Agents for Claude Code

poco-ai/poco-claw

Agent Claude Code

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

hesreallyhim/a-list-of-claude-code-agents

Agent Claude Code

Use this agent when you need comprehensive code review from a senior fullstack developer perspective, including analysis of code quality, architecture decisions, security vulnerabilities, performance implications, and adherence to best practices. Examples: Context: User has just implemented a new authentication system…

mohitagw15856/pm-claude-skills

Agent Claude Code

Customer success partner for account health, churn risk, renewals, escalations, and QBRs. Use to score an account, diagnose churn, prep a renewal or QBR, or write an escalation brief. Computes the weighted health score programmatically.

obot-platform/nanobot

Agent Claude Code

You are a helpful shopping assistant for the shopify.supply store.

qdhenry/Claude-Command-Suite

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…

nrslib/takt

Agent Claude Code

You are a team leader for worker-pool E2E testing.

Team-Commonly/commonly

Agent Claude Code

Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.

uluckyXH/OpenMOSS

Agent Claude Code

A backend engineering agent that builds server-side features such as APIs, databases, and command-line tools.

fastclaw-ai/fastclaw

Agent Claude Code

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

microsoft/waza

Agent Claude Code ✓ vendor

Your AI team. Describe what you're building, get a team of specialists that live in your repo.

Xiangyue-Zhang/auto-deep-researcher-24x7

Agent Claude Code

Experiment implementation, execution, and monitoring.

SmythOS/sre

Agent Claude Code

Worker mode allows an agent to dispatch complex, long-running tasks to background "copy" agents while the main agent stays fully interactive. When a worker finishes, its result is automatically surfaced back to the user through the main agent's conversation.

higress-group/himarket

Agent Claude Code

Verify that implemented features actually work by executing realistic functional scenarios against a running application.

najmuzzaman-mohammad/gawkbot

Agent Claude Code

A multi-agent rhythm for reviewing a single PR through several narrowly-scoped lenses to catch issues that one reviewer would miss.

revfactory/harness-100

Agent Claude Code

YouTube production reviewer (QA). Cross-validates consistency across strategy, script, thumbnail, and SEO. Identifies gaps, contradictions, and quality issues and provides actionable feedback.

coollabsio/jean

Agent Claude Code

Use this agent when you need to create or update technical documentation that helps developers understand the deep patterns, mental models, and architectural decisions of this codebase. Examples: Context: After implementing a new state management pattern using Zustand stores with specific naming conventions and data…

cbrock84/headcount

Agent Claude Code

Reviewer-class. Read-only review of what other departments commit to — contract terms, privacy and data handling, risk acceptance, and compliance findings. Holds no write surface. Its findings are not overrulable by the department under review.

uzairansaruzi/hermex

Agent Claude Code

Which app state is per-server versus intentionally global, where each lives, and which tests guard the isolation. Almost all isolation holds by construction through the server-keyed view tree and cache keys described below; "Clear Offline Cache" is explicitly scoped to the active server.

grafbase/grafbase

Agent Claude Code

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.

inclusionAI/AWorld

Agent Claude Code

Expert in analyzing code structure, complexity, design patterns, and providing refactoring recommendations. Uses CAST (Code Abstract Syntax Tree) tools for deep code understanding.

NomaDamas/slides-grab

Agent Claude Code

Run the slides-grab design gate before export.

mozilla-ai/any-agent

Agent Claude Code

Callbacks provide hooks into the lifecycle of an AnyAgent execution. Using callbacks, you can monitor, control, and extend agent behavior without modifying the core underlying agent logic.

open-gsd/gsd-pi

Agent Claude Code

OWASP security audit, dependency risks, and secrets detection.

CreminiAI/skillpack

Agent Claude Code

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