Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
Agent Claude Code
An architect for large software tasks who first turns requirements into a written specification and then divides the work into self-contained task packets. It also records dependencies and suggested ownership.
Agent Claude Code
Adversarial single-lens reviewer invoked by ship- skills (design, create-plan) to try to break an artifact through one specified lens. Read-only. Returns structured findings + a verdict.
Agent Claude Code
Use this agent when you need to design, create, or improve UI/UX for any feature or component in the project. This includes creating or updating the Semantic Design System, generating UI designs for web or mobile, implementing components with proper design patterns, or reviewing existing UI for improvements. This…
Agent Claude Code
Research and analysis specialist. Use for technical research, library comparison, CVE investigation, market analysis, dependency research, or feasibility analysis before architectural decisions. On-demand only.
RichardHightower/reliable-agentic-lab
Agent Claude Code
Writes one section of the white paper from verified claims only. Writes under sections/ and nothing else. Assembly owns paper.md.
Agent Claude Code
Use when you need a dedicated security audit. Checks for OWASP top 10, injection flaws, auth issues, secrets in code, and insecure dependencies. Invoke before any security-sensitive release.
Agent Claude Code
GSD-Lite Protocol — Pair programming with AI agents while maintaining ownership of reasoning and decisions.
Agent Claude Code
Orquestador principal. Recibe la solicitud del usuario, selecciona el workflow adecuado y coordina a los subagentes. NUNCA implementa directamente.
Agent Claude Code
Use when assembling and optimizing multi-agent teams to execute complex projects that require careful task decomposition, agent capability matching, and workflow coordination.
Agent Claude Code
stub for the scaffolded example.
AbdulmalekAlshugaa/claude-agents-fullstack
Agent Claude Code
Use after implementing a change and before committing/PR. Reviews the current diff for correctness, security, database pitfalls (Postgres/Drizzle or MongoDB), TanStack Query cache bugs, and Next.js mistakes. Read-only; returns findings ranked by severity.
Agent Claude Code
Orchestrates feature development across the project. Receives an approved implementation plan, identifies affected files, delegates work to the developer, routes changes through code review and security review gates, coordinates fixes when a gate fails, then hands off to the tester for a gated commit and the…
Agent Claude Code
This directory contains the 12 Claude Code agents that implement the SpecRoute skeleton. They are project-internal - they build SpecRoute itself, not consumer-facing templates that ship as artifacts.
Agent Claude Code
Builds complete circuits from requirements or reference designs. Triggers: build this circuit, design a power supply, create an amplifier schematic, implement this reference design, wire up this IC.
RaNDoM6913/claude-code-superkit
Agent Claude Code
Multi-source debug — Docker logs, Redis inspection, SQL diagnostics, git blame, execution traces.
Agent Claude Code
A code-review agent for C projects that checks coding standards, quality, security, architecture, performance, and unused or repeated code.
Agent Claude Code
Comprehensive pre-ship review of all changes since the last deploy or a specified commit. Walks correctness, atomicity/races, error handling, data-store hygiene, security, type safety, tests, integration, performance, observability, and any project-specific invariants. Use after any sprint and always before deploying.
Agent Claude Code
Coordinates multi-agent verification and review workflows — decomposes the goal, delegates to specialist subagents, and returns a structured verdict.
Agent Claude Code
Merges all sections and diagrams into final patent document.
Agent Claude Code
Cost-saving delegate backed by the GLM model (Zhipu/Z.ai). It does real repo work — read, write, edit, run commands — but ALWAYS through GLM (via mcpglmglmagent), so the work runs on GLM tokens (10x cheaper than Opus), NOT Claude. Use PROACTIVELY for cheap, well-specified, self-contained subtasks: frontend/UI…
ypollak2/claude-code-kickstart
Agent Claude Code
Checks UI code for accessibility issues — WCAG compliance, ARIA, keyboard nav, color contrast.
Agent Claude Code
Expert assistant for clooks — the persistent hook runtime for Claude Code.
Agent Claude Code
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
meesp123/claude-code-agent-team-debate
Agent Claude Code
A proxy agent for a debate command that sends a debate position to an external AI command-line tool and forwards the response to the team. It supports several external assistants, including Codex, Gemini, Qwen, Pi, and Kimi.
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: