# token-manager

> token-manager — kelegele-token-manager. Use this tool when you need to monitor and optimize language model usage across multiple platforms, including Kimi, OpenAI, and Anthropic, to reduce costs and improve resource allocation. It provides usage tracking and cost-saving recommendations, taking in usage data and outputting actionable insights. Ideal for managing large-scale language model deployments, this tool helps streamline expenses and inform strategic decision-making.

Canonical page: https://skillsregistry.net/skills/kelegele-token-manager  
JSON: https://api.skillsregistry.net/v1/skills/kelegele-token-manager

## Description

Universal LLM Token Manager - Monitor usage and provide cost-saving recommendations for Kimi, OpenAI, Anthropic.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/kelegele-token-manager)

## 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": "kelegele-token-manager"
    }
  }
}
```

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