Skip to content
TakoAPI
Back to skills

agent-registry

by matrixy

AI & LLMs
2.1kDownloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

MANDATORY agent discovery system for token-efficient agent.

Description

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

INPUT

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

AGENT
  1. 1

    Run search.js with keywords extracted from the request: bun bin/search.js "code review security authentication"

  2. 2

    Review relevance scores in results to identify best-matching agent

  3. 3

    Load the top-scoring agent's full instructions: bun bin/get.js security-auditor

  4. 4

    Follow 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

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

Installation

clawhub install matrixy/agent-registry

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links