Agents

Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.

clnode-reviewer

841

SierraDevsec/clnode

Agent Claude Code

Code reviewer — quality, security, performance, and pattern consistency.

not rated 25 9mo ago A 17 tokens

documentation-writer

842

raphaelmansuy/adk-code

Agent Claude Code

Technical writer creating clear, comprehensive documentation. Use when writing READMEs, API docs, guides, or improving documentation quality.

not rated 25 +1 6mo ago A 29 tokens

code-reviewer

843

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 25 yesterday A 0 tokens original MIT

planner

844

hzy970907/fish-claude-code

Agent Claude Code

Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.

not rated 25 8mo ago A 37 tokens

orchestrator

845

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 25 +1 1mo ago A 40 tokens AGPL-3.0

dev-qc

846

minhduc2803/shipyard

Agent Claude Code

Background dev-site QC agent for the parallel feature harness — the harness-integrated equivalent of playwright-dev-qa-tester. Spawned by the ship-feature skill at Stage 13 (runinbackground) right after a HUMAN merges the lane's PR into development — the post-merge verification that decides whether the topic is done…

not rated 25 3mo ago A 228 tokens

qa-scorer

847

charlie947/agent-harness-starter

Agent Claude Code

Hard quality gate. Scores the builder's output against a defined rubric. Returns PASS only if the score clears the threshold. Returns a specific list of lost points if below threshold so the builder can fix. Never lets sub-threshold work through to the user.

not rated 25 +1 1mo ago A 56 tokens original MIT

mcp-pr-reviewer

848

stacklok/toolhive-catalog

Agent Claude Code

Autonomous PR reviewer for MCP server updates and additions. Reviews PRs that modify server.json files in the registry, determines compliance, and approves/merges safe changes. Use when processing MCP server PRs in bulk or reviewing individual PRs.

not rated 25 +1 yesterday A 55 tokens original Apache-2.0

tdd-implementer

849

kirillgreen/skills

Agent Claude Code

Implement minimal code to pass failing tests for TDD GREEN phase. Reads the test file and writes minimum implementation. NEVER modifies test files. Raises specdefect: true instead of weakening tests when the spec is contradictory, unimplementable, or under-specified. Returns files, success output, and specdefect…

not rated 25 1mo ago A 70 tokens original CC0-1.0

direito-digital-lgpd

850

asv-digital/agents-advogados

Agent Claude Code

Especialista em Direito Digital e LGPD (Lei 13.709/2018) — resposta a incidente de seguranca / data breach (art. 48 — comunicacao a ANPD e titulares), parecer juridico LGPD, defesa em acao de dano moral por uso indevido de dados, RIPD/DPIA (Relatorio de Impacto a Protecao de Dados — art. 38), contrato com operador…

not rated 25 +2 6mo ago A 0 tokens

tikz-reviewer

851

ericluo04/claude-academic-workflow

Agent Claude Code

Adversarial visual critic for a rendered TikZ diagram. Looks at the actual PNG and reports overlaps, geometric errors, and spacing failures, each backed by explicit arithmetic. Use after writing or editing TikZ, or as the review step inside the compile-latex --figures loop.

not rated 25 changed 1mo ago A 62 tokens

pm

852

5throck/ai-workspace-standards

Agent Claude Code

Orchestrates Phases 0, 1-2, 5. Enforces quality gates. Decides agent hiring/firing and approves agent skill requests. Use when: "Managing workflow", "Coordinating multi-phase tasks", "PM orchestration needed".

not rated 25 +2 changed 7d ago A 56 tokens AGPL-3.0

matteocervelli/llms

Agent Claude Code

Coordinates sequential validation specialists with recursive communication to ensure code quality, test coverage, and security compliance before deployment.

not rated 25 5mo ago A 26 tokens original MIT

deep-researcher

854

gohypergiant/agent-skills

Agent Claude Code

Use when a task needs current, multi-source web research and evidence-backed synthesis, including comparisons, landscape analyses, literature reviews, or research before producing fact-dependent content. Do not use for simple lookups, local repository investigation, or implementation work without an external-research…

not rated 25 19d ago A 60 tokens original Apache-2.0

analyzer

855

robonuggets/agentic-ai-starter-kit

Agent Claude Code

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

not rated 24 +2 5mo ago A 0 tokens

dynamo_expert

856

AIFlowML/cursor_rules

Agent Claude Code

I am the NVIDIA Dynamo Expert Agent, specialized in all aspects of NVIDIA's high-throughput, low-latency inference framework for distributed LLM serving. I possess comprehensive knowledge of Dynamo's architecture, deployment strategies, performance optimization, and operational best practices.

not rated 24 1y ago A 0 tokens

ooloth/dotfiles

Agent Claude Code

Use to see or verify anything a web browser shows - that a page or UI change renders, console errors, clicking through a flow, screenshots. The main session has no browser tools; this agent brings its own Playwright.

not rated 24 changed 9d ago A 50 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 7mo ago A 0 tokens original Apache-2.0

codebase-explorer

859

DFilipeS/praxis

Agent Claude Code

Explores the repository to find code relevant to a given topic. Use when planning or investigating existing code before making changes.

not rated 24 7mo ago A 29 tokens

master-orchestrator

860

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 12mo ago A 86 tokens original MIT

implementer

861

ZhuHongji626/ClaudeCodeSaveToken

Agent Claude Code

A code-implementation specialist that turns requirements or a specification into working software.

not rated 24 3mo ago A 53 tokens

c4-diagram-generator

862

Trettin/docforge

Agent Claude Code

Use this agent when the user needs to generate C4 diagrams (System Context, Container, Component, and Code levels) in PlantUML format from a Feature Design Document (FDD) or similar technical documentation. The agent should be invoked in scenarios such as:\n\n \nContext: User has completed writing an FDD and wants to…

not rated 24 11mo ago A 0 tokens

analyst

864

wangjianjq/Skill

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 24 8mo ago A 5 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: