Write Sign in

← All tags

#anthropic

31 posts

Library 87.4k

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

JavaScript MIT Updated 6d ago
Julius Brussee · via GitHub 0 0
Library 59.4k

Open-source AI job search: scan job portals, score listings A-F, tailor your CV, track applications — runs locally in your AI coding CLI (Cl...

JavaScript MIT Updated 4h ago
Library 65.4k

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

TypeScript NOASSERTION Updated 4h ago
YeonGyu-Kim · via GitHub 0 0
Library 55.3k

Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Insta...

JavaScript CC0-1.0 Updated 22h ago
Ásgeir Thor Johnson · via GitHub 0 0
Library 58.2k

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Python Apache-2.0 Updated 4h ago
headroomlabs-ai · via GitHub 0 0
Library 227.9k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Code...

JavaScript MIT Updated 1d ago
Affaan Mustafa · via GitHub 0 0