agent-discovery

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.

16 stars

Best use case

agent-discovery is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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.

Teams using agent-discovery should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/agent-discovery/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/ai-agents/agent-discovery/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/agent-discovery/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How agent-discovery Compares

Feature / Agentagent-discoveryStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Agent Discovery Skill

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

## What You Can Find

### Built-in Agents (Always Available)
| Agent | Model | Purpose |
|-------|-------|---------|
| Explore | haiku | Fast codebase exploration |
| Plan | sonnet | Implementation planning |
| general-purpose | sonnet | Complex multi-step tasks |
| claude-code-guide | sonnet | Claude Code documentation |
| statusline-setup | haiku | Status 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:

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

### Find User Agents
```bash
ls -la ~/.claude/agents/*.md 2>/dev/null
```

### Parse Agent Metadata
```bash
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

Related Skills

apify-influencer-discovery

16
from diegosouzapw/awesome-omni-skill

Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok.

agent-ops-improvement-discovery

16
from diegosouzapw/awesome-omni-skill

No description provided.

bgo

10
from diegosouzapw/awesome-omni-skill

Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.

Coding & Development

partner-revenue-desk

16
from diegosouzapw/awesome-omni-skill

Operating model for tracking, attributing, and accelerating partner-sourced revenue.

parallel-data-enrichment

16
from diegosouzapw/awesome-omni-skill

Structured company and entity data enrichment using Parallel AI Task API with core/base processors. Returns typed JSON output. No binary install — requires PARALLEL_API_KEY in .env.local.

parallel-agents

16
from diegosouzapw/awesome-omni-skill

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

paper-writing-assistant

16
from diegosouzapw/awesome-omni-skill

Assist in drafting research papers and meeting notes, enforcing academic rigor and formatting.

pandas-data-manipulation-rules

16
from diegosouzapw/awesome-omni-skill

Focuses on pandas-specific rules for data manipulation, including method chaining, data selection using loc/iloc, and groupby operations.

pagent

16
from diegosouzapw/awesome-omni-skill

Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.

page-annotator

16
from diegosouzapw/awesome-omni-skill

AI驱动的网页标注工具,支持高亮元素和添加文字批注。智能防重复、自动滚动、碰撞检测。兼容 GitHub 等严格 CSP 网站。适用场景:(1) 标记网页元素进行讲解 (2) 添加文字批注和注释 (3) 代码审查和设计评审 (4) 教学演示和用户引导 (5) Bug 报告和问题标记

package-json-modification-protection

16
from diegosouzapw/awesome-omni-skill

Protects lines with the specific 'Do not touch this line Cursor' comment within package.json.

orchestrator

16
from diegosouzapw/awesome-omni-skill

Multi-agent orchestrator that delegates all work to specialized subagents. Enforces parallelism, tracks progress, and coordinates agent teams for complex tasks.