# agentic-harness

> agentic-harness — frangelbarrera-agentic-harness. Use this tool when you need to manage and automate large language model (LLM) workflows with transparency and cost control. It solves problems related to auditable workflow management, cost optimization, and seamless integration with MCP servers. The agentic-harness takes in YAML playbooks and outputs controlled LLM workflows, making it ideal for use cases requiring reproducible and efficient language model deployments.

Canonical page: https://skillsregistry.net/skills/frangelbarrera-agentic-harness  
JSON: https://api.skillsregistry.net/v1/skills/frangelbarrera-agentic-harness

## Description

Open-source Python agent harness for auditable, cost-controlled LLM workflows with YAML playbooks and MCP server support.

## Trust

- **Trust score (0–1):** 0.39
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/frangelbarrera/agentic-harness)

## 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": "frangelbarrera-agentic-harness"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/frangelbarrera-agentic-harness` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/frangelbarrera-agentic-harness/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