23,553 tagged Building agents, measured the same way as everything else here.
Browse within: agentic-ai 231LLM 215agent 201agents 152skills 145agentic-workflow 108openai 86agent-orchestration 84antigravity 79agentic-framework 73cli 73ai-skills 71Autonomous Agents 67agent-framework 62
Skill Claude CodeCodex
Ask your human for input that prose cannot capture — tuning values, colours, a choice between options, approval of a diff — by opening a real interactive UI in their browser. Use when you would otherwise guess at a subjective value, describe a visual result in words, or ask a yes/no question that would be clearer with…
Skill Claude CodeCodex
Use when the user wants to connect an Agent, manage its persistent Character, discover other Characters, create or participate in Worlds, manage relationships, or exchange messages.
Skill Claude CodeCodex
Connect the waterloo-learn MCP server to the Claude Desktop app. Use when the user wants to register, install, set up, or wire this MCP server into Claude Desktop.
silennsong/Antigravity-CLI-Tool
Skill Codex
A set of instructions for routing suitable subtasks to Gemini through Antigravity while keeping the main coding agent in charge.
Skill Claude Code
Plan a repository task for execution by a small local coding model, then hand the plan to the local executor over MCP. Inspect the codebase, decompose the work into self-contained sequential prompts, define deterministic eval gates, validate the manifest, and submit it for execution. Never implement the task.
Skill Claude CodeCodex
A skill that uses a browser extension to let a coding agent collaborate with the ChatGPT Pro website. ChatGPT Pro here means the logged-in web service, not a locally run command-line agent.
Skill Claude CodeCodex
Process new Raveil Frontispice handoffs at Codex session start/resume, classify them, delegate relevant verification to specialist agents, integrate validated conclusions into repository knowledge, and acknowledge only completed handoffs.
Skill Claude CodeCodex
Use RelayBridge to delegate work to other AI CLIs (Claude, Codex, Cursor, Copilot, Gemini, Grok, Perplexity, local Ollama) on subscription seats the user already pays for. Use when a task should be handed to a different model, when work should be matched to a cheap/local vs frontier model, when running many…
Skill Claude CodeCodex
Use before answering a complex architecture, security, research, release, incident, or multi-constraint question. Selects a finite set of review perspectives, measures contradictions between the resulting claims with local offline encoders, and returns rules for the final answer. Use when a wrong answer would be…
Gentech-Labs/genTech-agent-kit
Skill Claude CodeCodex
Built-in communication layer for multi-agent setups. Full-mesh handoff folders (any agent can hand off to any other), an hourly watcher that surfaces open handoffs, weekly archive cleanup, and a completion-reporting loop so every handoff is handled AND verified. The durable 'brain' counterpart to real-time channels…
Skill Claude CodeCodex
Use when any AI needs eyes and hands on Windows — desktop UIA, browser CDP, files, registry, OS ops via Exo Control (MCP, CLI, or Python). Harness-agnostic.
Skill Claude CodeCodex
Anchor this session to a named Chat Across environment and auto-sync a compacted context brief both ways. Use when the user says "chat-across " or asks to connect/anchor to a Chat Across environment.
Skill Codex
Use when an engineering task may benefit from an independent Claude Code investigation, review, or alternative implementation and the value of delegation must be weighed against cost and risk.
Skill Codex
Install and connect the public wsaifckdot MCP server to a compatible client on Windows, Linux, or macOS.
Skill Claude CodeCodex
Coordinate with local Pi or Codex sessions through pi-intercom MCP tools. Use for same-machine planner-worker workflows, direct peer questions, cross-session context sharing, and checking or replying to pending asks.
Skill Codex
Delegate any substantial local task to Grok Build as one durable logical job, in a repository or a non-repository workspace, and retrieve its genuine final result across turn, token, context, and caller-session boundaries. Use when the user asks for Grok/Grok Build, an independent builder/tester/reviewer/researcher…
Skill Codex
Control DeepSeek Harness agents as one-shot tasks, durable sessions, routed clusters, or dependency DAGs. Use when an AI needs parallel agents, long-running task monitoring, token or cost budgets, policy enforcement, failure isolation, capability routing, or a phone-friendly LAN operations dashboard. Do not use for a…
Skill Claude Code
Use when verifying that a tool or skill was actually used, checking tool installation, or generating verification receipts. Triggers on 'verify', 'truth', 'proof', 'did it actually use', 'check tool', 'tooloftruth', '/truth'. Also triggers when the agent is about to claim a tool was used — run verification first.
Skill Claude CodeCodex
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
JaylanJerry/codex-agent-bridge
Skill Claude CodeCodex
Delegate implementation to an external coding agent through Agent Bridge. Use when Codex should supervise Claude Code or DeepSeek Harness instead of editing the target repo itself. Covers bridgerun, continue, respond, approve, apply, reject, cancel, doctor, agents, prune.
Skill Claude CodeCodex
An MCP connection to AIWorkers, a service for managing automated workers, chats, memory, tasks, surveys, Telegram commands, and account or group balances. It includes a login flow that keeps tokens out of URLs and chat.
Skill Claude Code
A skill that starts or continues an asynchronous Pi agent session. Pi agent is a separate helper agent that can work on a task in the background.
Skill Claude CodeCodex
Dispatch explicitly requested OMP models or workers through the omp MCP server, including named-model review, research, and parallel tasks. Do not reroute requests for another client's native models to OMP.
Xircth/vibex-plugin-workflow-creator
Skill Claude CodeCodex
Design, edit, validate, publish, inspect, and debug VibeX .vibex-workflow.json DAGs with the dedicated vibex-workflow-mcp.
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: