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/anamized/x402-cloudflare-starter/agents-mdgit clone --depth 1 https://github.com/ANAMIZED/x402-cloudflare-starterWrote 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/anamized/x402-cloudflare-starter/agents-md)<a href="https://agentmods.dev/instructions/anamized/x402-cloudflare-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/anamized/x402-cloudflare-starter/agents-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 | $0.00524 | $0.00524 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
x402-cloudflare-starter AGENTS.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 4d 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.
What it actually says
AGENTS.md
This repository is the ANAMIZED x402 agent checkout for Cloudflare Workers.
What this project does
It lets agents pay USDC on Base Mainnet and Solana Mainnet using x402 for the same first-dollar SKUs sold on Stripe:
- Agentic OS Cycle
$0.75→GET /v1/cycle - OpenGOS Advanced Search
$0.40→GET /v1/search - OpenGOS Proposal Draft
$2.50→GET /v1/draft - Agentic Trading Decision Cycle
$4.00→GET /v1/trading
Humans keep using live Stripe Payment Links. Do not invent URLs.
Payments are verified via the PayAI facilitator. A 200 on a paid route is a receipt, not a Desk entitlement write. Trading receipts are not live execution.
Key files
| Path | Purpose |
|---|---|
src/catalog.ts |
Canonical SKU table (prices + Stripe parallels) |
src/index.ts |
Cloudflare Worker (Hono + x402 middleware) |
scripts/test-client.ts |
Auto-paying test client |
wrangler.toml |
Cloudflare Workers configuration |
mcp/server.ts |
MCP server for agent discovery & tooling |
Conventions
- Runtime: Cloudflare Workers + Hono
- Payments: x402 protocol (
exactscheme) - Networks: Base (
eip155:8453) + Solana (solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp) - Facilitator: PayAI (
@payai/facilitator) — no API key required on free tier - Secrets via
wrangler secret put(never commit private keys) - Fail-closed: misconfigured payTo → 500 + Stripe fallback link
Boundaries
- Do not invent Stripe links or prices
- Do not claim a paid x402 call unlocks Studio / seats
- Do not claim
/v1/tradingexecutes live trades - Do not switch the default facilitator to CDP unless the user explicitly wants Coinbase
- Prefer keeping the codebase minimal and readable
Useful commands
npm run dev
npm run deploy
npx wrangler secret put BASE_ADDRESS
npx wrangler secret put SOLANA_ADDRESS
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.
- 4d ago First seen · 53 lines · 524 tokens per session scan A 2a932e275a4d
x402-cloudflare-starter AGENTS.md is an instructions file published in the GitHub repository ANAMIZED/x402-cloudflare-starter (1 stars, last pushed 8d ago), licensed MIT. It adds 524 tokens to every session, about $0.0026 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
mcp-ts-core AGENTS.md
AGENTS.md instructions for cyanheads/mcp-ts-core, covering developer protocol, consumers, core rules, exports reference and import conventions.
sidewise CLAUDE.md
Claude Code instructions for nulljosh/sidewise, covering sidewise, architecture, endpoints, develop and tests.
toolstop CLAUDE.md
Claude Code instructions for toolstop/toolstop, covering toolstop, adding a server, constraints that are not negotiable, releasing and how the npm tarball is built.
elc-partnership-builder CLAUDE.md
Claude Code instructions for marian-kamenistak/elc-partnership-builder, covering elc-partnership-builder, what this is, stack, run / build / deploy / test and dev: npm run dev.
gw1-mcp CLAUDE.md
Claude Code instructions for Graphmaxer/gw1-mcp, covering claude.md — gw1-mcp, what this project is, commands, architecture and tech stack.
spliit-mcp-cloudflare AGENTS.md
AGENTS.md instructions for kegelmeier/spliit-mcp-cloudflare, covering instructions for coding agents, non-negotiable boundaries, new installation contract, upgrade contract for 0.x and development rules.