23,556 tagged Building agents, measured the same way as everything else here.
Browse within: agentic-ai 233LLM 217agent 200agents 151skills 145agentic-workflow 110agent-orchestration 86openai 86antigravity 79agentic-framework 73cli 73ai-skills 71Autonomous Agents 67agent-framework 63
Skill Claude CodeCodex
Scaffold production-ready Claude Code skills from a one-sentence description. Use when creating a new skill, bootstrapping a skill project, or turning an idea into a published skill. Generates SKILL.md, README.md, and domain-specific templates with best practices baked in.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Scans a project's current practice, classifies each convention by how it is best enforced, and routes it to the fittest mechanism - config, project doc, rule, a project skill, or a paste-ready pointer. Use when setting up an existing project so the first agent execution follows its conventions, or when asked to…
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude Code
Use when you need to send a message to another Claude Code agent, broadcast to all agents, or when you receive a message prefixed with [@agentName]. Covers terminal injection via TIOCSTI, pts discovery, message format, and kill switch.
mengqiuzhen/claude-code-skills
Skill Claude CodeCodex
Bridge between CLI Claude Code and VSCode Claude Code on the same Windows machine. Use when the user needs to: read what VSCode Claude last said, send commands to VSCode Claude, check if VSCode Claude is busy/idle, or coordinate between the two Claude instances. Triggers: "what did vscode claude say", "send to vscode…
ling-ling-luo/claude-code-skills
Skill Claude Code
Run dual Claude Code sessions with Worker (executes tasks) and Supervisor (makes decisions, reviews). Use when user wants "two Claude sessions", "supervisor-worker pattern", "decision maker and executor", "code review workflow", or "collaborative AI agents".
Skill Claude CodeCodex
Audit agent-facing documentation (CLAUDE.md, AGENTS.md, copilot-instructions.md) for redundancies, contradictions, gaps, and misplaced content. Supports Claude Code, OpenAI Codex, and GitHub Copilot. For a general agent's system prompt, persona, or tool descriptions (not repo docs), use audit-agent-prompt. Use when…
Skill Claude CodeCodex
Caravo is the first service marketplace built for autonomous AI agents — featuring 200+ ready-to-use services across categories: AI Models, Search, Data & Analytics, Finance, Social Media, Communication, eCommerce, Cloud & Infrastructure, Digital Assets, Utilities, and more. Caravo provides access to premium and…
paulo-yamagishi/claude-code-setup
Skill Claude Code
Auto-maintain Claude Code config files as your codebase evolves.
Skill Claude CodeCodex
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
joseph27/claude-code-token-save
Skill Claude CodeCodex
Toggle token-save mode on/off. When ON, skills use cheaper models (Haiku/Sonnet) for subagents. When OFF, everything uses Opus. Usage: /token-save, /token-save on, /token-save off, /token-save status, /token-save routing.
Skill Claude CodeCodex
Drive an async Claude Code chain — investigate the next slice, run confirm-understanding at a configurable threshold (default 95%), auto-fire via RemoteTrigger if confidence clears, otherwise ping the user. Use when the user has explicitly authorized auto-fire mode (Pattern B+) and asks for the next slice in a chain.
Skill Claude CodeCodex
Use codex/codex-reply as a persistent second-engineer thread for non-trivial uncertainty — design choices, risky implementation decisions, debugging when stuck, review, spec ambiguity, needing a current/authoritative websearch, or any point where you'd otherwise guess. Keep one thread and iterate; don't treat the…
Skill Claude CodeCodex
Capability layer. For identity see AGENT.md, for permissions see POLICY.md.
PatrickJaiin/claude-code-connect
Skill Claude Code
Put this Claude Code session into listener (child) mode so another session can connect to it with /connect, read a summary of this session, send it prompts, and read its replies. Use when the user runs /listen.
jidechao/Wechat-ClaudeCode-Skill
Skill Claude CodeCodex
A bridge between a personal WeChat account and Claude Code, so conversations can happen through WeChat. It supports text, images, permission approvals, and slash commands on macOS.
Skill Claude Code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Use when working in this plugin marketplace repository — adding plugins, updating skills or hooks, editing marketplace config, syncing versions, or making any code changes.
Skill Claude Code
Orchestration harness for iterative delivery. Runs a Plan→Implement→Evaluate→Analyze loop with locked rubric, failure routing, optional cron scheduling, and trace emission for skill evolution. Pure orchestration — no domain knowledge. Auto-detects delivery vs workflow improvement. Plans parallel implementation lanes…
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude Code
Orchestrates task delegation to Codex via MCP bridge. Automatically selects the right tool, sandbox mode, and output format based on the task type.
Skill Claude CodeCodex
Drive the code-oz agentic SDLC runtime to build or fix code with enforced gates and cross-family review. Use when the user asks to build, implement, or fix something in a code repository and wants gated, reviewed delivery rather than ad-hoc edits.
finml-sage/agent-swarm-protocol
Skill Claude CodeCodex
You are a Claude subagent participating in an Agent Swarm Protocol network. You process incoming messages from other agents and respond appropriately.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: