# token_save_mcp

> token_save_mcp — habartru-token-save-mcp. Use this tool when you need to optimize file reading in coding tasks, reducing context burn by 87-99% per call. It delegates large file reads to a cost-effective worker model, returning only the necessary answer, and can be integrated into various clients, including Claude Code. Ideal for use cases involving frequent or large file reads, such as git operations.

Canonical page: https://skillsregistry.net/skills/habartru-token-save-mcp  
JSON: https://api.skillsregistry.net/v1/skills/habartru-token-save-mcp

## Description

Stop your coding agent burning context on file reads. Delegates big reads to a cheap worker model and returns only the answer — 87-99% saved, measured per call. A hook enforces it in Claude Code; the MCP tools work in any client.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/Habartru/token_save_mcp)

## 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": "habartru-token-save-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/habartru-token-save-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/habartru-token-save-mcp/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