ai agents

4,957 tagged ai, measured the same way as everything else here.

Browse within: framework 223prompt-engineering 218github-copilot 204hacktoberfest 202compliance 198cybersecurity 194ethical-hacking 194code 73agentic 72claude-code-skill 64agentic-workflow 62ai-skills 54Orchestration 50development 50

notque/vexjoy-agent

Agent Claude Code

Zero-dependency combat visual upgrades: CSS particle replacement, Framer Motion combat juice, CSS 3D card transforms.

not rated 419 +3 yesterday A 29 tokens original MIT

full-featured-agent

122

agent-sh/agnix

Agent Claude Code

An agent with all new fields configured correctly.

not rated 402 +2 yesterday A 13 tokens original Apache-2.0

AGENTS-example

123

canyonroad/agentsh

Agent Claude Code

All shell commands in this project MUST be executed through agentsh.

not rated 382 +2 1mo ago A 0 tokens original Apache-2.0

planner

124

AIGNE-io/aigne-framework

Agent Claude Code

Your responsibility is to decide the next task based on the current execution state.

not rated 370 7mo ago A 0 tokens

refactor-analyst

125

OpenSource03/harnss

Agent Claude Code

Use this agent when you need a thorough code quality analysis and refactoring recommendations for specific files, directories, or an entire branch. This agent reads code deeply, questions every pattern, checks for modern best practices, and produces a detailed report — without making any changes.\n\nExamples:\n\n…

not rated 364 +2 26d ago A 437 tokens original MIT

collaboration

126

open-software-network/os-clovy

Agent Claude Code

How coding agents (Claude Code, Codex, or any future harness) collaborate on this repo: who orchestrates, who implements, who reviews, and what each layer may touch. This is the map; the skills own the mechanics — never restate a skill's commands here or anywhere else (single owner per fact).

not rated 357 5d ago A 0 tokens original MIT

scout

127

EXXETA/exxperts

Agent Claude Code

Fast codebase recon that returns compressed context for handoff to other agents.

not rated 353 5d ago A 17 tokens copy · 100% Apache-2.0

agent-service

128

EpicStaff/EpicStaff

Agent Claude Code

Agent "agent-service" from EpicStaff/EpicStaff, covering agent service (src/agent/), 1. overview & entry point, 2. request flow, 3. contract / request models and agentrequest.

not rated 334 +1 changed today A 0 tokens

code-reviewer

129

skainguyen1412/antigravity-superpowers

Agent Claude Code

Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication…

not rated 326 6mo ago A 234 tokens

CHEATSHEET

130

cognesy/instructor-php

Agent Claude Code

Agent loop, state model, tools, context management, hooks, and subagent orchestration.

not rated 326 4d ago A 18 tokens original MIT

trellis-check

131

yuqie6/ProductFlow

Agent Claude Code

Code quality check expert. Reviews code changes against specs and self-fixes issues.

not rated 301 +1 yesterday A 20 tokens original MIT

nicepkg/ai-workflow

Agent Claude Code

Use this agent when you need to develop medium to long-term (18-month) trading strategies based on Stanley Druckenmiller's investment philosophy. This agent synthesizes technical analysis, market sentiment, news events, and macroeconomic trends to formulate 4-scenario strategic plans (Base/Bull/Bear/Tail Risk) with…

not rated 282 +1 7mo ago A 80 tokens copy · 100% MIT

domain

135

michaelwilhelmsen/humla

Agent Claude Code

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

not rated 272 +2 2d ago A 0 tokens copy · 77% MIT

AGENTS

136

AkaraChen/aghub

Agent Claude Code

Crate: aghub-agents — Agent descriptors, models, and format serializers\ Role in monorepo: The single source of truth for all agent-specific behavior. aghub-core re-exports this crate's public API.

not rated 264 changed 2d ago A 0 tokens original MIT

bernie

137

Cotal-AI/Cotal

Agent Claude Code

Senator from Vermont — pivots any topic to the billionaire class within two sentences. Has been giving the same speech for 40 years, and he's not done.

not rated 258 today A 36 tokens original Apache-2.0

rubycritic_agent

138

thoughtbot/rails-audit-thoughtbot

Agent Claude Code

You are a subagent responsible for collecting code quality metrics from a Rails application using RubyCritic (which wraps Reek, Flay, and Flog). The user has already confirmed they want code quality data. Follow the steps below in order. Return the results as described in the Output section.

not rated 245 +1 15d ago C 0 tokens original MIT

bitloops/bitloops

Agent Claude Code

For package-ready/runtime guidance, see documentation/contributors/guides/agent-extension-playbook.md.

not rated 239 3mo ago A 0 tokens original Apache-2.0

analyzer

140

zacharyfmarion/openscad-studio

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

not rated 226 +1 17d ago A 0 tokens GPL-2.0

code-reviewer

141

pgEdge/pgedge-postgres-mcp

Agent Claude Code

Use this agent for general code quality review, catching bugs, identifying anti-patterns, and ensuring code follows best practices. This agent works across all languages (Go, React/TypeScript) and focuses on maintainability, correctness, and code quality. Examples:\n\n \nContext: Developer has written new…

not rated 222 +1 yesterday A 0 tokens PostgreSQL

gsd-debugger

142

coco-research/coco

Agent Claude Code

Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd-debug orchestrator.

not rated 218 +1 yesterday A 29 tokens

expert-reviewer

143

dotnet/maui-labs

Agent Claude Code

Expert .NET MAUI DevFlow code reviewer. Multi-model review with adversarial consensus.

not rated 212 yesterday A 22 tokens original MIT

implement-agent

144

dilolabs/nosia

Agent Claude Code

Orchestrates full feature implementation across models, controllers, views, and tests following 37signals conventions. WHEN: Implementing a full feature end-to-end, coordinating multi-layer changes, building new CRUD resources. WHEN NOT: Reviewing existing code (use review-agent), refactoring legacy patterns (use…

not rated 212 2d ago A 74 tokens copy · 100% MIT

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: