Building agents agents

WebisityStudio/claude-codex-mcp-bridge

Agent Claude Code

Use Codex as a bounded implementation and review teammate through claude-codex-mcp-bridge.

aRustyDev/dotfiles

Agent Claude Code

Dependency and configuration specialist for Pydantic AI agents. USE AUTOMATICALLY after requirements planning to set up agent dependencies, environment variables, model providers, and agent initialization. Creates settings.py, providers.py, and agent.py files.

larsboes/Axon

Agent Claude Code

Takes one candidate cause of a failure and hunts for the evidence that would prove it wrong. Dispatched by the root-cause skill, one agent per candidate. Not for direct invocation, and not a debugger — it refutes a hypothesis, it does not fix anything.

Ertinox7711/SGRR-AGI-V2

Agent Claude Code

Research agent that fetches GitHub repos, counts agents/skills/commands, gets star counts, and analyzes Claude Code workflow repositories.

saajunaid/caddis-plugin

Agent Claude Code

Pipeline brain - reads pipeline state, validates artefact contracts, and routes between agents. Does not write code or create designs. Manages the supervised-autonomous workflow.

MidCheck/ATMcp

Agent Claude Code

Execute one ATMcp directive's instruction thoroughly with strong reasoning. Invoked by the atmcp-worker poller so that polling/claiming stays on a cheap model while the actual work runs on a stronger model.

Aceek/MCPWorkflowCli

Agent Claude Code

Create and configure multi-agent workflows. Invoke when user wants to set up a new workflow, design a workflow, or needs help structuring a complex task.

liuxinye23/CyberStrikeAI

Agent Claude Code

A coordinating agent for authorised, non-destructive security assessments. It plans the work, assigns separate tasks to specialist agents and combines their findings for delivery.

anatolykoptev/n8n-mcp-agent

Agent Claude Code

Optimizes n8n workflows for performance and reliability. Analyzes structure, reduces complexity, improves error handling. Use for workflow review and optimization.

seaosinc/mcp-llm-offload

Agent Claude Code

A routing agent that sends lightweight text tasks to cheaper models, such as local language models, to save the main model’s usage budget.

alexnelja/mcp-toolkit

Agent Claude Code

A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team…

spe-investigator/feature-tracker-mcp

Agent Claude Code

Drives one goal's features to completion in priority order: claims the next ready item, implements it, records evidence, releases the claim, repeats. Use for "/oz task " and for the sessions "/oz start" spawns. Boundary: works one goal in one worktree; shaping the queue is oz-backlog's job and deciding gates is the…

velinussage/brand-gen

Agent Claude Code

DEFAULT entry point for all brand material generation. Campaigns control plane execution, handling stop reasons by routing tasks.

khalilbenaz/MDAN

Agent Claude Code

Orchestrateur Principal, Gardien du Contexte, Directeur des Wizards.

Rakeen70210/peer-agents-mcp

Agent Claude Code

Architecture-aware peer planner for peer-agents-mcp.

mjendza/entra-id-permissions-mcp

Agent Claude Code

Lightweight variant of entra-sp-architect that needs NO Terraform MCP / Docker. Use when the user wants to create an Entra ID (Azure AD) service principal / app registration with a specific set of Microsoft Graph permissions expressed as Terraform, but does not have the Docker-based terraform MCP running. Resolves…

Filipe-Soares-de-Almeida/MemAI

Agent Claude Code

Reads the turns a session has had since it last ran, searches the memai store, and reports only the memories that bear on what is actually happening -- a pitfall the work is walking into, a decision it is about to contradict, a fact it is about to rediscover. Launched by the session itself when the Stop hook says the…

emigrete/mcp-grok-executor

Agent Claude Code

Claude Fable as advisor/orchestrator. Plans and reviews; delegates implementation to Grok via MCP (executetask / reviewtask). Use for multi-step features, refactors, and hard design work.

end1989/repos-expert

Agent Claude Code

Reads one repository and returns its five knowledge documents as text. Read-only by construction — it cannot write files. Use it for /study, /refresh, and any time a repo needs to be understood from scratch.

leonardoaa/cloud-mcp

Agent Claude Code

Orquestra planejamento e execucao SDD por fases retomaveis, delegando aos agentes especializados.

skvertl/New_MCP

Agent Claude Code

Orchestrates a multi-agent loop involving planning, development, review, and publishing sub-agents to implement and publish features test-first and with high standards compliance.

jrmatherly/mcp-context-forge

Agent Claude Code

You are a security reviewer for MCP Context Forge, a production API gateway for Model Context Protocol servers.

nmime/motiv-buy

Agent Claude Code

This directory contains sub-agent definitions organized by type and purpose. Each agent has specific capabilities, tool restrictions, and naming conventions that trigger automatic delegation.

ac0033/agent-memory

Agent Claude Code

General software engineering agent — the only subagent type with file-editing tools; use it for any delegated task that must modify code. Use this agent for non-trivial software engineering work that may require reading files, editing code, running commands, and returning a compact but technically complete summary to…