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
Use when styling with Tailwind CSS, building responsive layouts, creating design systems with utility classes, or optimizing CSS. Proactively invoke for any Tailwind/CSS work.
SKZL-AI/boris-cherny-claude-code-playbook
Agent Claude Code
Specialized subagent for scanning X/Twitter and secondary sources for new Boris Cherny Claude Code tips.
Agent Claude Code
Sub-agent that runs in parallel during a full audit (or standalone) to identify growth opportunities by comparing target site against competitors via backlink/keyword data and surfacing actionable next steps.
Agent Claude Code
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
Agent Claude Code
The UMG/CommonUI specialist owns all Unreal UI implementation: widget hierarchy, data binding, CommonUI input routing, widget styling, and UI optimization. They ensure UI follows Unreal best practices and performs well.
jasonjgarcia24/ai-assisted-job-search
Agent Claude Code
Use this subagent when the user requests an update or review of the job-application-helper to make sure it's aligned with the baseline resume (assets/JasonJGarcia-RESUME.docx).
JayZeeDesign/claude-code-vault
Agent Claude Code
Use for Vercel AI SDK v5 implementation work: chat interfaces, tool calling, streaming, agentic loop control, type-safe custom messages, or migrating from v4. Covers useChat, streamText, generateText, tools, and the React/Vue/Svelte/Angular integrations.
Agent Claude Code
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
Agent Claude Code
UI design specialist for web, mobile, and desktop apps; advises on layout, hierarchy, and interaction patterns.
Agent Claude Code
Clean-room tester that runs one realistic task using only an installed skill as documentation, then reports what it did. Invoked by the /skills:validate command; do not delegate ordinary work to it.
Agent Claude Code
Task implementation leaf subagent. Invoke only when the user explicitly requests Task Executor and supplies an authoritative task source.
jeremylongshore/plugins-nixtla
Agent Claude Code
Phase 1: map raw inputs to canonical contract and produce ingest evidence + mapping artifacts. Use when starting a verification run. Trigger with 'phase 1 ingest', 'map schema', or 'canonicalize inputs'.
Agent Claude Code
Reviews Godot 4.7+ code or game-design changes against the repository's selected skills. Use after implementation or when the user asks for a focused review. Read-only.
Agent Claude Code
Create or update the feature specification from a natural language feature description.
Agent Claude Code
You are a research analyst. Your job is to scan project documents and extract information relevant to a product concept being stress-tested through the PRFAQ process.
Agent Claude Code
QDM Work Manager - Quinn.
5throck/ai-workspace-standards
Agent Claude Code
Diagram agent — generates high-quality SVG concept diagrams and data charts from visualspec fields in slidedeck.md, styled to match designspec.md. SVG is the primary delivery format for HTML; PNG is optional and required only for PDF export. Runs at Stage 3.5 parallel to image-curator.
Agent Claude Code
Reviews always-on background software — launch agents, daemons, login items, menu bar apps, VPNs, sync clients — and says which ones are worth removing or disabling for battery. Needs judgment about what an app is for — runs on a mid-size model.
Agent Claude Code
Evaluates LLM agent performance from session transcripts — token usage, tool-call efficiency, and error patterns. Diagnoses dumb errors from hasty narrow edits that miss the bigger pattern, and prescribes concrete fixes to CLAUDE.md, hooks, permissions, and skills. Scope is agent behavior and agent config only …
Agent Claude Code
A project setup agent that gets a project from GitHub or a local path, identifies its technology, and prepares a runnable development environment. It can work with conda, venv, Docker, Node.js, and Java.
robonuggets/agentic-ai-starter-kit
Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Claude Code
A backend implementation agent for building approved non-interface components such as APIs, services, databases, workers, command-line tools, and libraries.
Agent Claude Code
Use to plan a non-trivial change before any code is written. Classifies doctrine risk (GREEN/AMBER/RED) via Nauro, writes a structured plan, and drafts decision additions, updates, or supersedes for the direct-user Delivery parent. Returns a plan and never writes project truth or edits files.
Agent Claude Code
A one-pass draft checker that examines a document for formatting and numbers, rules and quotations, and the strength and completeness of its position.
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: