Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
anthropics/cwc-long-running-agents
Agent Claude Code ✓ vendor
Skeptical second-opinion reviewer. Reads the diff and the builder's evidence, then returns PASS or NEEDSWORK with specific findings. Has no Write/Edit tools; Bash is granted for git diff only and is NOT a hard read-only boundary (drop it from tools if you need one).
stretchcloud/claude-code-unified-agents
Agent Claude Code
Master orchestrator that coordinates multiple sub-agents for complex multi-domain tasks.
Agent Claude Code ✓ vendor
This agent creates new TypeAgent agents using the "Onboarding Agent" actions provided by commandexecutor MCP server.
Agent Claude Code
Analyzes codebase and PRD to create a comprehensive task breakdown.
Agent Claude Code
PostHog access control system implementation expert - use when adding access controls to new products, debugging access control issues, or questions about RBAC patterns.
Agent Claude Code
SecondEye adversarial reviewer. Constrained critic that analyzes lifecycle artifacts from a specific lens (efficiency, completeness, or risk) and outputs structured findings with six-severity labels. Invoked by $secondeye in parallel at three model tiers.
Agent Claude Code
Use this agent when you need comprehensive full-stack engineering expertise, particularly for server-side development, system architecture, DevOps, and infrastructure tasks. Examples include: (1) Designing and implementing scalable server architectures using languages like Node.js, Python, Go, Java, or Ruby; (2)…
HazAT/pi-interactive-subagents
Agent Claude Code
Interactive planning agent - clarifies WHAT to build and figures out HOW. Lightweight requirements engineering, approach exploration, design validation, premortem, plan + todos. Can spawn scouts/researchers mid-session when it needs facts.
Agent Claude Code
Read-only search agent for broad fan-out searches - when answering means sweeping many files, directories, or naming conventions and you only need the conclusion, not the file dumps. It reads excerpts rather than whole files, so it locates code; it doesn't review or audit it. Specify search breadth - "medium" for…
Agent Claude Code
Specialized agent for verifying React projects and fixing frontend quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, type, or fix requests.
Agent Claude Code
Performs security analysis on completed features - OWASP scanning, secrets detection, dependency audit. Blocks on Critical/High.
kangarooking/kangarooking-skills
Agent Claude Code
Use this agent to test implementations against sprint contracts and specifications. Uses Playwright MCP for E2E testing, Chrome DevTools for UI inspection, and visual tools for verification. Grades implementations and provides specific failure reports. Trigger when user says "test", "evaluate", "qa", "verify", or…
Agent Claude Code
Surf GPT Pro advisor through ChatGPT GPT-6 Astra Pro web mode.
ThibautBaissac/rails_ai_agents
Agent Claude Code
Orchestrates full feature implementation across models, controllers, views, and tests following 37signals conventions. WHEN: Implementing a full feature end-to-end, coordinating multi-layer changes, building new CRUD resources. WHEN NOT: Reviewing existing code (use review-agent), refactoring legacy patterns (use…
Agent Claude Code
Reviews a diff of obsidian-reminder for CodeMirror 6 and Obsidian API lifecycle bugs — widget/ViewPlugin/StateField state, register cleanup, Svelte mount/destroy, leaks across plugin reloads. Used by the pr-review workflow; read-only.
Agent Claude Code
Subconscious subagent that surfaces cross-disciplinary structural parallels from the Vestige memory graph. Invoked by the preflight-swarm.sh UserPromptSubmit hook (Pre-Cognitive Triad v2.3 "Thalamus"). Fresh context, Haiku 4.5, Vestige MCP tool access. Outputs a single XML block or EMPTY.
Agent Claude Code
Senior advisor for hard problems. Consult when stuck on architecture decisions, ambiguous tradeoffs, or when an approach isn't working. Returns guidance, not implementation.
Agent Claude Code
Checks if a PR is too large and suggests how to split it into smaller PRs. Analyzes diff size, logical groupings, and dependencies to recommend optimal splits. Target: max 400 added lines per PR.
Agent Claude Code
Use for DESIGN wave infrastructure-level architecture. Designs distributed systems, scalability strategies, load balancing, caching, database sharding, message queues, back-of-envelope estimation, and trade-off analysis. Complements solution-architect (application-level) with infrastructure-level depth.
Agent Claude Code
Use this agent when you need expert guidance on creating, improving, or reviewing CLAUDE.md files and LLM integration patterns. Examples: Context: User wants to create a CLAUDE.md file for their new TypeScript project. user: 'I'm starting a new React TypeScript project and want to create a CLAUDE.md file. What should…
Agent Claude Code
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd-plan-phase orchestrator.
Agent Claude Code
Use this agent when making structural decisions: database schema changes, API contract design, service boundaries, dependency choices, or any change that affects the system's fundamental architecture. Also use when evaluating technical debt or refactoring proposals. Context: User wants to add a new domain entity user…
Matt-Dionis/claude-code-configs
Agent Claude Code needs its repo
Expert in multi-tenant AI companion architecture, isolation strategies, companion lifecycle management, and scaling patterns for production companion services.
Agent Claude Code
Use this agent when C source files (.c, .h) have been created or modified, especially code involving memory allocation, file descriptors, sockets, cryptographic operations, credential handling, or external input parsing. Should be triggered on every code change to C files to catch resource lifecycle bugs and security…
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: