# io.github.MukundaKatta/agentfit

> Use this tool when you need to optimize chat history for models with limited context budgets, as it truncates messages to fit within token limits. It solves the problem of information loss due to excessive chat history, ensuring relevant context is preserved. The tool takes in chat history and model context budgets as inputs, and outputs truncated messages that fit within the specified token limits.

Canonical page: https://skillsregistry.net/skills/io-github-mukundakatta-agentfit  
JSON: https://api.skillsregistry.net/v1/skills/io-github-mukundakatta-agentfit

## Description

Token-aware message truncation: fit a chat history into your model's context budget.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 0.1.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.MukundaKatta%2Fagentfit)
- **Repository:** <https://github.com/MukundaKatta/agentfit-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": "io-github-mukundakatta-agentfit"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-mukundakatta-agentfit` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-mukundakatta-agentfit/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