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
Read-only codebase exploration. Use to locate code, trace dependencies, or summarize modules without polluting the main context window. MUST be used for heavy reading during /cold-start and /create-feature-catalog.
Agent Claude Code
QA Engineer and Security Auditor agent for code review, security auditing, testing verification, compliance checking, dead code detection, and quality gates. MUST BE USED for any review, audit, quality check, or security assessment. Use PROACTIVELY after any code changes or before releases.
Agent Claude Code
ML engineering specialist sub-agent. Principles from Andrej Karpathy's work — micrograd, nanoGPT, llm.c, Tesla Autopilot, Stanford CS231n.
Agent Claude Code
An agent that evaluates a business idea through five stages in a single call. The description does not explain the stages or the evaluation criteria.
Agent Claude Code
ML engineering specialist sub-agent. Designs and implements inference pipelines, provider selection, quantization strategies, and hardware abstraction for ONNX models. Benchmark-driven — measures before optimizing.
Agent Claude Code
Use this agent when triaging issues, feature requests, or bugs for the Rememora project — a cross-agent persistent memory CLI for AI coding assistants. This includes prioritizing work, categorizing tasks across the Rust CLI, eval bench, and plugin subsystems, and grooming the GitHub project board. Also use when the…
Agent Claude Code
Run reference coverage and syntax audits for Obsidian CLI docs. Use proactively during local /o-qa runs.
Agent Claude Code
Smalltalk specialist sub-agent. Principles from Extreme Programming, Test-Driven Development, and Smalltalk Best Practice Patterns.
Edmonds-Commerce-Limited/claude-code-hooks-daemon
Agent Claude Code
Read-only documentation-SSoT auditor. Scans a project's documentation corpus (and, per its comment-hunt mandate, verbose source-code comment blocks that function as documentation) for conflicting truths, distributed/duplicated truths, stale derived facts and doc-shaped comments with no canonical home — the semantic…
Agent Claude Code
VPS maintenance agent. Use when the user asks about server status, wants to check their deployments, apply OS updates, or run maintenance on Pulse, Curia, or any registered server. Handles status checks (read-only) and updates/reboots (write) based on intent.
madebyaris/cursor-composer-rules
Agent Claude CodeCursor
Debugging specialist for errors, test failures, and unexpected behavior. Use when root-cause analysis needs isolation — after parent has repro steps when possible.
Agent Claude Code
Gate System orchestrator - analyzes project state, determines current phase, and coordinates gate reviews.
rhyean88/apple-platform-build-tools-claude-code-plugin
Agent Claude Code
STRONGLY PREFER to delegate Apple platform builds and tests to this agent to preserve your context window. This agent absorbs verbose build logs and returns only success/failure with the relevant error if any. Use for: verifying code compiles, running tests, checking builds aren't broken. Discovers schemes and…
Institut-du-Numerique-Responsable/skill-nr
Agent Claude Code
Revue écoconception d'un diff selon le RGESN v2 et le GR491.
Agent Claude Code
Phase B of the delegated brief→expand archive flow. Receives a fully-decided ArchiveBrief from the orchestrator and renders it into the archive body + new context.md, then persists via memarchive. Decides NOTHING — pure rendering. Spawned by mem-archive full mode on a low-tier model with a fresh window; the cost win…
Agent Claude Code
Repository-grounded planner. Dispatched when the orchestrator detects a task touching 3+ files, unknown code, schema/API/auth/secrets/infra changes, or when the user explicitly asks for a plan. Does not edit files.
weorbitant/claude-code-agentic-research-orchestrator
Agent Claude Code
Orchestrates Gemini CLI and Copilot CLI agents for comprehensive research, development, and analysis tasks. Coordinates multiple AI perspectives, consolidates findings, and provides consensus-based recommendations. Use PROACTIVELY for complex tasks requiring multi-agent collaboration.
Baba01hacker666/gemini-redteam
Agent Claude Code
Source code security analyzer for CMS and web applications. Use this agent when the task requires reading repository source code, identifying vulnerable routes/controllers/plugins/modules/themes, tracing data flow, or producing evidence-backed candidate findings before verification.
Agent Claude Code
Answers questions about the user's own health data — sleep, HRV, resting heart rate, recovery, stress, body battery, training load, workouts, weight, VO2max, and trends over any time range. Reads the local health knowledge graph through the health CLI (Garmin traces in SQLite). Use for "how did I sleep", "how's my…
Agent Claude Code
Web research and advisory agent for external knowledge gathering.
Agent Claude Code
Use this agent when the user needs AWS-specific technology research using the AWS Knowledge MCP server to match project requirements to AWS services, architecture patterns, Well-Architected guidance, and Security Hub controls. Examples: Context: User has a project with requirements and wants AWS service…
Agent Claude Code
CC fallback implementation-plan reviewer for make-detail-plan; invoked when codex CLI is unusable. Thorough — surfaces minor issues as well as major ones.
Agent Claude Code
Use this agent when you need to assess the actual state of project completion, cut through incomplete implementations, and create realistic plans to finish work. This agent should be used when: 1) You suspect tasks are marked complete but aren't actually functional, 2) You need to validate what's actually been built…
Agent Claude Code
Use this agent when you need to review WordPress-related documentation, announcements, blog posts, or marketing materials for quality, clarity, and compliance with WordPress Brand Writing Style Guide standards. This agent should be called after drafting or revising WordPress content to get detailed, actionable…
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: