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/anveai/agentpay/agents-mdgit clone --depth 1 https://github.com/ANVEAI/agentpayWhat 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 | $0.00788 | $0.00788 |
| Opus 5 | $0.00394 | $0.00394 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
agentpay 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AgentPay runbook for coding agents
AgentPay lets AI agents pay for things (x402 / USDC) and lets merchants accept those payments. This file tells a coding/developer agent how to configure AgentPay and provision paying agents programmatically — no GUI, no browser sign-in.
1. Configure (programmatic)
Set two env vars (on the control plane, and wherever the CLI runs):
AGENTPAY_ADMIN_TOKEN— a long random string; the CLI/API authenticate with it.AGENTPAY_API_URL— the control-plane endpoint, e.g.http://localhost:3000(alias:AGENTPAY_BASE_URL).
Then provision: pnpm agentpay init (interactive), pnpm agentpay prompt (emit this
runbook as a prompt to hand another agent), the flags below, or the HTTP API. CLI flags
map 1:1 to the API.
Create a merchant project + API key
AGENTPAY_ADMIN_TOKEN=… AGENTPAY_BASE_URL=… \
pnpm agentpay create-project --name "My API" --amount 0.1 --pay-to 0xMerchantWallet
# → { project: {...}, apiKey: "ap_live_…" }
Add (provision) a paying agent
pnpm agentpay add-agent --project <projectId> --label research-bot --budget 10
# → { agent: {...}, privateKey: "0x…" } # privateKey shown once — fund this wallet
Or just generate a wallet locally: pnpm agentpay gen-wallet.
Equivalent HTTP API
POST /api/cp/projects Authorization: Bearer <ADMIN_TOKEN> { name, amount, payTo }
POST /api/cp/agents Authorization: Bearer <ADMIN_TOKEN> { projectId, label, dailyLimit }
GET /api/cp/config Authorization: Bearer <apiKey> → { payTo, amount, ... }
GET /api/cp/projects Authorization: Bearer <ADMIN_TOKEN>
GET /api/cp/agents?projectId=<id> Authorization: Bearer <ADMIN_TOKEN>
2. Integrate (merchant side) — gate a route in one line
npm i @agentpay/merchant-sdk
import { paymentGateway } from "@agentpay/merchant-sdk/express";
app.use("/api/premium", paymentGateway({
apiKey: process.env.AGENTPAY_KEY,
baseUrl: process.env.AGENTPAY_BASE_URL,
}));
Next.js: withPayment(handler, { apiKey }). Any Fetch server: createWebGateway({ apiKey }).guard(request).
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.
- 2d ago First seen · 71 lines · 788 tokens per session scan A 7e011d324fd9
agentpay AGENTS.md is an instructions file published in the GitHub repository ANVEAI/agentpay (2 stars, last pushed 2mo ago), licensed MIT. It adds 788 tokens to every session, about $0.0039 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
stipend AGENTS.md
AGENTS.md instructions for stipend-sh/stipend, covering agents.md, what this is, run it, the rule that matters and where the money paths are.
x402trace CLAUDE.md
Instructions for fardinvahdat/x402trace, covering claude.md — operating manual for x402trace, project mission, status, hard rules — non-negotiable and strict audit gate (autonomous mode).
lightning-enable-mcp CLAUDE.md
Instructions for refined-element/lightning-enable-mcp, covering claude.md — lightning enable mcp, project overview, bug fix workflow and engineering standards.
gblin-treasury-risk-regime AGENTS.md
AGENTS.md instructions for gblinproject/gblin-treasury-risk-regime, covering agents.md — gblin mcp server, what this repo is, tech stack (working on this codebase), hard rules for code edits and critical files.
x402-stellar-kit AGENTS.md
AGENTS.md instructions for CodeStrux/x402-stellar-kit, covering working with x402-stellar-kit, the one invariant, production seams, bootstrapping accounts across a custody boundary and add x402 to an existing api.
aegis-protocol CLAUDE.md
Instructions for im-sham/aegis-protocol, covering aegis protocol — claude code project context, what this is, core architecture, job state machine and erc-8004 integration (critical — this is our moat).