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
React Native mobile implementation specialist. Builds features using the 3-file split pattern (hook/view/glue) with React Native, NativeWind, React Navigation, and React Native Reusables (shadcn/ui for RN). Use when implementing mobile app features, screens, or native components.
memorysaver/Looplia-Tauri-V2-concept
Agent Claude Code
Document original media materials with journalistic rigor to provide comprehensive source material for future writing.
Agent Claude Code
Skeptical product manager for HydraFlow. Reviews the find queue, epics, roadmaps, and specs for outcome coverage, right-sizing, priority correctness, and stillness alignment. Verdict-driven; evidence-named findings; no cheerleading.
Agent Claude Code
🐝 Swarm Command — multi-model consensus swarm orchestrator. Launches 50-250+ AI agents across 15 models with hierarchical fan-out, cross-family review, shadow scoring, and quality-gated synthesis. Say "swarm command", "swarmcommand", or "swarm250" to start.
Federated-Industrial-Laboratories/agentbus
Agent Claude Code
Adversarial review of work products the reviewer did not build. Reports verified defects separately from suspicions, severity-ranked. Use to verify builds, audits, and releases with an outside eye.
Agent Claude Code
Implements a GitHub issue in the demo-app project.
akikisai/copilot-custom-config-template
Agent Claude Code
An advisor for AWS infrastructure and CDK code. AWS is Amazon's cloud platform, while CDK is a way to define cloud infrastructure in code.
Agent Claude Code needs its repo
An end-to-end assistant workflow for developing NuttX device drivers, reviewing them, creating tests, or adapting AUTOSAR MCAL modules. NuttX is an operating system for embedded devices, and a device driver lets that system communicate with hardware.
driftnode986/claude-multiagent-guide-en-samples
Agent Claude Code
Audits code for security vulnerabilities including OWASP Top 10. Use proactively when reviewing authentication, authorization, input handling, or data storage code.
fadhlirahim/claude-starter-kit
Agent Claude Code
You are a senior code reviewer for a TanStack Start + tRPC + better-auth + Drizzle + Zod 4 project.
Cumulocity-IoT/cumulocity-skills
Agent Claude Code
Use when you want to interact with Cumulocity IoT via the c8y CLI. Handles session setup, command discovery, execution, and JSON output processing. Trigger phrases: c8y, cumulocity, devices, alarms, events, measurements, operations, inventory, tenant, list devices, query cumulocity.
Agent Claude CodeOpenCode
Loop9 controller (orchestrates solver/validator/refiner with sharded IO). FIXED variant (force direct orchestration; no loop9 command/skill bounce).
LEg-er/academic-research-skills-opencode
Agent Claude Code
Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases.
Agent Claude Code
An agent for writing professional reports, work summaries, project documents, and other formal reporting materials.
Agent Claude Code
Expert Claude Code skill reviewer that validates skills against official Anthropic specifications AND effectiveness for auto-invocation with deterministic scoring. Use PROACTIVELY after creating or modifying any SKILL.md file to ensure compliance with official requirements AND that the skill will actually be…
Agent Claude Code
A DevOps specialist for building and operating software delivery systems. DevOps combines development and operations work, including automated testing, packaging, and deployment.
Agent Claude Code
Autonomously execute ANY technical guide built by the technical-guide-architect skill. Use when prompted with "run guide", "execute guide", "run technical guide [name]", or given a path to a technical guide markdown file. Parses the guide structure dynamically and executes all stages, phases, and prompts sequentially…
Agent Claude Code
Code review subagent — checks correctness, security, and style.
Seeed-Solution/csg-design-system
Agent Claude Code
Replaces hardcoded style values in an existing project with CSG Design System tokens from DESIGN.md. Scans the full codebase, imports tokens, swaps values, and generates a migration report.
Agent Claude CodeOpenCode
TDD-focused implementation agent. Enforces strict RED → GREEN → VALIDATE → REFACTOR cycle. Works with or without plan files. Delegates specialized work to subagents.
Agent Claude Code
Use when designing high-availability database topology — covers read replica setup, primary/standby failover, connection pooling, and streaming replication configuration. Part of the database-architect harness.
Agent Claude Code
Delegates self-contained tasks to OpenAI Codex MCP for independent parallel execution. Use for orthogonal tasks that benefit from a separate context window and autonomous work.
Agent Claude Code
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
regen-coordination/org-os-template
Agent Claude Code
Operates org-os instances — sessions, registries, memory, federation — with vault-safe discipline.
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: