Synthelion — AI skill for Claude Code
Synthelion compresses prompts before they reach any AI model — cutting token usage by up to 70%, reducing API costs, and speeding up responses.
How to install Synthelion
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open francescopaolopassaro/Synthelion and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Synthelion does
Synthelion compresses prompts before they reach any AI model — cutting token usage by up to 70%, reducing API costs, and speeding up responses. It works with any agent or framework: Claude Code, OpenAI, LangChain, OpenCode, Cursor, and more.
Alternatives in AI
- Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
- Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
- Token Monitor — Local-first desktop widget for tracking token usage, costs, and limits across 32+ AI coding tools—including Cl 1.8k ★
README
Synthelion — Universal Token Compressor and Prompt Manager for AI Agents
[](https://pypi.org/project/synthelion/) [](https://pypi.org/project/synthelion/) [](https://opensource.org/licenses/MIT) [](https://github.com/francescopaolopassaro/synthelion/stargazers) [](https://modelcontextprotocol.io)
Synthelion compresses prompts before they reach any AI model — cutting token usage by up to 70%, reducing API costs, and speeding up responses. It works with **any agent or framework**: Claude Code, OpenAI, LangChain, OpenCode, Cursor, and more.
Supports 50+ languages out of the box. No AI model required. No configuration.
"Why use many tokens when few tokens do trick?" — A caveman (and your wallet).
Table of contents
- Why Synthelion?
- Privacy & Security — PrivacyGuard
- EnterpriseGuard — outbound data-loss-prevention firewall
- Synthelion vs other prompt/context-compression tools
- Quick install — one command
- Install (manual)
- Update
- Set up on Claude Code
- [Automatic prompt compression — Claude Code hook](#automatic-prompt-compress
Related Skills
Image Read Cache
Agent Skill that caches LLM image descriptions as XMP metadata inside image files, reducing token usage by ~92
Local Secure Prompt Agent
Browser extension that redacts PII (emails, phone numbers, Aadhaar/PAN, API keys, names, locations) from promp
Furl Ctx
Context compression for AI agents — cut token usage costs with retrievable CCR compression. Rust core + Python
Token Proxy
Local AI API gateway for OpenAI / Gemini / Anthropic. Runs on your machine, keeps tokens counted (SQLite), off
Tokenmeter
htop for AI Agents — monitor token usage, costs & tool calls across Claude Code and Codex in real time
Cc Token Status
new macOS menu bar dashboard for Claude Code. Shows plan usage limits, costs, tokens, trends, model breakdown,
Related Agents
API Cost Scanner
Scans codebase for AI/API cost optimization opportunities including model usage, token estimates, caching stra
Stats Analyzer
Analyzes ~/.claude/stats-cache.json and history.jsonl to produce a concise usage report with model token break
Context Memory Manager
Context Window & Token Optimization Specialist. Manages token budgets, compresses prompts (RTK/Caveman), imple
