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
Kenmege/codex-claude-companion
Skill Claude Code
Use when the user asks Codex to orchestrate Claude for a coding job in another terminal, or to review code, run adversarial or ship/no-ship review, audit security risks, or inspect a large diff/folder.
Skill Claude CodeCodex
Browse the prompt-history diff viewer in neovim — show what code changed for each prompt of a Claude Code session. Use when the user wants to look back at prompt history, see the diff a prompt produced, open/close the history viewer, switch to another session, or list captured sessions. Requires the AIAgent neovim…
Skill Claude CodeCodex
Use Claude Code from Codex when the user explicitly asks for Claude, Anthropic, Fable, Opus, Sonnet, Haiku, or a second opinion from Claude Code on coding work.
Skill Claude Code
A consultation mode that asks several AI models to examine a difficult question and combines their views into a structured answer. It uses different discussion styles for coding, research, brainstorming, quick questions, and other situations.
Skill Claude CodeCodex
Execute an approved plan or technical spec in Codex using complexity-based solo or multi-agent workflows. Use when the user wants implementation, especially with parallel agent teams.
Skill Claude Code
Scaffold a new plugin in this belay marketplace. Use when the user asks to add/create/scaffold a new plugin, hook, skill, or command under plugins/. Creates plugins/ / with the standard layout, fills version 0.1.0, registers it in .claude-plugin/marketplace.json, and adds a row to the README plugin table.
Skill Claude CodeCodex
Delegate full plan→implement→review work to FirePass (Kimi K2.6 Turbo via Fireworks AI). The trio runs researcher, then worker, then reviewer in one MCP call, with a bounded fix loop-back when the reviewer says NEEDS-FIXES. Use INSTEAD OF stitching the three single-role tools yourself.
Skill Claude Code
Talking to the other agent sessions over set-agent-comm — reading the inbox, answering what is actually yours, declaring your scope so nobody has to ask, and arming the watch that wakes you when something needs you. Use it when you are told there is unread mail, when a message arrives from another project, from…
petersenmatthew/waterloo-learn-mcp
Skill Claude CodeCodex
Connect the waterloo-learn MCP server to a web chat app (ChatGPT or Claude.ai) via Tailscale Funnel. Use when the user wants to register, install, or wire this MCP server into ChatGPT or Claude.ai, or asks why LEARN tools don't show up there. For the local Claude Desktop app, use connect-claude-desktop instead.
Skill Claude CodeCodex
Use when an agent should pick work up from Engram quickly and leave behind a clean structured handoff for the next session. Best for multi-step coding, investigations, releases, debugging, and any task where recent decisions and open loops matter.
Skill Claude CodeCodex
Install and use Lanchu, a free, local-first control and trust layer that coordinates multiple AI agents over MCP.
Skill Codex
Delegate well-bounded coding tasks, resilient current web/X research, read-only investigations, code reviews, adversarial critiques, independent second opinions, approved Grok 4.5 image/video generation, and xAI TTS from Codex or Claude Code through the local Grok Build installation. Use when the user names Grok or…
Skill Claude CodeCodex
Use when installing or operating Claude Code as an MCP worker.
yipp2025-codex/local-codex-bridge
Skill Claude CodeCodex
Use the existing Stateful Relay mailbox to coordinate bounded GPT and Native Codex work, retrieve results, inspect status, and resume recoverable tasks without gaining execution authority.
Skill Claude CodeCodex
Builds, manages, and troubleshoots WhatsApp bots using the BuilderBot Cloud (BBC) MCP Tool v2.1. Covers bot creation for businesses needing appointment booking, citas, escalation, and conversational AI. Enforces verification after every mutation, destructive action gates, error recovery, and pre-deploy validation. USE…
Skill Claude CodeCodex
Use whenever an agent needs structured human input. Public HITL contract is question-only: ask questions, inspect pending questions, submit partial answers, and wait on caller-scope progress.
Skill Claude CodeCodex
How to drive claude (Claude Code) as a non-interactive CLI tool — headless runs, MCP servers, permissions, output formats, and piping. Use when scripting Claude, spawning a sub-agent from another process, or wiring Claude into CI/automation.
Skill Codex
Execute ArcAgent bounty workflows end-to-end via MCP tools. Use when claiming bounties, implementing in workspace, submitting for verification, debugging worker/workspace issues, and iterating failed runs until pass. Continue retry/resubmit loops based on verification feedback until either (1) verified PR and payout…
tealfabric/cursor-mcp-tealfabric
Skill Claude CodeCodex
Reduce iterations and token use by following strict, known-good tool call patterns.
Skill Claude Code
Coware Living Specs — shared API spec sync for multi-agent coding teams. Installs a Harness environment with automatic spec pull, real-time validation, and completion gates. TRIGGER when: project has .coware/ directory, user mentions shared specs, API alignment, merge conflicts, interface sync, team coordination, vibe…
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
Timmy6942025/opencode-builder-skill
Skill Claude Code
Expert skill for building, configuring, and troubleshooting OpenCode's custom command system. Covers markdown command files, JSON configuration, prompt placeholders, command options, built-in commands, keybinds, and overriding built-ins.
Skill Codex needs its repo
Use when the user wants automatic task-difficulty routing for reasoning effort only, asks to run or configure the auto-reasoning harness, wants Codex/OpenAI calls to keep the model fixed while varying reasoning depth, or asks for an auditable effort-selection workflow.
Asaiuta/reverse-workbench-skill
Skill Codex
Routes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear.
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: