise start one with agent start.
Send self-contained assignments. Track each agent's task and last instruction.
Verify completed work before reporting it done. Use $agent-communication for agent-to-agent updates.

Commands

ai-devkit agent list --json
ai-devkit agent detail --id <name> --json --tail 20
ai-devkit agent start --type codex --name <name> --cwd <path>
ai-devkit agent send --id <name> "<single-line instruction>"
ai-devkit agent send --id <name> --wait --timeout 120000 --json "<single-line instruction>"
ai-devkit agent send --group <group> "<single-line instruction>"
ai-devkit agent sessions --cwd <path> --type codex --json --limit 20
ai-devkit agent rename <old-name> <new-name>
ai-devkit agent kill <name>

Use exact names from list --json. Partial matches are convenient but risk sending work to the wrong agent.

Assignment Rules

Do not send instructions to yourself unless intentional.
Prefer task names like auth-review, ui-tests, or docs-pass.
Include objective, scope/files, constraints, validation command, expected output, and whether to stop or continue.
Assign non-overlapping files or sequence dependent work.
Use groups only for broadcasts that truly apply to every member.
Ask before killing agents you did not start, destructive actions, production/shared-system actions, or product decisions.

Example:

ai-devkit agent send --id auth-review "Review auth middleware in /repo. Do not edit files. Report security findings with file/line references, ranked by severity."