# agentmd

> agentmd — doramirdor-agentmd. Use this tool when you need to audit and optimize your Claude Code agents, as it helps solve problems related to agent management and safety by providing a command-line interface to reduce, fix, and route agents, accepting Git inputs and producing optimized agent configurations as output. It is particularly useful for ensuring agent integrity and streamlining agent workflows. Use agentmd via CLI or MCP for safe and efficient agent management.

Canonical page: https://skillsregistry.net/skills/doramirdor-agentmd  
JSON: https://api.skillsregistry.net/v1/skills/doramirdor-agentmd

## Description

A check-up for your Claude Code agents — audit, reduce, fix, and route agents safely via CLI + MCP.

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/doramirdor/agentmd)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "doramirdor-agentmd"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/doramirdor-agentmd` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/doramirdor-agentmd/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt