# TokenPilot

> Use this tool when you need to optimize token usage in Claude Code and extend session duration. TokenPilot automates token optimization, reducing waste across effort tuning, file reads, and task classification, to improve overall efficiency. It takes in Claude Code sessions as input and outputs optimized token configurations, making it ideal for use cases where token conservation is crucial.

Canonical page: https://skillsregistry.net/skills/rish-e-tokenpilot  
JSON: https://api.skillsregistry.net/v1/skills/rish-e-tokenpilot

## Description

Automatic token optimization for Claude Code that extends session duration by reducing wasted tokens across effort tuning, file reads, tool cost, context health, and task classification.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/q0h22egkyj)
- **Repository:** <https://github.com/rish-e/tokenpilot>

## 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": "rish-e-tokenpilot"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rish-e-tokenpilot` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rish-e-tokenpilot/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