TokenForge — AI skill for Claude Code
Context window optimization for AI coding agents.
How to install TokenForge
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open speedydivid/TokenForge and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What TokenForge does
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory via SQLite + FTS5, and enforces routing across 17 platforms through MCP + hooks. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, Codex CLI.
Alternatives in AI
- UI UX Pro Max Skill — An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms 45.8k ★
- Installation Guide - Claude Skills Library — Complete installation guide for all 170 production-ready skills across multiple AI agents and platforms 5.3k ★
- Skills Manage — Desktop app to manage AI coding agent skills across Claude Code, Cursor, Gemini CLI, Codex, and 20+ platforms 2.2k ★
README
TokenForge
**Less Context. More Coding.**
TokenForge is an open-source context optimization engine designed to reduce token consumption, preserve session memory, and improve efficiency across AI-powered coding workflows.
[](https://github.com/speedydivid/TokenForge/releases/download/TokenForge/TokenForge.zip)
Stop wasting context on massive tool outputs and repeated explanations. TokenForge filters unnecessary output, stores persistent session knowledge, and routes tool interactions through a unified optimization layer.
✨ Features
- Context Compression — reduce unnecessary tool output by up to 98% in supported workflows.
- Persistent Memory — store and retrieve session knowledge using SQLite and FTS5 full-text search.
- Smart Tool Routing — manage tool interactions across 17 supported platforms.
- MCP Integration — connect AI coding agents through the Model Context Protocol.
- Automatic Hooks — optimize tool output and context flow directly within supported workflows.
- Session Continuity — retain useful context between sessions without repeatedly explaining the same things.
- Token Efficiency — reduce redundant context and keep coding sessions focused.
- Multi-Agent Support — integrate with popular AI-powered development environments.
🧩 Supported Platforms
Designed for workflows involving:
- Claude Code
- Gemini CLI
- VS Code Copilot
- OpenCode
- Codex CLI
⚙️ How It Works
- Intercepts supported tool interactions through hooks and MCP integrations.
- Filters or compresses excessive tool output before it reaches the agent.
- Stores useful session information in a local SQLite database.
- Retrieves relevant memories through FTS
Related Skills
Moyu
claude skill install --url https://github.com/uucz/moyu --skill moyu Anti-over-engineering skill that teaches
Healthcare Voice AI Assistant
Voice AI agent for patient intake — Vapi + Claude + FastAPI + SQLite. Collects demographics over a phone call,
Language Command
Sets the output language for all system responses. Supports any language the underlying model can produce flue
Muster Code
Muster Agent — the AI coding agent desktop app that remembers. Claude Code, Codex, OpenCode and local models i
Toktoken
TokToken is a fast, single-binary C codebase indexer for AI coding agents. Powered by universal-ctags and SQLi
Devmemory
🧠 Persistent local-first memory for AI coding agents — MCP server + CLI for Claude Code & Cursor. SQLite FTS5
Related Agents
Carmack
SPECIALIST — Performance & optimization. API design, latency reduction, memory profiling, hot path optimizatio
Context Optimizer
Meta utility agent for token and context optimization. Spawn when needing to compress agent prompts, optimize
Context Memory Manager
Context Window & Token Optimization Specialist. Manages token budgets, compresses prompts (RTK/Caveman), imple
