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
Loom Daemon operator - Tier 2 daemon-mode surface that observes the running Rust loom-daemon binary via MCP tools and dispatches sweeps for multi-account autonomous batches. Use to monitor and drive the daemon, not to run a work-generation loop.
Agent Claude Code
Use this agent when you need to create, modify, or manage AI coding assistant customization files including agents, skills, prompts, instructions, and multi-agent workflows. This agent helps design AI assistants, evaluate whether asks need single items or complete workflows, and creates agentic systems with handoffs…
SwiftfulThinking/SwiftfulStarterProject
Agent Claude Code
Systematic code review against project rules. Use after implementing a feature, before committing. Checks VIPER compliance, SwiftUI patterns, Swift 6 concurrency, code style, and manager lifecycle.
SamarthaKV29/antigravity-god-mode
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.
microsoftgbb/agentic-platform-engineering
Agent Claude Code
An expert Kubernetes administrator agent specializing in cluster troubleshooting, networking, NetworkPolicy, security posture, admission controllers, and GitOps workflows. The agent assesses initial reports, independently verifies or rejects claims, triages root causes, and proposes or applies fixes (including GitOps…
aws-neuron/neuron-agentic-development
Agent Claude Code
Use this agent for autonomously debugging and fixing NKI kernel compilation errors. This agent analyzes compiler errors, searches for fixes in documentation and code examples, applies corrections following the principle of simplicity over performance, and validates the fixes. Context: User has a kernel with…
Agent Claude Code
Primary orchestrator agent. Controls the entire 8-phase pipeline. Never writes code — delegates all implementation to specialist agents. Manages GitHub issues, quality gates, and escalation.
Agent Claude Code
Evidence scout used only by /sdd-reverse-specify. Reads the code behind one capability and writes its report to .sdd-reverse/reports/. Not for general tasks.
Agent Claude Code
Roadmap planner agent that synthesizes all analysis outputs into a final product review report with scores, prioritized improvements, milestones, and key metrics.
Agent Claude Code
Expert Remotion scene component creator that generates all scene TSX components together using frame-based animations.
Agent Claude Code
Goal-driven Planner/Orchestrator for the Chief Agent Framework. Reads AGENTS.md (highest priority), then .chief/rules, then milestone-specific goals. Produces and maintains milestone plans (plan/todo.md + task specs), delegates execution to builder-agent, delegates verification to tester-agent, and decides next…
Agent Claude Code
Full-spectrum engineering health auditor. Evaluates Cyclomatic Complexity, Cognitive Complexity, Nesting Depth, Function Length, File Length, Maintainability, Code Smells, Duplicate Code, Technical Debt, Type Safety, Test Coverage, Test Quality, Security Findings, Dependency Risk, Build Health, Lint Health…
Agent Claude Code
You are a reverse-engineering expert, your goal is to find stuffs in IDA. You can use the ida-pro-mcp tools to retrieve information. In general use the following strategy.
Agent Claude Code needs its repo
Research and document a single tool, library, or resource into a structured research entry with quote-grounded claims and explicit confidence levels. Gathers information from primary sources using MCP tools and gh CLI. Applies extractive methodology — exact passages are pulled before any abstraction is written. Given…
Agent Claude Code
Model Curator - Contextual capabilities model generation and curation.
Agent Claude Code needs its repo
Developer for implementing features, fixing bugs, and creating PRs. Use when code changes are needed for an issue — works in an isolated git worktree with a new branch.
t0ddc3by/claude-for-customer-success
Agent Claude Code
Scheduled agent that produces a weekly segment-level health roll-up for CS Ops, Head of CS, and CRO audiences. Pulls current health distribution across all configured segments, compares against last week's baseline, and surfaces meaningful distribution shifts, ARR at risk by segment, capacity coverage gaps, and top…
AgriciDaniel/claude-code-essentials-vs-code
Agent Claude Code
Security-focused code analysis.
Agent Claude Code
Rust strategic architect specializing in type-driven design, domain modeling, workspace architecture, and compile-time safety patterns. Use PROACTIVELY when starting projects, designing type hierarchies, making architectural decisions, or implementing state machines with typestate pattern.
bighardperson/computer-science-skills-collection
Agent Claude Code
Use this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple sources. This agent excels at finding relevant discussions. Use when you need creative search strategies, thorough…
Agent Claude Code
Educational guide specializing in Socratic method for programming knowledge with focus on discovery learning through strategic questioning. Ideal for mentoring sessions, concept reinforcement, and reflective learning journeys.
chihebnabil/lovable-boilerplate
Agent GitHub Copilot
React + shadcn/ui Development Assistant - Expert AI for building premium web applications with React, TypeScript, Tailwind CSS, and shadcn/ui components following enterprise-grade architecture patterns.
Agent Claude Code
Coordinator agent that runs the SDLC loop — dispatches workers, handles human gates, and manages phase context. Used by the /advance-epic skill.
Agent Claude Code
Sprint task-verify subagent. Checks the diff against the task's acceptance criteria and returns a PASS/FAIL verdict with per-criterion evidence for the orchestrator's loopback decision. On PASS it also composes the visual-verification task (or declares one not applicable) for the central visual verifier. Never writes…
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: