By AqilJaafree
Aqil's personal Claude Code setup with 14 productivity commands and 12 specialized AI agents for modern web development
Analyze task complexity and create actionable implementation plan
You are a code education expert specializing in explaining complex code through clear narratives, visual diagrams, and step-by-step breakdowns. Transform difficult concepts into understandable explanations for developers at all levels.
Analyze and optimize code for performance, memory, and efficiency
Refactor and clean up code following best practices
Plan feature implementation with technical specifications
Use this agent when the user is planning new features or functionality and needs guidance on technology choices, architecture decisions, or implementation approaches. Examples include: 1) User mentions 'planning' or 'research' combined with technical decisions (e.g., 'I'm planning to add real-time notifications, what should I use?'), 2) User asks about technology comparisons or recommendations (e.g., 'should I use WebSockets or Server-Sent Events?'), 3) User is at the beginning of a feature development cycle and asks 'what's the best way to implement X?', 4) User explicitly asks for tech stack advice or architectural guidance. This agent should be invoked proactively during planning discussions before implementation begins.
Design reliable backend systems with focus on data integrity, security, and fault tolerance
Specialist for comprehensive research with adaptive strategies and intelligent exploration
Create accessible, performant user interfaces with focus on user experience and modern frameworks
Teach programming concepts and explain code with focus on understanding through progressive learning and practical examples
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Voice-authorized agentic payments. One biometric voice auth opens a bounded spending session — the agent transacts autonomously via x402 with no per-transaction wallet popups.
1. Open http://localhost:3000
→ Jarvis HUD loads (dark arc-reactor UI, boot chime plays on first tap)
2. Tap the arc-reactor mic — enroll your voice (3 samples)
→ "Enroll voice (1/3)… (2/3)… (3/3)"
→ Voiceprint stored in the voice sidecar
3. Tap the mic — speak a purchase command
→ "Speak to Jarvis" e.g. "buy some water" / "get me a coffee" / "bus ticket"
4. Jarvis executes in one shot — no popups, no wallet approval:
a. Voice verified against enrolled voiceprint (Resemblyzer cosine match ≥ 0.75)
b. Session mandate minted ($5 budget · 10 min · water + bus + coffee + parking)
c. Intent parsed by Claude → { item: "coffee", qty: 1, maxPriceUsd: 2 }
d. Cheapest seller found across multi-city catalog (geolocation price arbitrage)
e. x402 payment via pay --sandbox curl → on-chain tx sig in payment-receipt header
f. Audit log updated immediately (no "pending" state ever)
5. UI shows immediately:
✅ Bought BeanHub for $1.00 — confirmed (5uKw9VMp…)
Session panel shows budget bar: $5.00 · Spent $1.00
6. Speak again — no re-auth (session is still open)
→ Second purchase executes instantly, demonstrating zero friction within session
Sound cues (Web Audio API, no files):
| Say… | Item | Seller chosen | Price | Why |
|---|---|---|---|---|
| "buy some water" | water | AquaVend (KL) | $0.50 | cheapest |
| "get a coffee" | coffee | BeanHub (KL) | $1.00 | cheapest |
| "bus ticket" | bus | CityBus (KL) | $1.20 | cheapest |
| "parking" | parking | ParkEasy (KL) | $0.80 | cheapest |
Other sellers at higher prices exist (Bangkok, Singapore) — resolveMerchant picks the cheapest and exposes alternatives[] for display/arbitrage UI.
npm install -g @solana/pay (installs the pay x402 CLI binary)cd services/voice
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
uvicorn app:app --port 8000
cd apps/web
cp .env.local.example .env.local # fill in ANTHROPIC_API_KEY
pnpm install
pnpm dev
# predev hook auto-starts: pay --sandbox server start services/payments/provider.yml (:1402)
# then starts Next.js on :3000
open http://localhost:3000
.env.local requiredANTHROPIC_API_KEY=sk-ant-...
VOICE_URL=http://localhost:8000
API_PROVIDER=anthropic # default — direct Anthropic API (claude-opus-4-8)
API_PROVIDER=litellm-remote # remote LiteLLM proxy
API_PROVIDER=litellm-local # local OpenCode/LiteLLM on :4000
Browser (Next.js — Jarvis HUD, Orbitron font, arc-reactor mic)
└─ mic → /api/enroll → voice sidecar → voiceprint stored
└─ mic → /api/verify → voice match → mandate minted
→ /api/transcribe → Whisper STT → transcript
→ /api/purchase → orchestrator
/api/purchase (Next.js App Router)
└─ checkMandate (budget · category · expiry)
└─ resolveMerchant (pickCheapest — haversine geo arbitrage)
└─ pay-gateway: shells out → pay --sandbox curl -X POST :1402/v1/{item}
└─ services/payments/provider.yml (x402 sandbox, routing: respond)
└─ payment-receipt header → reference (tx sig) → AuditLog
services/voice/ (Python FastAPI)
POST /enroll — Resemblyzer voiceprint embedding stored
POST /verify — cosine similarity ≥ 0.75 → mandate issued
POST /transcribe — Whisper STT → transcript text
No browser wallet. The pay CLI owns a sandbox wallet (auto-funded, 402.surfnet.dev:8899).
Multi-seller catalog with real city coordinates for price arbitrage:
water AquaVend $0.50 KL · SpringWell $0.65 Bangkok · HydroMart $0.75 Singapore
bus CityBus $1.20 KL · MetroLink $1.50 Singapore
coffee BeanHub $1.00 KL · CafeNow $1.35 Bangkok · Roastery $1.80 Singapore
parking ParkEasy $0.80 KL · QuickPark $1.10 Singapore
resolveMerchant(item, { userLocation: {lat, lng} }) picks cheapest, tiebreaks by distance, returns alternatives[].
services/payments/provider.yml — runs as pay --sandbox server start:
POST v1/water → $0.50POST v1/bus → $1.20POST v1/coffee → $1.00POST v1/parking → $0.80Uses routing.type: respond (demo mode, no real upstream API).
Aqil's personal Claude Code setup with 14 productivity commands and 12 specialized AI agents for modern web development
npx claudepluginhub aqiljaafree/jarvismaxxingComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.