Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/jarrodwatts/scuttlepay/claude-mdgit clone --depth 1 https://github.com/jarrodwatts/scuttlepayWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/jarrodwatts/scuttlepay/claude-md)<a href="https://agentmods.dev/instructions/jarrodwatts/scuttlepay/claude-md"><img src="https://agentmods.dev/badge/instructions/jarrodwatts/scuttlepay/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01066 | $0.01066 |
| Opus 5 | $0.00533 | $0.00533 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
scuttlepay CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What is ScuttlePay
Wallet-as-a-service for autonomous AI agents. Agents get API keys with spending policies, execute USDC purchases against Shopify storefronts, and settle payments on-chain via the x402 protocol (EIP-712/EIP-3009 TransferWithAuthorization).
Commands
pnpm dev # Next.js dev server (Turbopack)
pnpm build # Production build
pnpm check # Lint + typecheck in one shot
pnpm lint # ESLint only
pnpm typecheck # tsc --noEmit only
pnpm format:check # Prettier check
pnpm format:write # Prettier fix
# Database (Drizzle + PostgreSQL)
pnpm db:generate # Generate migration from schema changes
pnpm db:migrate # Run pending migrations
pnpm db:push # Push schema directly (dev only)
pnpm db:seed # Seed database (reads .env.local)
pnpm db:studio # Drizzle Studio GUI
# E2E
pnpm e2e # Run e2e tests (reads .env)
Architecture
Monorepo (pnpm workspaces): root Next.js app + packages/shared + packages/mcp.
Stack
- Next.js 15 (App Router) + React 19, Tailwind 4, shadcn/ui (Radix)
- tRPC 11 + TanStack Query 5 for data fetching
- Drizzle ORM + PostgreSQL (Vercel Postgres / Neon)
- thirdweb SDK v5 for wallet management and auth (JWT from wallet signatures)
- Zod for all input validation (shared schemas in
packages/shared)
Path alias
~/* → ./src/*
Layered backend
src/server/api/routers/ → tRPC routers (thin: validate input, call service, map errors)
src/server/services/ → Domain logic (purchase flow, spending evaluation, payment signing)
src/server/lib/ → Infrastructure (thirdweb client, Shopify GraphQL, API key validation, USDC math)
src/server/db/schema/ → Drizzle table definitions (all prefixed scuttlepay_*)
src/server/auth/ → thirdweb Auth setup + cached user resolution
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 104 lines · 1,066 tokens per session scan A c2a8fe99a313
scuttlepay CLAUDE.md is an instructions file published in the GitHub repository jarrodwatts/scuttlepay (6 stars, last pushed 6mo ago), licensed MIT. It adds 1,066 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
knowmint CLAUDE.md
Instructions for Sou0327/knowmint, covering claude.md, project info, project overview, commands and architecture.
Hackathon-Stellaroid_Earn AGENTS.md
AGENTS.md instructions for Iron-Mark/Hackathon-Stellaroid_Earn, covering agents.md, what this repo is, common commands, frontend (frontend/) and stellar cli (environment setup).
Bags-SDK-hackathon CLAUDE.md
Instructions for outerheaven199X/Bags-SDK-hackathon, covering bags hackathon — token launch assistant, auto-scan trigger (critical — always follow), when the user already has a topic, scout launch flow (localhost — no exceptions) and hard rules for launches.
swarmfi CLAUDE.md
Claude Code instructions for zacharyftw/swarmfi, a project described as: AI agent swarm that farms DeFi yields so you don't have to.
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
plamen CLAUDE.md
Claude Code instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.