Skip to content

diegosouzapw/awesome-omni-skill / skills/ai-agents/agent-discovery

agent-discovery

Verified

Discovers all Claude Code agents in the system including built-in, plugin, project, and user-level agents. Use when you need to find which agents are available, understand the agent ecosystem, or prepare agents for Actoris registration.

Agent Discovery Skill

Use this skill to discover and catalog all Claude Code agents.

What You Can Find

Built-in Agents (Always Available)

AgentModelPurpose
ExplorehaikuFast codebase exploration
PlansonnetImplementation planning
general-purposesonnetComplex multi-step tasks
claude-code-guidesonnetClaude Code documentation
statusline-setuphaikuStatus line configuration

Custom Agent Locations

  1. Project Agents: .claude/agents/*.md
  2. User Agents: ~/.claude/agents/*.md
  3. Plugin Agents: {plugin-root}/agents/*.md

Agent File Format

Custom agents are Markdown files with YAML frontmatter:

---
name: my-agent
description: What this agent does and when to use it
tools: Read, Write, Bash  # Comma-separated
model: sonnet  # sonnet, opus, haiku, or inherit
skills: skill1, skill2  # Optional
---

# Agent Instructions

Your agent prompt goes here...

Discovery Commands

Find Project Agents

ls -la .claude/agents/*.md 2>/dev/null

Find User Agents

ls -la ~/.claude/agents/*.md 2>/dev/null

Parse Agent Metadata

grep -A 5 "^---" .claude/agents/my-agent.md | head -10

MCP Integration

Use the Actoris MCP tool for structured discovery:

list_claude_code_agents(source="all", detailed=true)

Returns JSON with:

  • Total agent count by source
  • Agent name, description, tools, model
  • File path for custom agents

After Discovery

Once agents are discovered, they can be:

  1. Registered with Actoris via register_agent_with_actoris
  2. Monitored for trust scores
  3. Tracked in the Darwinian leaderboard
  4. Included in AGDP calculations
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall