# tokfold

> tokfold — ivanbbaev-tokfold. Use this tool when you need to reduce token costs for large language model (LLM) outputs, such as JSON data and logs, with a reversible and structure-aware context compression engine. It solves problems related to costly token usage, providing a deterministic and offline solution. Ideal for use cases where minimizing token expenses is crucial, such as in git-based workflows.

Canonical page: https://skillsregistry.net/skills/ivanbbaev-tokfold  
JSON: https://api.skillsregistry.net/v1/skills/ivanbbaev-tokfold

## Description

Reversible, structure-aware context compression engine for LLM agents (Rust) — cuts token cost of tool outputs, JSON and logs. Deterministic, sans-io, zero network.

## Trust

- **Trust score (0–1):** 0.80
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/IvanBBaev/tokfold)

## 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": "ivanbbaev-tokfold"
    }
  }
}
```

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