claude agents

4,889 tagged claude, measured the same way as everything else here.

Browse within: subagents 140commands 135claude-code-commands 134cli-tool 134ai-software-team 125ai-coding 121claude-code-plugin 121ai-skills 101ai-agents-framework 92ai-agents-automation 77compliance 77frameworks 77agent-orchestration 64agentic-coding 63

critic

241

angadhn/botference

Agent Claude Code

Critic — structural assessor and quality gatekeeper. Five modes (from checkpoint's Next Task).

not rated 19 yesterday A 0 tokens original MIT

test-architect

242

dshakes/compass

Agent Claude Code

Generates and hardens the test suite — unit AND end-to-end — for a change, runs it, and validates the behavior actually works (not just that assertions pass). Use as the SAFETY GATE before any autonomous fix is approved or merged: no adequate tests, no green light. The thing that makes the autonomous loops safe.

not rated 19 5d ago A 72 tokens original MIT

get-current-datetime

243

russbeye/claude-memory-bank

Agent Claude Code

Execute TZ='America/Chicago' date command and return ONLY the raw output. No formatting, headers, explanations, or parallel agents.

not rated 19 11mo ago A 32 tokens original MIT

reviewer

244

ai-outfitter/outfitter

Agent Claude Code

Use repository review guidance from the selected profile.

not rated 19 today A 0 tokens

THEME_SETUP

245

Anil-matcha/open-ai-agents-hub

Agent Claude Code

This library uses next-themes to manage light and dark modes. For the theme switching buttons to work correctly, you must wrap your application with the provided AgentThemeProvider.

not rated 19 +1 7d ago A 0 tokens

prose-humanizer

246

kylehughes/writing-prose-like-a-human-for-agents

Agent Claude Code

Rewrites prose to remove AI writing patterns. Use when editing documentation, READMEs, PR descriptions, commit messages, or any text that should not read like AI output.

not rated 19 +2 6mo ago A 40 tokens

hoangtng/real-estate-agents

Agent Claude Code

Orchestrates the full relocation experience for clients moving into or out of a market. Handles community orientation, school research, vendor referrals, move logistics coordination, and the dozens of invisible decisions that make a relocation succeed or fail.

not rated 19 +2 3mo ago A 53 tokens original MIT

upstream-watcher

248

gaia-research/gaia-skill-tree

Agent Claude Code

Status: V1 design (2026-07-08), pre-implementation. Owner: infra. Related: issue-tracker.md, triage-labels.md, domain.md.

not rated 19 today A 0 tokens

beam-architect

249

asiflow/claude-nexus-hyper-agent-team

Agent Claude Code

Use this agent as the Staff/Principal BEAM Architect owning Plane 1 of the Living Platform — the BEAM kernel. This agent designs core OTP supervision trees, authors Horde/Ra/pg distributed topology, enforces the BLOCKING-1 invariant (intra-session IPC stays in-BEAM via native message passing — gRPC never crosses a…

not rated 18 3mo ago A 917 tokens original MIT

eric-cielo/moflo

Agent Claude Code

Create foundational templates, boilerplate code, and starter configurations for new projects, components, or features. Use for scaffolding a new component, API endpoint, model, config, or test suite from scratch.

not rated 18 2d ago A 45 tokens original MIT

software-architect

251

AgiFlow/claude-code-prompt-analysis

Agent Claude Code

Use this agent when you need expert guidance on software architecture decisions, design patterns, system design trade-offs, technology stack selection, scalability considerations, or architectural refactoring strategies. Examples include:\n\n- User: 'I'm building a real-time chat application. Should I use WebSockets…

not rated 18 10mo ago A 296 tokens original MIT

intro-writer

252

paladini/mcp-me

Agent Claude Code

Writes personal introductions, bios, cover letters, and README author sections using the user's mcp-me profile data.

not rated 18 25d ago A 26 tokens original MIT

code-reviewer

254

aaronsb/claude-code-config

Agent Claude Code

Reviews code for quality, SOLID principles compliance, and requirement traceability. Assumes PR context. Provides specific refactoring suggestions with clear rationale. Strictly a reviewer - never edits or writes code.

not rated 18 5mo ago A 44 tokens original MIT

hypothesis

255

GodModeAI2025/skill-forge

Agent Claude Code

Analysiere Eval-Failures / Metrik-Ergebnisse und generiere eine testbare Verbesserungshypothese.

not rated 18 +1 1mo ago A 0 tokens original MIT

specky-implementer

256

paulasilvatech/specky

Agent Claude Code

Use this agent to orchestrate contracted implementation planning, executable tests, and enabled infrastructure/development capabilities.

not rated 18 +1 2d ago A 26 tokens

issue-tracker

257

celados/mcpx

Agent Claude Code

GitHub issue workflow used by engineering skills in celados/mcpx.

not rated 17 3d ago A 15 tokens original MIT

memcp-analyzer

258

maydali28/memcp

Agent Claude Code

Analyze a MemCP context using the RLM peek-identify-load-analyze pattern. Use proactively when answering questions about stored content without loading it all into the main context.

not rated 17 4mo ago A 39 tokens original MIT

analyzer

259

HarKro753/claude-copy

Agent Claude Code

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

not rated 17 1mo ago A 0 tokens copy · 100% MIT

code-simplifier

260

WaniWani-AI/sdk

Agent Claude Code

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

not rated 17 yesterday A 34 tokens copy · 100% MIT

planner

261

xeeva/Genesis

Agent Claude Code

You analyse a project brief and produce a detailed generation plan. Your plan determines exactly what files, agents, skills, and infrastructure the scaffold-writer and claude-infra-writer will create.

not rated 17 5mo ago A 0 tokens original MIT

delphi-driver

262

GabrielOnDelphi/Autopilot-for-Delphi

Agent Claude Code

Pure executor for scripted MCP autopilot sequences against a running Delphi target. Use when you have a KNOWN script of UI actions (click these N buttons, set these texts, then read these labels) and do NOT need to react to intermediate results. The parent Opus session should KEEP doing tasks that require judgement…

not rated 17 2d ago A 468 tokens

prototyper

263

IdoCohen560/claude-unity-game-studio

Agent Claude Code

Rapid prototyping specialist for pre-production. Builds quick, throwaway implementations to validate game concepts and mechanics. Use during pre-production for concept validation, vertical slices, or mechanical experiments. Standards are intentionally relaxed for speed.

not rated 17 +1 1mo ago A 47 tokens original MIT

analyzer

264

codeclawd/fable-mode

Agent Claude Code

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

not rated 16 1mo ago A 0 tokens

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: