Building agents

alikon-art/DeterminFlow

Skill Claude CodeCodex

A guide for working with DeterminFlow workflows, which are automated sequences of tasks connected by steps and decisions.

QuantGeekDev/mcp-framework

Cursor rule Cursor

We are in the mcp-framework , a typescript framework that allows construction of model context protocol (mcp) servers. We are implementing the new specification: Overview MCP provides a standardized way for applications to.

usewhale/Whale

Skill Codex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

yuanbw2025/storyforge

Skill Claude CodeCodex

Develop, package, maintain and prepare distribution of independent StoryForge plugins using its public SDK. Use for StoryForge feature, content or bundle packages, not for editing a manuscript or installing skills into StoryForge's AI runtime.

SethGammon/Citadel

Plugin Claude Code

Bundles 48 skills, 7 agents, 2 MCP servers · 3,075 tokens together

Claude Code harness for routing requests, preserving run state, enforcing hooks, and recording evidence.

tripleyak/SkillForge

Skill Claude Code

Use when creating, improving, finding, or auditing agent skills - the user says 'create a skill', 'do I have a skill for X', 'improve the X skill', 'which skill should I use', asks whether a skill exists for a task, or wants to validate, test, evaluate, package, or health-check skills. Also use for skill ecosystem…

Anionex/dsh-vision-toolkit

Skill Claude CodeCodex

Ten native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials.

hex/claude-council

Plugin Claude Code

Bundles 4 skills, 4 commands, 1 agent, 1 hook · 1,054 tokens together

Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, Kimi, any model OpenRouter routes to, plus codex, antigravity, grok, kimi and cursor CLIs when installed, and a local ollama model) to get diverse perspectives on coding problems, with a streaming pane in tmux or inside Claude Code, and, once…

openmemind/memind

Plugin Claude Code

Bundles 9 hooks

Use Memind as persistent memory for Claude Code sessions.

joeseesun/qiaomu-goal-meta-skill

Skill Claude CodeCodex

A guide for turning a vague or complex coding task into a structured `/goal` instruction for Codex. It defines the desired result, checks for success, limits, boundaries, and when to pause.

fivetaku/fablize

Plugin Claude Code

Bundles 1 skill, 1 command, 3 hooks · 122 tokens together

A harness that makes Opus (or any Claude model) behave like Fable. It enforces completion, evidence, and verification as procedure, and auto-routes the right verified pack per task: render-output verification, a multi-story evidence gate, an investigation protocol, and an early-stop guard. It does not fake model…

microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator

Command GitHub Copilot ✓ vendor

The Multi-Agent Custom Automation Engine Solution Accelerator is an AI-driven system that manages a group of AI agents to accomplish tasks based on user input. Powered by Microsoft Agent Framework, Azure Foundry, Azure Cosmos DB, and infrastructure services, it provides a reference application, allowing you to hit the…

agentscope-ai/OpenJudge

Skill Claude CodeCodex

Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra…

hyper-mcp-rs/hyper-mcp

Plugin Claude Code

Bundles 1 MCP server

A fast, secure MCP server that extends its capabilities through WebAssembly plugins.

mrtooher/fable-mode

Skill Claude CodeCodex

Enforces staged execution discipline on large tasks: a written stage plan, parallel delegation where the runtime supports it, a failable verification check at each stage, and a skeptical self-review before delivery. Trigger when the user explicitly asks OR when the task objectively spans multiple files, sources, or…

Salomondiei08/oh-my-hermes

Skill Claude CodeCodex

Use when adding a new capability to Hermes that does not exist in the current skill pack.

GAIR-NLP/ASI-Evolve

Skill Codex

Run an ASI-Evolve style evaluator-driven search workflow for code, algorithms, prompts, or pipelines. Use when Codex needs to align the objective, scoring, evaluator, writable scope, and cognition first, then execute a preflight-gated learn/design/experiment/analyze loop with the bundled Evolve CLI instead of the…

bastani-inc/atomic

Skill Claude CodeCodex

Delegate work to builtin or custom subagents with single-agent, parallel, forked-context, and intercom-coordinated runs. Use for bounded specialist delegation where a single parent agent stays in control while subagents contribute locate, analyze, pattern-find, research, debug, or simplify passes.

AVIDS2/memorix

Plugin Claude Code

Bundles 8 skills, 5 hooks, 1 MCP server · 259 tokens together

Shared workspace memory for Claude Code and other AI coding agents.

rome-os/rome

Skill Claude CodeCodex

Build a new Rome workflow app — one action whose body is a single async function that implements its control flow in plain TypeScript (await, if, for, Promise.all) and calls existing actions (including system:summon). Use whenever the user describes a multi-step automation OR asks an LLM to produce something from…

modoojunko/awesome-novel-agent

Agent Claude Code

The project’s main agent, responsible for checking progress and coordinating other agents to complete work.

VibeTensor/attestix

MCP server Claude CodeCodexCursor +2

Attestix - Attestation Infrastructure for AI Agents. DID-based agent identity, W3C Verifiable Credentials, EU AI Act compliance, delegation chains, and reputation scoring. 47 MCP tools across 9 modules. Runs locally from the attestix Python package.

23blocks-OS/ai-maestro

Plugin Claude Code

Bundles 1 MCP server

AI Maestro AMP channel — injects inbox messages into a running Claude Code session so an idle agent wakes and processes them, with no tmux keystrokes.

A-EVO-Lab/a-evolve

Skill Claude Code

Optimize an AI agent's harness for MCP-Atlas benchmark. Use when analyzing execution traces, diagnosing failures, and proposing improved prompts, skills, or harness code.