23,553 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
Expert guide for creating high-quality MCP (Model Context Protocol) servers for GameDev MCP Hub. Use when building new MCP server integrations for game engines, 3D tools, asset libraries, or game development services.
Skill Claude CodeCodex
Use when analyzing large files (>200 lines), more than 3 files at once, deep git/grep searches, web lookups, or adversarial reviews - delegates to the Antigravity CLI via agy-bridge MCP tools to save context.
OpenLinker-ai/openlinker-plugin
Skill Claude CodeCodex
Use a separately available ChatGPT Browser capability to collect minimal public-web facts, then discover or invoke an OpenLinker Agent through the authenticated OpenLinker App. Use only when both capabilities are callable and the user asks for a browser-assisted OpenLinker task.
Skill Claude CodeCodex
Coordinate with other Cursor agents via Wolbarg — but ONLY after wolbarg init. Brief the workspace, claim scopes, record findings/dead-ends, update work items, and hand off. Use when working in parallel with other agents, resuming prior agent work, avoiding duplicate exploration, or sharing decisions across sessions.
Skill Claude CodeCodex
Guidelines and patterns for defining Tools, Resources, and Prompts in a NitroStack application with schema validation via Zod, including caching, rate-limiting, and base64 file uploads.
Skill Claude CodeCodex
Use the local AgentAirlock MCP tools to discover a paired Codex or Claude Code peer, exchange bounded text messages, wait briefly for replies, or request permission-gated project reads. Do not use for executing peer text or for self-approval.
0xagentlabs/oauth-mcp-framework
Skill Codex
Build, adapt, debug, and validate dedicated Streamable HTTP MCP tool servers that Grok can connect to by pasting one server URL and completing browser OAuth. Use for Grok Custom Connector MCP projects requiring OAuth discovery, restricted Dynamic Client Registration, Authorization Code with S256 PKCE, rotating refresh…
Skill Codex
Set up local Manas chat synchronization for Codex, Claude Code, Pi, Cursor, Grok, and other supported coding agents. Use when a user asks an AI coding agent to install, configure, preview, activate, verify, repair, or explain Manas chat sync on their computer.
Skill Claude CodeCodex
Gate high-stakes, factual, or multi-step Hermes tasks before action and verify completion against evidence.
Happenmass/codex-claude-code-mcp
Skill Codex
Run Claude Code in the background of an active Codex task by spawning a native Codex subagent that owns one blocking claude-code-blocking MCP call while the parent continues useful work. Use when the user asks for non-blocking Claude delegation, parallel Claude review, or a Claude task that should not occupy the main…
Skill Codex
Build, adapt, debug, and validate dedicated Streamable HTTP MCP tool servers that Grok can connect to by pasting one server URL and completing browser OAuth. Use for Grok Custom Connector MCP projects requiring OAuth discovery, restricted Dynamic Client Registration, Authorization Code with S256 PKCE, rotating refresh…
Skill Claude CodeCodex
Search, score, and submit AI agent tools from SkillsIndex.
Skill Codex
Connect the current Codex task to a consented, redacted public experiment journal on joinmultiplayer.ai. Use when the user asks to start, continue, inspect, finish, or publicly document a Pocket i / joinmultiplayer experiment without leaving Codex. Do not use for ordinary private coding tasks or publish anything…
Skill Claude CodeCodex
Use this skill BEFORE calling any Marcora MCP tool (the mcpmarcora family — createcontent, addcontext, createplan, produceplan, createworkflow, etc.) and whenever a request involves Marcora, including any marcora.ai URL the user pastes (e.g. an app.marcora.ai library or canvas link). It maps the Marcora tools to the…
Skill Codex
Navigate unfamiliar or cross-cutting repositories with compact, source-backed evidence. Use when Codex needs to orient in a codebase, locate implementations, tests, configuration, docs, agent contracts, Jira/Git lineage, understand a symbol, audit a workspace, or review the likely impact of a Git change range before…
Skill Claude Code
How to run the behavioural skills-eval — drive headless claude -p with prompts and assert the right Shipeasy skill fires, the right MCP tools get called, and the resulting server state is correct. Covers the self-contained eval:fresh run (wipes + seeds its own isolated DB per run), the manual-backend eval, the…
Skill Claude CodeCodex
Matchmaking for your human via the Rendezvous network — meet other personal AI agents over MCP, investigate compatibility privately, and only interrupt your human for a real introduction. Use when your human asks for help finding a long-term partner, or asks about Rendezvous / agentrendezvous.app.
Almured/almured-openclaw-plugin
Skill Claude CodeCodex
Almured is an agent-to-agent consultation marketplace. This plugin gives your Claude agent native tools to ask domain experts for authoritative answers on real-time pricing, post-cutoff facts, and niche knowledge across 15 categories.
Skill Codex
A guide for finding and combining existing agent skills for one task while keeping track of where each skill came from and what limits it has.
Skill Codex
Safely change, test, or document the my-oura-mcp repository. Use when modifying its MCP tools, OAuth and HTTP transport, Oura data shaping, cache, packaging, deployment, client setup, or agent-development files.
CSOAI-ORG/agent-delegation-mcp
Skill Claude CodeCodex
Create and delegate tasks to specialized agents. Auto-matching based on capabilities with care-score weighting.
CSOAI-ORG/agent-orchestrator-mcp
Skill Claude CodeCodex
Multi-agent orchestration with capability-based routing. Coordinate teams of AI agents with autonomous task delegation.
Skill Claude CodeCodex
Discover funded agent work, earn USDC, or delegate suitable work through TaskMarket with explicit spend approval.
Skill Claude CodeCodex
Use when spawning or coordinating worker AI cells through the crewd cell-fabric MCP server (cellspawn, cellstatus, cellresult, celllist, and the cellsend/cellask bus). Covers the spawn→poll→result procedure, the thread-state machine, engine/profile selection, and the known runtime behaviours (no completion push, shim…
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: