Agent Management

Agent Management is an AI Engineering skill for Claude Code, published by codeaholicguy in ai-devkit.

1.6K stars242 forkson codeaholicguy/ai-devkitAdded 2026/08/19Repository updated 2026/08/18

agent-frameworkagent-skillsaiai-agentsai-codingantigravityclaude-codeclicodex-clicoding-agentscursor-aideveloper-toolsgemini-climcpmemoryopencodepisoftware-engineeringworkflow-automation

Install in seconds

Install Agent Management

Copy Agent Management into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/codeaholicguy/ai-devkit/tree/main/skills/agent-management ~/.claude/skills/agent-management

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/codeaholicguy/ai-devkit.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/agent-management/SKILL.md in codeaholicguy/ai-devkit
Installs to: ~/.claude/skills/agent-management
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Agent Management does

Agent Management uses ai-devkit agent commands to list, start, inspect, assign work to, and stop AI agents. Use it when an agent needs to identify itself, manage other agents, or delegate tasks.

Agent Management is cataloged under AI Engineering on DirSkills. Agent Management comes from a repository tagged agent-framework, agent-skills, ai, ai-agents and ai-coding.

Documentation

README

Excerpt

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

This is the opening of the README. Read the full README on GitHub.

Commands Agent Management provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/repo

Frequently asked about Agent Management

What else does codeaholicguy publish alongside Agent Management?
Agent Management is one of 25 skills that DirSkills catalogs from codeaholicguy/ai-devkit, the repository it ships in. Its siblings there include Agent Communication, Agent Orchestration and Brainstorm. Each one is a separate skill with its own page in this directory, installs the same way Agent Management does, and is maintained by codeaholicguy in that same repository. The rest of the collection is listed on the codeaholicguy/ai-devkit page.
How does Agent Management compare to other AI Engineering skills?
Agent Management ranks #956 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Management against them. Open each page to compare what they document and how they install.