# luna-agents

> luna-agents — lunaos-ai-luna-agents. Use this tool when you need to create complex AI workflows and audit honesty in AI outputs, leveraging a concatenative shell language with 358 verbs and features like evidence-weighted voting swarms. It solves problems in AI development, auditing, and decision-making, accepting code and data as inputs and producing executable workflows and audit reports as outputs. Ideal for use in local development environments, particularly with git version control.

Canonical page: https://skillsregistry.net/skills/lunaos-ai-luna-agents  
JSON: https://api.skillsregistry.net/v1/skills/lunaos-ai-luna-agents

## Description

Luna Pipes: a concatenative AI shell language. 358 verbs composed via >>. AI honesty auditor (/ll-no-bluf), agent scaffolder, 21 stack-aware doctors, evidence-weighted voting swarm. Claude Code plugin. MIT. Runs locally.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## 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/lunaos-ai/luna-agents)

## 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": "lunaos-ai-luna-agents"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lunaos-ai-luna-agents` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lunaos-ai-luna-agents/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