Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.
eliranwong/biblemate-agentic-workspace
Agent Claude Code
Integrate all study outputs into a single, comprehensive, publication-quality final document. Write through iterative drafting, integrating, auditing, and revising — never in a single pass.
Agent Claude Code
Use this agent to create audio and video assets using Google NotebookLM. Handles notebook creation, source uploads, Audio Overview generation (Deep Dive, Brief, Critique, Debate), video generation, interactive sessions, and custom persona configuration. Use when you need to transform documents into podcasts, explainer…
Agent Claude Code
DevOps Engineer responsible for stack-aligned Infrastructure as Code, technology-optimized CI/CD pipelines, architecture-informed deployment execution, technology-aware environment management, and stack-specific rollback procedures.
Agent Claude Code
EdTech + student-privacy specialist. Use PROACTIVELY when code touches K-12 / higher-ed / corporate-learning platforms — LTI 1.3, xAPI, SCORM, cmi5, OneRoster, Caliper, QTI, Open Badges 3.0, AccessForAll, IRT adaptive assessment, proctoring, learning analytics. Owns FERPA + COPPA + 2025 FTC Final Rule + GDPR Art 8 +…
Agent Claude Code
This agent is launched by the orchestrator with a specName argument to scaffold OpenSpec artifacts and produce an implementation design for a named change. It does NOT trigger autonomously on /opsx:ff or any other slash command — it must be invoked explicitly with the change name as a positional argument. Examples…
Agent Claude Code
Budget and bidding specialist. Audits budget allocation, bidding strategies, learning phase health, audience targeting, and campaign structure across LinkedIn, TikTok, and Microsoft.
PUSHINGSQUARES/pushing-creation
Agent Claude Code
Director-of-photography-voiced interlocutor that authors style.md packs autonomously from a brief + reference images. Use when the user wants to delegate brainstorming or run multiple packs in parallel.
timothywarner-org/ai901-cert-buddy-claude
Agent Claude Code
AI-901 study buddy. Generates exam-realistic practice questions, brief hands-on Microsoft Foundry labs, and personalized study plans, all grounded in Microsoft Learn. Use when the user asks to be quizzed on Azure AI Fundamentals, wants an AI-901 lab, or wants an AI-901 study plan.
Agent Claude Code
PROACTIVELY scan codebases for LLM API usage patterns and classify each call by task type, model used, and optimization potential.
Agent Claude Code
Integration test engineer for non-unit tiers. Writes integration tests, contract tests, and end-to-end tests that exercise real infrastructure at component boundaries. Never writes skip conditions for missing infrastructure.
NullSpace-BitCradle/ats-resume-agent
Agent Claude Code
Use this agent when the user needs to create, build, or update their Master Career Document (MCD). This includes building an MCD from scratch, enriching an existing MCD with missing content, adding new roles or skills, or running a guided career documentation interview. Examples of when to use this agent: User: "Help…
Agent Claude Code
Builds and revises Livewire Flux UI — Blade markup using components, forms, modals, tables, page layouts and icons. Use when a task involves creating or changing a Flux interface, picking the right Flux component, checking whether a component needs Flux Pro, or resolving Heroicon names. Resolves every Flux question…
Agent Claude Code
Use proactively when implementing an OACS-scoped repo task or recording command evidence.
Agent Claude Code
MUST BE USED PROACTIVELY. Universal read-only explorer agent. Combines jrag graph navigation (call chains, service boundaries, routes, impact analysis, FQN resolution) with broad file-system search (grep, glob, excerpt reading). Use for any exploration task: locating code, tracing dependencies, finding patterns…
Agent Claude Code
Autonomous code review agent that analyzes code for security vulnerabilities, quality issues, and best practices adherence.
Agent Claude Code
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gtd:plan-phase orchestrator.
SarutobiSasuke8/agentops-template
Agent Claude Code
Defensive security review - secrets exposure, injection risk, unsafe automation, privacy, dependency risk, and local-system exposure. Use when changes touch auth, user data, external input, new dependencies, CI, or anything that runs automatically. Read-only.
Agent Claude Code
CFO advisory agent for financial strategy, modeling, analysis, and fiscal leadership. Use when analyzing financial statements, building financial models, DCF analysis, Monte Carlo simulations, board financial presentations, capital allocation, risk management, or when user mentions CFO, financial planning, budgeting…
Friz-zy/ai-capability-registry
Agent Claude Code
Never place secrets, credentials, tokens, PII, or production data in any field; reference affected files by redacted path only.
kasperjunge/agent-resources-legacy
Agent Claude Code
A simple subagent that greets the user.
Agent Claude CodeCursor
Compare two outputs WITHOUT knowing which skill produced them.
tornikegomareli/claude-plugin-codex
Agent Claude Code
Proactively use when Codex is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Claude Code through the companion runtime.
CodePhobiia/claude-roblox-game-studio
Agent Claude Code
Owns the Roblox/Luau wiki at wiki/ — a persistent LLM-maintained knowledge base per Karpathy's LLM Wiki pattern. Coordinates ingest, query, lint, and update operations. Delegates domain-specific page updates to the relevant specialist agent. Use when the user wants to add sources, query the wiki, check wiki health, or…
Agent Claude Code
Validates and synchronizes marketplace.json AND README.md with all plugin changes. Use PROACTIVELY after creating, updating, or modifying any plugin in this repository to ensure the marketplace registry and documentation stay accurate.
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: