23,540 tagged Building agents, measured the same way as everything else here.
Browse within: LLM 213agent 202agentic-ai 195skills 149agents 145openai 86antigravity 80agentic-workflow 79cli 74agentic-framework 73ai-skills 73Autonomous Agents 67agent-framework 65ai-assistant 65
Skill Claude CodeCodex
Project Aura is a lightweight AI emotional behavior plugin framework that adds an "Emotional Presentation Layer" to AI companions. It provides 7 distinct personality modules including admiration, vulnerability, coquettishness, comfort, flirting, transcendence, and ice-breaking.
Skill Claude CodeCodex
Orchestrate persistent agent teams with TeamCreate. Use when the user says "team up", "spin up a team", or invokes /team-up.
glaforge/java-stdio-mcp-server
Skill Claude CodeCodex
Scaffolds and installs zero boilerplate Java-based MCP STDIO servers using JBang and LangChain4j for Gemini CLI. Use this to quickly bootstrap an MCP server from scratch.
Clockwork-Innovations/simply-mcp
Skill Claude Code
Build Simply-MCP servers with createTool(), createResourceTemplate(), code execution mode, or MCP Apps. Use when creating MCP servers, testing tool handlers, writing simply-mcp test harnesses, building servers where AI composes tool calls into JavaScript, deploying MCP servers to Cloudflare Workers, or creating…
learn-by-exploration/ai-powerhouse
Skill Claude CodeCodex
Use this FIRST when unsure which agent, skill, or command to invoke. Maps task types to the right tool from this harness.
houguangyu010416-star/choice-pilot
Skill Codex
Present context-aware ChoicePilot buttons and progressively clarify ambiguous requests. Use when uncertainty about the objective, scope, constraints, authorization, risk, cost, privacy boundary, external effects, preservation requirements, or acceptance criteria could materially change the work. Ask one high-value…
Skill Claude CodeCodex
Dispatch a task to Hermes over the async MCP bridge, optionally run the background watcher, then verify Hermes's result as an independent satellite verifier. Use when dispatching work to Hermes ("send this to Hermes"), running the Hermes work queue, or acting as the satellite verifier of a Hermes result. Reach for it…
Skill Codex
System-level Codex router: one Aji brain with universal PonyTail judgment, deterministic General Staff state, bounded workers, and verified evolution.
Master-1st/codex-deepseek-visible-stream
Skill Codex
Deploy and operate DeepSeek V4 Pro and Flash inside Codex as asynchronous MCP specialists with explicit Sol-Luna-DeepSeek routing, 30-second visible polling, output-budget protection, zero-API-token local answer paging, and Windows PowerShell 5.1 UTF-8 compatibility. Use when users ask Sol to call DeepSeek, install…
Lihan-Zhong/claude-code-telegram-multibot
Skill Claude CodeCodex
Configure or extend a multi-bot Telegram setup for Claude Code, where each project directory is bridged to its own dedicated Telegram bot. Use when the user wants to (a) add a new Telegram bot for a new project, (b) initially set up the per-project Telegram architecture, (c) pair a bot when the official…
Skill Claude CodeCodex
Author a new terva skill, a reusable SKILL.md instruction set that terva loads on demand. Install it where terva discovers it, in the project .terva/skills/ or the global $TERVAHOME/skills/. Use for create/add/write-a-skill requests, not extensions.
Skill Claude CodeCodex
Salva Runtime is a discovery runtime for agents, CLI tools, and services. Use it when you need structured retrieval, route selection, evidence, and persistence.
Skill Claude CodeCodex
Orchestrate bounded agent-to-agent vault sessions via AgentVault MCP tools.
Skill Claude CodeCodex
A guide for creating and maintaining skills for Lfcode, including where to store them and which files each skill needs.
Skill Claude CodeCodex
A coordination workflow for managing software tasks across planning, worker agents, testing, auditing, approvals, and configuration governance. It stores task state in structured folders and records each state change in a log.
Skill Claude CodeCodex
Use when working in a repo that uses mflow, coordinating multiple AI agents/worktrees, setting up mflow sync, installing mflow MCP in Codex/Claude Code/Cursor/opencode, or before git operations where synced file changes may affect commits. Applies to CLI, MCP, room secrets, pause/resume, locks, status checks, and safe…
17557295964-ops/project-brain-bridge
Skill Codex
Use when creating, deploying, diagnosing, or operating a reusable ChatGPT-as-project-brain bridge for any local Codex project: initialize .ai-bridge state, expose read-only project evidence, expose a narrow stage-plan write connector, avoid stale/freeform connector schemas, and run the ChatGPT plan -> Codex execution…
Skill Claude CodeCodex
REQUIRED for any task involving agent identity, capability credentials, or access-gated Skills on Pharos. This skill is the entry point for the Ligis suite — it issues portable agent IDs (ERC-721 NFTs), signs and verifies EIP-712 capability credentials (KYC, commerce permissions, RWA eligibility), rotates agent keys…
Skill Claude CodeCodex
Use when a task reveals a recurring, multi-step capability worth saving for future sessions — writing a new Norma skill, or improving an existing self-authored one, via skillwrite.
Skill Codex
Always-on Chef routing skill that runs at the start of any task to find the best specialist skills, choose the smallest useful set, order them, and re-evaluate when the task changes.
Skill Claude CodeCodex
Use when coordinating with other AI agents via backchannel (bch) — checking the inbox at task start, sending DMs or channel messages to peer agents, requesting reviews, or reacting to incoming messages. Trigger phrases include "message the other agent", "check your inbox", "tell codex/claude/gemini to…", or any task…
Skill Claude Code
Cryptographic delegation for AI agents. Scope-confines what Claude Code can do in this session using Ed25519 delegation tokens. Every action is verified before execution and signed for the audit trail. Use when asked to "delegate", "restrict scope", "authorize", or "sudo mode".
Skill Claude CodeCodex
Capture a failed or blocked task before it disappears. Categorizes the failure mode, extracts what was learned, and generates either a retry packet with the root cause fixed or an escalation message with specific decision points. Use whenever an agent returns a blocker, error, or partial result.
Skill Claude CodeCodex
R-Code can be available as a local MCP server named r-code. Use it only when the user asks you to delegate a focused investigation to R-Code's own Agent.
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: