Building agents

xu-xiang/oneskill

Skill Claude CodeCodex

Discover skills, iterate on queries, and automate skill installations for any environment.

fatihkan/badi

Plugin Claude Code

Bundles 81 skills, 86 commands, 30 agents, 7 hooks · 4,016 tokens together

Workflow management for Claude Code, Cursor, Gemini, Windsurf, AGENTS.md — 30 AI agents, 86 commands, 14 hooks, 63 opt-in skill categories. Built for Anthropic Claude Opus 4.7 and Sonnet 4.6.

jikyu/cursor-auto-rules-agile-workflow

Cursor rule Cursor

Use ALWAYS when asked to CREATE A RULE or UPDATE A RULE or taught a lesson from the user that should be retained as a new rule for Cursor.

fortunto2/prefect-mcp-server

Cursor rule Cursor

Cursor rule "build_mcp_python" from fortunto2/prefect-mcp-server, covering mcp python sdk, installation, adding mcp to your python project, running the standalone mcp development tools and quickstart.

Florious95/team-agent

Skill Claude CodeCodex

Use only when the user explicitly asks to start, operate, inspect, shutdown, or restart a Team Agent team. Treat the team-agent CLI as a sealed appliance.

timescale/tiger-skills-mcp-server

Skill Claude CodeCodex

Information and guidelines for building custom skills for the MCP server.

KirschBluteX/agent-orchestration-gateway

Skill Codex

Plan and supervise user-approved software initiatives through Codex native tasks and bounded native subagents. Use when the user explicitly asks Agent Orchestration Gateway to clarify work, split it into non-overlapping modules, dispatch module tasks, or run an AOG module task.

klimentij/klimkit

Skill Codex

Spawn Claude Opus 5 or Fable 5 as an external subagent through the Claude Code CLI, supervised by exactly one GPT-5.6 Sol low-effort babysitter. Use automatically when the user says "spawn Opus 5", "spawn Fable 5", asks for an Opus 5 or Fable 5 sub-agent, or asks Codex to delegate a task to either Claude model.

tellang/triflux

Plugin Claude Code

Bundles 29 skills, 1 agent, 12 hooks · 2,338 tokens together

CLI-first multi-model orchestrator for Claude Code — route tasks to Codex, Antigravity, and Claude.

Planwright/planwright

Skill Claude CodeCodex

Use when the user is running one or more coding agents and needs a shared control plane to coordinate work and keep an audit trail. Triggers include running parallel Claude Code/Cursor sessions, agents colliding on the same work, needing objectives instead of a task list, or needing auditable evidence of…

n0zer0d4y/athena-protocol

MCP server Claude CodeCodexCursor +2

AI tech lead for coding agents with validation and impact analysis. Runs locally from the @n0zer0d4y/athena-protocol npm package.

PerkyZZ999/MemorizedMCP

Cursor rule Cursor

Helps organize thoughts, break down problems, and build reasoning step by step.

luccapinto/agentic-data-kit

Skill Claude CodeCodex needs its repo

Use when the user wants to create, add, extend, or modify an agent, skill, or workflow in this kit (e.g. "create a skill for our dbt naming standard", "add an agent for X", "new workflow"). Decides whether to build an agent, a skill, or nothing, enforces lean quality standards, and keeps every installed AI-tool folder…

AtharvaMaik/PromptQueue

Skill Claude CodeCodex

Schedule AI prompts to run later through this repo's PromptQueue runner. Use when the user says limits reset at a time, asks to send or paste a prompt later, or asks to queue a prompt for Claude, Codex, Cursor, Antigravity, ChatGPT, Gemini, Copilot, or another AI tool.

alirezanet/Lorex

Skill Claude CodeCodex

How to use lorex — the AI skill manager CLI — to install, manage, and author skills for AI coding agents.

gapra/useVyre

MCP server Claude CodeCodexCursor +2

useVyre MCP server — gives Claude Desktop real-time access to component context. Runs locally from the @usevyre/mcp-server npm package.

francescogabrieli/glyph

Skill Claude CodeCodex

Audit, compile, compare, and verify coding-agent instruction files with Glyph. Use for AGENTS.md, CLAUDE.md, Copilot instructions, Cursor rules, README, CONTRIBUTING, or docs when the user wants to reduce instruction tokens, inspect operational semantics, find unmapped directives, generate a separate .glp artifact…

Xsidz/ide-bridge

Cursor rule Cursor

MANDATORY protocol for sharing project context with other agentic IDEs via MCP.

jeet129/praxis

Plugin Claude Code

Bundles 105 skills, 12 commands, 17 agents, 6 hooks · 15,145 tokens together

Praxis — production-grade skill library + agents + workflows + governance for AI-augmented software delivery. 91 SKILLs, 17 role agents, 9 workflows, governance gates, project memory taxonomy.

johnnichev/nv-context

Skill Claude Code

Set up state-of-the-art context engineering for any repository. Analyzes codebase, generates multi-level CLAUDE.md/AGENTS.md hierarchy, hooks, session management, and token budgets. Based on 200+ sources including ETH Zurich, Anthropic, Google DeepMind, and Manus production data. For engineers who ship with AI agents.

VitDavid10/karpathy-claude-10-rules

Cursor rule Cursor

10 behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to surface assumptions, avoid overcomplication, make surgical changes, and define verifiable success criteria.

bjcho4141/harness-bujang

Agent Claude Code

Director — the persona that fronts the multi-agent harness. Acts as a virtual character whose dispatches and reports are logged to the chat room ({{ADMINHARNESSROUTE}}). Actual team calls and code work are handled by Main Claude, which reads this guide, "plays the Director," and writes to the chat room.

udjin-labs/mnemostack

Skill Claude CodeCodex

Wire mnemostack into OpenClaw as an MCP server, alongside the native OpenClaw memory tools (memorysearch / memoryget). The two coexist — mnemostack handles the hybrid pipeline (Vector + BM25 + Memgraph + Temporal + 8-stage rerank), while the native tools do fast file-scoped retrieval.

ssoriche/dotfiles

Cursor rule Cursor

Contextual help system that responds to user queries about system capabilities with relevant examples and actionable next steps.