# tokencut

> tokencut — 00200200-tokencut. Use this tool when you need to simplify and optimize AI-generated code, reducing verbosity and improving readability. Tokencut solves problems of overly complex coding output by providing targeted reads, output budgets, and recoverable context for Claude Code and Codex. It takes in AI-generated code as input and outputs refined, concise code through a local CLI and MCP server interface.

Canonical page: https://skillsregistry.net/skills/00200200-tokencut  
JSON: https://api.skillsregistry.net/v1/skills/00200200-tokencut

## Description

Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.

## Trust

- **Trust score (0–1):** 0.53
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/00200200/tokencut)

## 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": "00200200-tokencut"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/00200200-tokencut` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/00200200-tokencut/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
