Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
wly-lizhong/claude-config-skills
Agent Claude Code
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication…
ivanhoinacki/team-exp-claude-config
Agent Claude Code
Daily copilot. Accumulated memory across all conversations, full vertical context. Use as default conversation mode: ask questions, verify decisions, discuss trade-offs. Lightweight startup: context loaded on demand, not automatically. Triggers: "copilot", "chat", "update me", "what do we have", "context".
rodrigoratouu-code/saas-factory-setup
Agent Claude Code
Tiempo: 25 minutos Prerequisitos: Bloque 01 (Chat Streaming), Supabase configurado.
cwoodruff/dotnet-claude-code-kit
Agent Claude Code
Plans large refactors, framework upgrades, and legacy modernization for .NET solutions. Produces phased plans with risk and effort estimates. Use for audits of legacy code or "should we modernize or rewrite" questions. Read-only.
BuaaJoseph/claude-code-best-practice-zh
Agent Claude Code
A software-engineering work process for clarifying requirements, planning milestones, testing changes, and preparing pull requests. TDD means writing tests before the code they check.
Agent Claude Code
Records manual browser interactions and generates natural language test scripts with rich locator metadata and assertion capture. Use when asked to "record a test", "capture actions", or "record UI steps".
Agent Claude Code
Backend Developer Agent Persona.
Agent Claude Code
Creates test strategy, Apex test classes, LWC Jest tests, validation checklists, and regression checklists. Ensures code coverage, edge cases, and security scenarios are covered.
Agent Claude Code
Detective focused on semantic search to discover what exists in the codebase related to a topic.
Agent Claude CodeCursor
Agent "orchestrator" from jy315189/everything-cursor, covering agent — ai project manager, identity, thinking process, step 1: classify the task and step 2: announce the plan.
Agent Claude Code
Domain expert who reads the system from the outside in — by what it produces, what it gets right, and where it gets things wrong. Holds the deep-rigour pockets the rest of the team doesn't have time to hold. Use during big-picture storms, regulatory or correctness review, and any work where domain truth matters more…
Agent Claude Code
Review backend designs, TRDs, architecture changes, module boundaries, API contracts, and implementation plans before coding. Use for high-risk or cross-cutting backend work.
Agent Claude Code
Use this agent when you need to analyze CodeRabbit's pull request reviews and either implement fixes for valid feedback or provide justifications for invalid feedback. This agent should be triggered after CodeRabbit has completed its review of a pull request on GitHub. Examples:\n\n \nContext: The user has pushed code…
Agent Claude Code
A research agent for studying open-source software and libraries. Open source means the source code is available for inspection, and the agent examines repositories directly to find implementation details and design patterns.
Agent Claude Code
An agent that reviews work plans and designs from several viewpoints, looking for risks, weak reasoning, and unanswered questions.
Omed0/convex-selfhost-starterkit
Agent Claude Code
Convex performance review specialist. Reviews queries/mutations for scalability issues, index usage, aggregate patterns, and best practices. Assumes millions of documents per table. Focuses on O(log n) vs O(n) operations, proper edge usage, and streaming patterns.
Agent Claude Code
Subagent that runs the AI-SDLC framework end-to-end in an isolated context. Use when delegating a full SDLC session to keep the main conversation lean. The subagent boots from .ai-sdlc/ENTRY.md and executes phases sequentially, returning a summary on completion.
Agent Claude Code
Creates modern Angular v20+ applications with signals, standalone components, and latest control flow syntax.
Agent Claude Code
A senior software architect agent. Use when you need high-quality architecture documentation based on vague, incomplete, or complex prompts. Supports multi-tier architecture, cloud-native designs, API specs, and implementation roadmaps.
TrevorEdris/fellowship-of-the-workflows
Agent Claude Code
Use this agent for comprehensive WCAG accessibility auditing of web interfaces. Covers all four POUR principles, keyboard navigation, screen reader compatibility, color contrast, ARIA patterns, and semantic HTML. Requires Playwright MCP for live browser testing.
Agent Claude Code
Supergroup interaction agent for Info-Sentry. Listens in the Feedback forum topic, processes inline button callbacks from Main-News and Predictions, and lets the user manage their tracked interests through natural language. Runs on DeepSeek V3.2.
Agent Claude Code
You are a UI designer who creates interfaces that are both beautiful and implementable. You design through code—React components, HTML/CSS, Tailwind—and produce working UI that developers can use directly. You understand modern design trends, platform conventions, and the balance between innovation and usability.
Agent Claude Code
The GDScript specialist owns all GDScript code quality: static typing enforcement, design patterns, signal architecture, coroutine patterns, performance optimization, and GDScript-specific idioms. They ensure clean, typed, and performant GDScript across the project.
Agent Claude Code
Hunts latent bugs — race conditions, off-by-one, null deref, unbounded loops, integer overflow, encoding mismatches, time-of-check/time-of-use.
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: