# tokenguard

> Use this tool when you need to monitor and control API costs for AI agents, solving problems of unexpected expense overruns and optimizing resource allocation. Tokenguard provides an interface to track and manage API usage, accepting input parameters such as cost thresholds and agent IDs, and outputting alerts and usage reports. It is particularly useful in contexts where AI agents rely heavily on external APIs, ensuring cost-effective and efficient operation.

Canonical page: https://skillsregistry.net/skills/g0head-tokenguard  
JSON: https://api.skillsregistry.net/v1/skills/g0head-tokenguard

## Description

API cost guardian for AI agents.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** ai-ml
- **Updated:** 2026-05-15

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/g0head-tokenguard)

## 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": "g0head-tokenguard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/g0head-tokenguard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/g0head-tokenguard/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