chopratejas — 3 Open-Source AI Agent Skills

chopratejas is the author of 3 open-source AI agent skills and MCP servers spanning mcp-server, uncategorized, agent-tool, with a combined 44,384+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 62/100) and security-graded — 3 verified safe.

Top skills by chopratejas

• headroom — Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. (44.4k★ · quality 63/100 · security: safe)
• invalidate — The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev. (23★ · quality 57/100 · security: safe)
• tokview — See where your LLM tokens actually go — down to the individual tool call. A small, local, zero-config proxy + dashboard for token/cost track (5★ · quality 65/100 · security: safe)

View chopratejas on GitHub · Explore audited agent skills