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
Use this agent when the user explicitly requests data modeling assistance or asks to analyze data sources for creating storage schemas or reports. This agent should be invoked as a standalone task and is NOT meant to run proactively. Examples of when to use:\n\n \nuser: "Can you analyze our user database table and…
Agent Claude Code
Create PRDs through structured discovery.
christianestay/claude-code-base-project
Agent Claude Code
Implementa features complejas (>3 archivos) en monorepo Turborepo. Trabaja con contexto aislado. Usar para features completas, refactorizaciones grandes, o migraciones. Invocar ante "implementar", "crear módulo", "refactorizar", "migrar", "feature completa".
Agent Claude Code
Reviews and critiques a drafted HBS-style teaching case. Verifies facts and references against primary/credible sources via web search, checks HBS style fidelity and pedagogical soundness, and produces a scored report with required revisions. Use after the hbs-case-writer drafts a case. This is a CRITIC agent — it…
Agent Claude Code
Reviews a supplied diff for introduced, concrete design and maintainability hazards. Use only when dispatched by the code-review skill.
Agent Claude Code ✓ vendor
Autonomous QA engineer for Android apps. Runs user scenarios on a connected emulator or device, reads UI state via element tree, checks logcat, and produces a structured PASS / FAIL / BLOCKED report. Does NOT modify source code or run builds.
Agent Claude Code
An image and video analysis agent that uses the Mimo V2.5 model to examine visual content.
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.
davidmatousek/agentic-oriented-development-kit
Agent Claude Code
This document provides comprehensive guidance for designing, customizing, and maintaining agents in Agentic Oriented Development Kit.
codingthefuturewithai/mcp-cookie-cutter
Agent Claude Code
Use this agent when you need to analyze code for security vulnerabilities, unsafe patterns, or potential security risks. Trigger this agent proactively after code changes that involve: authentication/authorization logic, data validation/sanitization, external API interactions, file system operations, database queries…
Agent Claude Code
Build React components, implement responsive layouts, and handle client-side state management. Masters React, Vite and TypeScript, and modern frontend architecture. Optimizes performance and ensures accessibility. Use PROACTIVELY when creating UI components or fixing frontend issues.
Agent Claude Code
An agent for auditing AI prompt development against company standards. It reviews prompt structure, type definitions, safety controls, versioning, tests, and requirements for different use cases.
Agent Claude Code
Multi-Agent Coordination System that spawns and synthesizes analysis from specialist agents.
Agent Claude Code
Platform optimization specialist analyzing readiness for Google AI Overviews, ChatGPT web search, Perplexity AI, Google Gemini, and Bing Copilot.
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.
Agent Claude Code
Technical SEO specialist analyzing crawlability, indexability, security, URL structure, mobile optimization, Core Web Vitals (INP replaces FID), server-side rendering, and JavaScript dependency.
F-U-S-E-E/FuseDevelopmentGroup
Agent Claude Code
Design and maintain Roslyn incremental source generators with strict pipeline discipline, parser vs emitter separation, and long-term maintainability for large generator suites.
Agent Claude Code
Use this agent when the user asks to write, create, or draft an SEO-optimized article, blog post, or page. This includes requests involving keyword optimization, internal linking (maillage interne), content strategy, or any web content that needs to rank well on search engines. Examples: Context: The user wants to…
Agent Claude Code
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by {{COMMANDPREFIX}}new-project or {{COMMANDPREFIX}}new-milestone orchestrators.
gracefullight/docusaurus-plugins
Agent Claude Code
Bug diagnosis and fix specialist. Error analysis, root cause identification, regression test writing.
Agent Claude Code
Use this agent to create audio and video assets using Google NotebookLM. Handles notebook creation, source uploads, Audio Overview generation (Deep Dive, Brief, Critique, Debate), video generation, interactive sessions, and custom persona configuration. Use when you need to transform documents into podcasts, explainer…
lucasrosati/claude-security-agents
Agent Claude Code
Defensive security specialist. Use to apply vulnerability fixes, security hardening, security headers implementation, rate limiting, and automated security tests. Works on top of red-team-scanner reports.
Agent Claude Code
Iterative OpenAPI improvement subagent. Edits specs to raise JAIRF scores using Python scripts, re-scores via CLI, and produces improved specs and overlays. Spawned by the jentic-api-improve skill — do not invoke directly.
Agent Claude Code
Converts a clean human plan into an execution graph — steps, component wiring, model choices, pattern references, and verify commands.
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: