# token-guard

> token-guard — zakenn-token-guard. Use this tool when you need to optimize Large Language Model (LLM) resource utilization in coding workflows, reducing token consumption and improving efficiency. The token-guard MCP server takes in coding tasks and outputs optimized LLM queries, integrating with git for seamless workflow management. Ideal for agentic coding applications where LLM token limits are a concern.

Canonical page: https://skillsregistry.net/skills/zakenn-token-guard  
JSON: https://api.skillsregistry.net/v1/skills/zakenn-token-guard

## Description

MCP server, written in Java 21 and compiled to a GraalVM native image, that reduces LLM token consumption in agentic coding workflows.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/ZakEnn/token-guard)

## 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": "zakenn-token-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zakenn-token-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zakenn-token-guard/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