# TokenJar

> TokenJar — farukes-tokenjar. Use this tool when you need to optimize token usage in AI coding assistants, reducing costs by 70-95% through advanced techniques like AST skeletons and differential caching, with seamless integration via git. It solves token overage problems and optimizes code generation for Claude Code, Cursor, Antigravity, and Windsurf. Ideal for large-scale AI coding projects where token efficiency is crucial.

Canonical page: https://skillsregistry.net/skills/farukes-tokenjar  
JSON: https://api.skillsregistry.net/v1/skills/farukes-tokenjar

## Description

Zero-cost token optimization engine for AI coding assistants (Claude Code, Cursor, Antigravity, Windsurf). Saves 70-95% tokens via AST skeletons, differential cache, and line slicing.

## 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:** 2026-09-26

## Source

- **Source listing:** [GitHub](https://github.com/Farukes/TokenJar)

## 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": "farukes-tokenjar"
    }
  }
}
```

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