# tokenbrake

> tokenbrake — willbgreen777-tokenbrake. Use this tool when you need to prevent unexpected AI costs by monitoring and controlling AI API calls. Tokenbrake solves the problem of runaway AI agents by hard-stopping them within 10 seconds, saving you from excessive bills. It takes AI API call metrics as input and outputs hard-stop controls to prevent financial losses.

Canonical page: https://skillsregistry.net/skills/willbgreen777-tokenbrake  
JSON: https://api.skillsregistry.net/v1/skills/willbgreen777-tokenbrake

## Description

A circuit breaker for your AI bill. Meters every AI API call on your machine and hard-stops a runaway agent in ~10 seconds — before the money is gone, not after the invoice.

## Trust

- **Trust score (0–1):** 0.23
- **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/willbgreen777/tokenbrake)

## 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": "willbgreen777-tokenbrake"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/willbgreen777-tokenbrake` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/willbgreen777-tokenbrake/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