Warddamn

Tiny Tools — Data skill for Claude Code

Data community

Small, local-first MCP tools that let AI agents know things about files without reading them.

How to install Tiny Tools

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Warddamn/tiny-tools and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Tiny Tools does

Small, local-first MCP tools that let AI agents know things about files without reading them. tiny-context: outline, search, slice, SQL, log clusters, diffs, validation, extraction for PDF/DOCX/PPTX/XLSX and more.

Alternatives in Data

README

tiny-tools

Small, local-first tools that AI agents install with one config line and *actually use* to cut their time and token spend — starting with **`tiny-context`**, an MCP server that lets an agent know things about files (PDF, DOCX, XLSX, CSV, logs, code) without reading them.

[![npm version](https://img.shields.io/npm/v/@tinytools/context)](https://www.npmjs.com/package/@tinytools/context) [![npm downloads](https://img.shields.io/npm/dw/@tinytools/context)](https://www.npmjs.com/package/@tinytools/context) [![CI](https://github.com/Warddamn/tiny-tools/actions/workflows/ci.yml/badge.svg)](https://github.com/Warddamn/tiny-tools/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/Warddamn/tiny-tools/blob/main/LICENSE) [![Install in Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en/install-mcp?name=tiny-context&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIi1wIiwiQHRpbnl0b29scy9jb250ZXh0IiwidGlueS1jb250ZXh0LW1jcCJdfQ%3D%3D) [![Install in VS Code](https://img.shields.io/badge/VS_Code-Install_Server-0098FF)](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522tiny-context%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522-y%2522%252C%2522-p%2522%252C%2522%2540tinytools%252Fcontext%2522%252C%2522tiny-context-mcp%2522%255D%257D)

**Before → after, measured on this repo's fixtures** (read both columns together — the first is the ceiling, the second is what a capable coding agent actually gains):

vs. reading whole files vs. a shell-capable agent
17 tasks · 7,415,930 naive tokens → 9,169 tool tokens · 99.9% saved same answers, ~20% fewer tokens, ~50% less time
what an agent pays when it Reads / cats the file, or cannot open a PDF/DOCX/XLSX at all headless Claude Code with Bash/Read/Grep/Glob, 12 tasks, with vs. without the tools

Method and full tables: [Benchmark