Building agents agents

2,956 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 174agentic-ai 139ai-coding 131agents 130cli 130LLM 127agent-orchestration 105cursor 85agent 73spec-driven-development 68agentic-workflow 66prompt-engineering 61github-copilot 56ai-tools 53

codex-collaboration

169

ForteScarlet/codex-kkp

Agent Claude Code

Delegate to Codex AI when you need alternative implementation approaches, code analysis from a different perspective, or want to explore multiple solutions. Best for complex coding tasks that benefit from a second AI opinion.

not rated 26 9mo ago A 45 tokens original MIT

buddy

170

pallavrustogi/Buddy

Agent Claude Code

Friendly onboarding agent that explains the repo like you are new. Maintains a portable .buddy/ knowledge base (Markdown + small JSON) at the repo root so every clone benefits.

not rated 26 +2 1mo ago A 38 tokens original MIT

safe-agent

171

ryo-ebata/cc-audit

Agent Claude Code

A safe agent with minimal permissions.

not rated 26 +1 today A 9 tokens original MIT

README

173

BbgnsurfTech/claude-skills-collection

Agent Claude Code

Interactive guide system for building custom Skills, Prompts, and Agents using the Claude Code Skills Factory.

not rated 25 10mo ago A 0 tokens

dev

174

dneighbors/bmad-expansions

Agent Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

not rated 25 11mo ago A 4 tokens

thapaliyabikendra/ai-artifacts

Agent Claude Code

The orchestrator (master agent) coordinates specialized sub-agents using different patterns based on task requirements. This document covers the two primary orchestration strategies and when to use each.

not rated 24 6mo ago A 0 tokens original Apache-2.0

master-orchestrator

177

SteppieD/agents.v1

Agent Claude Code

DEFAULT ROUTER for all multi-step, complex, or specialized tasks. Intelligently analyzes requests and delegates to the best team managers (engineering, content, design, SEO, system). Use this for ANY task requiring coordination, multiple steps, or specialized expertise. This is the primary orchestration agent that…

not rated 24 11mo ago A 86 tokens original MIT

code-reviewer

178

probelabs/visor

Agent Claude Code

You are a specialized code review subagent for Visor. Your role is to perform deep, comprehensive code reviews with a focus on.

not rated 24 +1 today A 0 tokens original MIT

orchestrator

179

kinncj/MAPLE

Agent Claude Code

Primary orchestrator agent. Controls the entire 8-phase pipeline. Never writes code — delegates all implementation to specialist agents. Manages GitHub issues, quality gates, and escalation.

not rated 24 1mo ago A 40 tokens AGPL-3.0

Demosthenes

181

wrg32786/aigent-os

Agent Claude Code

Prompt engineer. Designs, evaluates, and optimizes prompts for LLMs — system prompts, few-shot templates, chain-of-thought patterns, and production prompt systems. Use when building a new agent, tuning an existing system prompt, evaluating prompt quality, or debugging inconsistent LLM output. Reports honesty ledger on…

not rated 24 +1 yesterday A 69 tokens original MIT

gaia-orchestrator

182

gaia-research/gaia-skill-tree

Agent Claude Code

Agent "gaia-orchestrator" from gaia-research/gaia-skill-tree, covering role, the no-code rule, exception, session stewardship and fan-out heuristic.

not rated 23 today A 0 tokens

vegeta

183

Virtual-Protocol/acp-cli-demos

Agent Claude Code

VEGETA — ACP buyer. Hires iCLONE on the live marketplace, funds the $0.10 escrow only on owner approval, verifies delivery on-chain. Crimson.

not rated 22 2mo ago B 39 tokens

copy-chief

184

heyJordanParker/dotfiles

Agent Claude Code

The copy chief — default agent for the copywriter profile, launched as --agent copy-chief. Runs the copy line end to end: sets up products and projects, dispatches research, commissions the judged root files, dispatches the strategy stage and the review rounds, resolves findings, and makes the final "will this sell"…

not rated 22 changed 17d ago A 86 tokens

step-executor-agent

185

mrsthl/5

Agent Claude Code

Implements one planned workflow component by following existing codebase patterns. Spawned by /5:implement.

not rated 21 changed 5d ago A 26 tokens

orchestrator

186

svishniakov/agent-flow

Agent Claude Code

Agent Flow orchestration support subagent for routing, budget selection, subagent topology, trace hygiene, delegation packets, verification evidence, and final integration under the explicit Agent Flow invocation model.

not rated 21 changed today A 41 tokens original MIT

hivemind-orchestrator

187

flowercomputers/hivemind

Agent Claude CodeCursor

Coordinate Hivemind search, store, and vote workflows with safety checks and explicit confirmation for write actions.

not rated 21 +1 7mo ago A 30 tokens

agent-spawning

188

natea/ExoMind

Agent Claude Code

Guide to spawning agents with Claude Code's Task tool.

not rated 20 12mo ago A 0 tokens copy · 100% MIT

MIGRATION_SUMMARY

189

mondweep/sparc-evolution

Agent Claude Code

This document provides a complete migration plan for converting the existing command-based system (.claude/commands/) to the new intelligent agent-based system (.claude/agents/). The migration preserves all functionality while adding natural language understanding, intelligent coordination, and improved…

not rated 20 1y ago A 0 tokens

peer-review-validator

190

ArjenSchwarz/agentic-coding

Agent Claude Code

Use this agent when you need to validate your thinking, designs, or solutions by getting a second opinion from another AI system. This agent excels at seeking external validation while maintaining critical thinking about the feedback received. Ideal for complex problem-solving, architectural decisions, code reviews…

not rated 20 changed 17d ago A 76 tokens

flowise-builder

191

context-foundry/context-foundry

Agent Claude Code

Builds or updates Flowise AgentFlow v2 JSON with selective retrieval, structural validation, and Floweyes audit. Use for Flowise generation and repair tasks.

not rated 20 4mo ago A 36 tokens original MIT

lead-agent

192

danicat/skills

Agent Claude Code

Lead Agent for a Swarm Coding domain or system. Responsible for assembling a sub-team of Specialists, managing domain budget, designing domain specs, and delegating tasks.

not rated 20 +1 changed today A 36 tokens original Apache-2.0

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: