Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
nikandr-surkov/ai-saas-starter
Agent Claude Code
Read-only reviewer for auth, billing, and credits-ledger changes. Use proactively after modifying src/lib/auth, src/lib/billing, src/lib/credits, or src/app/api — before committing.
Agent Claude Code
Agent "gaia-orchestrator" from gaia-research/gaia-skill-tree, covering role, the no-code rule, exception, session stewardship and fan-out heuristic.
Agent Claude Code
Synthesizes all reviewer reports into a unified editorial decision letter and revision roadmap.
Agent Claude Code
Quill - Product Manager for Quick PRD authoring (one-pass drafting with explicit assumptions).
asiflow/claude-nexus-hyper-agent-team
Agent Claude Code
Use this agent as the Staff/Principal BEAM Architect owning Plane 1 of the Living Platform — the BEAM kernel. This agent designs core OTP supervision trees, authors Horde/Ra/pg distributed topology, enforces the BLOCKING-1 invariant (intra-session IPC stays in-BEAM via native message passing — gRPC never crosses a…
Agent Claude Code
name: code-reviewer-design description: Specialized code reviewer for spec compliance, architecture consistency, and pattern drift. Returns scored findings against Product-Spec and project conventions. skills: code-review model: inherit.
Agent Claude Code
Create foundational templates, boilerplate code, and starter configurations for new projects, components, or features. Use for scaffolding a new component, API endpoint, model, config, or test suite from scratch.
Agent Claude Code
A bilingual guide for contributors to the Noosphere project, a software project about digital consciousness and consciousness-upload protocols. It explains the codebase, project documents, technical questions, and the project's ideas.
Agent Claude Code
Audits a feature plan PR before human review — checks spec.md and plan.md against the planning conventions in PLANNING.md and the constitution's allowlists. Reports findings; never modifies files. Invoke during Phase 2.5 (plan freeze) of the wordpress-feature skill, after scripts/open-plan-pr.sh opens the plan PR and…
Agent Claude Code
Session workspace finalization agent. Commits and pushes uncommitted work from project repos and team repo before session cleanup. Handles push conflicts with D-10 recovery (recovery branch + GitHub issue). Run only by Session Management during deactivation.
Agent Claude Code
Writes personal introductions, bios, cover letters, and README author sections using the user's mcp-me profile data.
Agent Claude Code
Maps a codebase using team-based deep analysis with priority-driven agent assignments. Use after initial project setup, when pending-analysis memories appear, or periodically to refresh the knowledge graph.
MarcusJellinghaus/mcp-tools-py
Agent Claude Code
Commits and pushes changes. Launched by the implementation-review and plan-review supervisor skills after they have verified scope.
Agent Claude CodeCursor
Coordinate Hivemind search, store, and vote workflows with safety checks and explicit confirmation for write actions.
Agent Claude Code
An agent that advises on SAP Ariba, a cloud system for sourcing, contracts, purchasing, supplier management, and supplier-network transactions. It also covers connections between Ariba and SAP ERP through CIG, now called Managed Gateway.
Agent Claude Code
Reviews code for quality, SOLID principles compliance, and requirement traceability. Assumes PR context. Provides specific refactoring suggestions with clear rationale. Strictly a reviewer - never edits or writes code.
carlos-rodrigo/claude-code.nvim
Agent Claude Code
Comprehensive research agent that combines codebase analysis with web research, creating organized topic-specific folders with structured findings.
drasticstatic/tradingview-mcp-jackson
Agent Claude Code
Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.
Agent Claude Code
Fast read-only codebase exploration that returns compressed findings.
Agent Claude Code needs its repo
Dedicated Communications Officer subagent for Intercom. Manages the persistent background IPC transport bridge, handles real-time inter-session message routing, and unblocks the main session.
IdoCohen560/claude-unity-game-studio
Agent Claude Code
Rapid prototyping specialist for pre-production. Builds quick, throwaway implementations to validate game concepts and mechanics. Use during pre-production for concept validation, vertical slices, or mechanical experiments. Standards are intentionally relaxed for speed.
Agent Claude Code
Trellis quality check agent. Use this exact agent for Trellis task verification, check.jsonl context injection, and self-fixing code review. Do not use generic/default/generalPurpose agents for Trellis checks.
Agent Claude Code
Prompt engineer. Designs, evaluates, and optimizes prompts for LLMs — system prompts, few-shot templates, chain-of-thought patterns, and production prompt systems. Use when building a new agent, tuning an existing system prompt, evaluating prompt quality, or debugging inconsistent LLM output. Reports honesty ledger on…
Agent Claude Code
Use at the end of a deep security scan to write the findings workspace — report.md, per-finding reports, hardening recommendations, and the three JSON automation files (scan-manifest, findings, coverage).
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: