lidge-jun — 9 Open-Source AI Agent Skills

lidge-jun is the author of 9 open-source AI agent skills and MCP servers spanning codex-skill, mcp-server, claude-skill, with a combined 18,922+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 64/100) and security-graded — 9 verified safe.

Top skills by lidge-jun

• opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, an (18.3k★ · quality 70/100 · security: safe)
• agbrowse — Ultimate browser automation toolkit for AI agents. Zero MCP token tax, JS evaluate, vision-click with DPR correction. (231★ · quality 65/100 · security: safe)
• cli-jaw — 🦈 2-line install personal AI assistant. 11 AI runtime surfaces (Claude, Codex, Cursor, Gemini, Grok, Antigravity, OpenCode, Copilot), 200+ (208★ · quality 67/100 · security: safe)
• aside-codemode — One call where Aside used to spend fifty — rg-backed search, Aside-shaped file tools, and batched browser work inside a single sandboxed Jav (129★ · quality 72/100 · security: safe)
• codexclaw — Development discipline + multi-model subagents for OpenAI Codex — 13 dev skills, PABCD workflow, repo map, recall, skill search. Single plug (49★ · quality 67/100 · security: safe)
• aside-skill — Codex skill for driving the Aside browser CLI without triggering unrecoverable hangs (11★ · quality 63/100 · security: safe)
• claude-e — PTY-backed claude -p-style executor for Claude Code, packaged as the claude-e npm CLI (8★ · quality 72/100 · security: safe)
• agent-sync — Sync MCP, skills, and AGENTS.md across all AI coding agents (Claude, Codex, Copilot, Gemini, Antigravity, OpenCode) (2★ · quality 47/100 · security: safe)

View lidge-jun on GitHub · Explore audited agent skills