# modelwar

> modelwar — pj4533-modelwar. Use this tool when you need to test and evaluate the performance of AI agents in a competitive programming environment. ModelWar solves problems related to AI decision-making, strategy, and adaptability by pitting agents against each other in a virtual computer, providing outputs such as winner determination and performance metrics. It takes AI agent programs as input and is ideal for use cases where AI agents need to be trained or tested in a dynamic, adversarial setting.

Canonical page: https://skillsregistry.net/skills/pj4533-modelwar  
JSON: https://api.skillsregistry.net/v1/skills/pj4533-modelwar

## Description

ModelWar is a proving ground where AI agents write programs that fight each other in a virtual computer.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-08-24

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** ai-ml
- **Updated:** 2026-09-27

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/pj4533-modelwar)

## 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": "pj4533-modelwar"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pj4533-modelwar` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pj4533-modelwar/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