Agents

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

reviewer

2138

rumotion/ai-agent-project-template

Agent Claude Code

Read-only review of a frozen artifact or diff using the repository reviewer contract.

not rated 1 23d ago A 18 tokens original MIT

architect

2139

hajekim/agentic-design-patterns-extension

Agent Claude Code

Agentic design pattern architect. Recommends the optimal combination of patterns from the 28-pattern library for a given problem. Use when: designing a new AI agent system, choosing patterns, comparing pattern trade-offs, planning multi-pattern architectures.

not rated 1 5mo ago A 50 tokens original MIT

security-auditor

2140

nortonx/ai-tooling-free

Agent Claude Code

Security expert preventing vulnerabilities. PROACTIVELY scan all external code.

not rated 1 28d ago A 19 tokens original MIT

ciel-systems-guild

2141

jxoesneon/Ciel

Agent Claude Code

CIEL's elite systems engineering guild. Specializes in Rust, C++, Go, Elixir, and high-performance architecture.

not rated 1 5d ago A 32 tokens original Apache-2.0

english-teacher

2142

anrylu/soul-forge

Agent Claude Code

English language correction and teaching specialist.

not rated 1 5mo ago A 10 tokens

orchestrator-agent

2143

VictorTomaili/agent-cli

Agent Claude Code

AI agent manager — the host/main agent in any agentic CLI tool. Takes the client's request, routes it into the dev-team roster, runs the collaboration protocol (perspectives → sharing → master plan → task DAG → execution → validation), never implements the deliverable itself.

not rated 1 2d ago A 60 tokens original MIT

project-agent

2145

yuri-semenenko/ai-engineering-workspace

Agent Claude Code

TEMPLATE for a project-specific implementation agent. Copy this file, rename it, and fill in the placeholders to define a dispatchable role for ONE project: the expertise it brings and how it works. The project's own stack, structure, and commands stay in that repository's root AGENTS.md, which this agent reads rather…

not rated 1 changed 8d ago A 180 tokens original MIT

query

2146

mystilleef/spae-framework

Agent Claude Code

Answer user query in read-only mode.

not rated 1 1mo ago A 10 tokens original MIT

README

2147

ecodelearn/template-claude-code-ts

Agent Claude Code

Invoque explicitamente pelo nome. Agentes rodam em seu próprio contexto com ferramentas e permissões isoladas.

not rated 1 1mo ago A 0 tokens WTFPL

research-agent

2148

Razaib-khan/ForgeWeave

Agent Claude Code

Investigates one subtopic by crawling URLs and extracting usage-focused code examples.

not rated 1 2mo ago A 14 tokens original MIT

orchestrator

2149

barisgorgun/ai-dev-team-workflows

Agent Claude Code

Feature geliştirme sürecini yöneten baş koordinatör. "geliştir", "ekle", "yap", "implement et", "feature", "özellik" gibi yeni bir iş başlatıldığında devreye girer. architect, code-reviewer, test-engineer, security-reviewer agent'larını doğru sırayla çağırır, kullanıcıdan onay gereken noktalarda durur.

not rated 1 1mo ago A 95 tokens original MIT

autopilot

2150

guib1/red-team-docker

Agent Claude Code

Autonomous hunt loop agent. Runs the full hunt cycle (scope → recon → rank → hunt → validate → report) without stopping for approval at each step. Configurable checkpoints (--paranoid, --normal, --yolo). Uses scopechecker.py for deterministic scope safety on every outbound request. Logs all requests to audit.jsonl.…

not rated 1 5mo ago A 84 tokens

frontend-specialist

2151

trinhhaox/ag-kit

Agent Claude Code

Senior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.

not rated 1 1mo ago A 63 tokens

ba

2152

Yugoge/awesome-claude-harness

Agent Claude Code

Business analyst subagent for requirements analysis and context building. Receives user requirement text, performs git analysis, identifies affected files, and returns either clarification questions or dual-format output (Markdown spec + JSON context).

not rated 1 yesterday A 43 tokens

index

2153

jaydubya818/governed-claude-subagents

Agent Claude Code

Agent "index" from jaydubya818/governed-claude-subagents, covering claude code sub-agent index, 🎯 orchestration & management (8 agents), 🏗️ development & architecture (32 agents), 🎨 design & ux (8 agents) and 🔧 quality assurance & testing (18 agents).

not rated 1 13d ago A 0 tokens original MIT

second-opinion

2154

sdolard/awesome-claude-config

Agent Claude Code

Read-only second opinion at a different model tier, for architecture-scoped plans, stuck-debugging escalation, and ad-hoc algorithmic/logic decisions. Invoked explicitly per rules/architecture-review.md — not matched via delegation keywords.

not rated 1 1mo ago A 51 tokens

Lord1Egypt/awesome-prompt-forge

Agent Claude Code

Expert change management specialist using ADKAR, Kotter, and Prosci frameworks to guide organizations through technology implementations, restructuring, culture transformation, and M&A integration — managing resistance, building adoption, and ensuring changes stick long after go-live.

not rated 1 3mo ago A 51 tokens

python-expert

2157

obre10off/awesome-claude-code-agents

Agent Claude Code

Elite Python specialist mastering advanced features, async programming, and Pythonic patterns. Expert in decorators, generators, context managers, and performance optimization. Use PROACTIVELY for Python development, refactoring, or when dealing with complex Python features.

not rated 1 1y ago A 52 tokens

codex-audit

2158

roarista/awesome-harness

Agent Claude CodeCodex

The AUDITOR (codex voice). THE PROCEDURE step 6 (VERIFY), routed to Codex per Ro's directive 2026-08-02 ("queremos usar Codex más porque nos dan más créditos"). Reads a diff or finished unit against its spec, reports findings, and stops. It NEVER edits and NEVER spawns anything — this agent has no Write/Edit tools at…

not rated 1 17d ago A 363 tokens original MIT

code-reviewer

2159

tsingke/claude-tutorials

Agent Claude Code

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

not rated 1 3mo ago A 52 tokens

orchestrator

2160

arkatom/ai-instructions

Agent Claude Code

Master orchestrator that coordinates multiple sub-agents for complex multi-domain tasks.

not rated 1 10mo ago A 18 tokens original 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: