Skip to main content

Multi-agent skill

Agent Management Skill

List, start, inspect, and assign work to running AI coding agents.

On this page

Install command

AI DevKit installs its built-in skills as one curated set. Run this once to install agent-management with the rest of the built-in workflow skills.

bash
npx ai-devkit@latest skill add --built-in

What it does

Use agent-management when one agent needs to coordinate others: list running agents, identify itself, start a worker, inspect what an agent is doing, and send it a self-contained assignment. It uses the ai-devkit agent commands and checks completed work before reporting it done.

When to use it

  • Delegate a scoped task to an idle agent or start a new worker
  • Inspect an agent's recent output before sending it more work
  • Split work across agents with non-overlapping files and clear validation steps

Supported agents

  • Claude Code
  • Codex
  • Gemini CLI
  • opencode
  • Pi

The SKILL.md file

This is what your agent reads when the skill runs. View it on GitHub (opens in a new tab)

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

Workflow#

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

Commands#

bash
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:

bash
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."
esc