# ironharness

> ironharness — cezman-ironharness. Use this tool when you need to safely interact with external devices and systems using protocols like serial, Modbus TCP, and MQTT, while maintaining a secure audit trail through a JSONL journal. It solves problems related to secure I/O operations and firmware benchmarking for LLM agents and firmware agents. Ideal for use cases involving device communication, testing, and validation, with inputs from various protocols and outputs to a secure audit journal.

Canonical page: https://skillsregistry.net/skills/cezman-ironharness  
JSON: https://api.skillsregistry.net/v1/skills/cezman-ironharness

## Description

Safe I/O harness for LLM agents: serial, Modbus TCP, MQTT, file sandbox and ESP32 flashing behind an MCP server, with a JSONL audit journal - plus ironbench, a pass@k benchmark for firmware agents on Wokwi/Renode/real hardware.

## Trust

- **Trust score (0–1):** 0.40
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/cezman/ironharness)

## 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": "cezman-ironharness"
    }
  }
}
```

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