code-yeongyu — 20 Open-Source AI Agent Skills
code-yeongyu is the author of 20 open-source AI agent skills and MCP servers spanning claude-skill, codex-skill, mcp-server, agent-tool, with a combined 71,295+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 60/100) and security-graded — 6 verified safe.
Top skills by code-yeongyu
- oh-my-openagent — omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode (68.1k★ · quality 65/100 · security: safe)
- lazycodex — The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex. (3.2k★ · quality 62/100 · security: safe)
- codex-lsp — Codex plugin that exposes Language Server Protocol diagnostics and MCP tools (19★ · quality 72/100 · security: safe)
- pi-lsp-client — Language Server Protocol integration for the pi coding agent. Faithful port of the LSP tools from oh-my-openagent: shared server pool, refCo (13★ · quality 73/100 · security: caution)
- pi-nested-agents-md — Nested AGENTS.md context injection for pi-mono coding-agent — ported from omo (oh-my-openagent). Walks up from any read file, injects nearby (9★ · quality 72/100 · security: safe)
- lsp-tools-mcp — Standalone Language Server Protocol tools exposed as a stdio MCP server. Consumed by codex-lsp and oh-my-openagent. (7★ · quality 60/100)
- pi-websearch — Provider-backed web search tool for pi-coding-agent with config-gated activation, TUI status, and source-aware results. (6★ · quality 70/100 · security: safe)
- pi-webfetch — Web fetch tool extension for the pi coding agent (5★ · quality 71/100 · security: safe)
View code-yeongyu on GitHub · Explore audited agent skills