LaunchKit · 2026
Back to Skills

agent-registry

AI & LLMsv2.0.1

MANDATORY agent discovery system for token-efficient agent.

0
2.1k downloads
by @matrixy

Setup & Installation

openclaw skills install @matrixy/agent-registry

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install agent-registry

Version History

v2.0.1Feb 15, 2026 - Version note by skill developer:

agent-registry v2.0.1 - Migrated all CLI scripts from Python to faster Bun/JavaScript implementations. - Introduced user prompt hook for agent search (integrated with Claude's plugin system). - Enhanced install process: optional dependency install for improved UI, Bun-first workflow, Python no longer required. - Added modern interactive migration UI using @clack/prompts (with fallback to basic text selection). - Updated docs and commands to reflect new Bun-based CLI; all registry operations via `bun bin/*.js`.

What This Skill Does

Agent Registry is a lazy-loading discovery system for Claude Code agents. Instead of loading all agents upfront, it indexes them and loads only what's needed for a given task. Reduces context window usage by roughly 95% compared to loading all agents at startup.

Avoids the ~16k token overhead of loading all agents upfront by indexing them and fetching only the ones relevant to each task.

When to use it

  • Finding the right specialized agent for a code review task
  • Listing all available agents when starting a new project
  • Loading a security auditor agent on demand for vulnerability checks
  • Migrating existing ~/.claude/agents/ files into the registry
  • Running complex multi-step workflows without hitting token limits

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Can you review my authentication code for security issues?

AGENT
  1. 1Run search.js with keywords extracted from the request: bun bin/search.js "code review security authentication"
  2. 2Review relevance scores in results to identify best-matching agent
  3. 3Load the top-scoring agent's full instructions: bun bin/get.js security-auditor
  4. 4Follow the loaded agent's instructions to perform the security review
OUTPUT

Security audit of the authentication code using the loaded agent's specialized instructions

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

Bun runtime (ships with Claude Code, no separate install needed)