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/worldliberty/agentpay-sdk/claude-mdgit clone --depth 1 https://github.com/worldliberty/agentpay-sdkWrote 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/worldliberty/agentpay-sdk/claude-md)<a href="https://agentmods.dev/instructions/worldliberty/agentpay-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/worldliberty/agentpay-sdk/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 | $0.01312 | $0.01312 |
| Opus 5 | $0.00656 | $0.00656 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
agentpay-sdk 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 — 122 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.
Build & Development Commands
# Install dependencies (also builds Rust binaries via postinstall)
pnpm install
# Build everything (Turbo + tsup CLI bundle)
npm run build
# Full check (cargo test compile + turbo typecheck)
npm run check
# TypeScript type checking
npm run typecheck
# Lint (Biome)
npm run lint
npm run lint:fix # auto-fix
# Run all TypeScript integration tests
npm run test:ts
# Run a single TypeScript test
node --experimental-strip-types --test test/<file>.test.mjs
# Run Rust tests
cargo test --workspace
# Run a single Rust crate's tests
cargo test -p vault-domain
# Build/install Rust binaries to ~/.agentpay/bin
npm run install:rust-binaries
# Package-specific commands (vitest)
pnpm --filter @worldlibertyfinancial/agent-relay test:unit
pnpm --filter @worldlibertyfinancial/agent-web test:unit
# Relay deployment
pnpm --filter @worldlibertyfinancial/agent-relay deploy:local
pnpm --filter @worldlibertyfinancial/agent-relay deploy:development
pnpm --filter @worldlibertyfinancial/agent-relay deploy:production
Architecture
This is a monorepo for a macOS signing CLI built around a self-custodial local daemon. The system has two language layers: Rust handles cryptography, policy evaluation, and daemon operations; TypeScript handles CLI orchestration, configuration, and web interfaces.
How the layers interact (daemon mode)
The TypeScript CLI (src/cli.ts) is the user-facing entry point (agentpay). It spawns Rust binaries (vault-cli-admin, vault-cli-agent, vault-cli-daemon) as child processes for security-critical operations. The Rust daemon runs persistently and communicates via Unix domain sockets (or macOS XPC). The relay server bridges external requests to the daemon, and the web UI provides a manual approval console.
TypeScript CLI (src/cli.ts)
│ spawns Rust binaries
▼
Rust CLIs (vault-cli-*)
│ Unix socket / XPC
▼
Daemon (vault-daemon) ← Relay (apps/relay, tRPC/Hono) ← Web UI (apps/web, Next.js)
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 · 122 lines · 1,312 tokens per session scan A e467441d3a50
agentpay-sdk CLAUDE.md is an instructions file published in the GitHub repository worldliberty/agentpay-sdk (460 stars, last pushed 2mo ago), licensed MIT. It adds 1,312 tokens to every session, about $0.0066 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 2026-08-30.
Other instructions, from other repositories
x402-client AGENTS.md
Instructions for vybenetwork/x402-client, covering vybe x402 client — agent instructions, quick reference, prerequisites, complete flow and step 1: install.
inflow-cli AGENTS.md
AGENTS.md instructions for inflowpayai/inflow-cli, covering agents.md, what this repo is, repo map, before merging and conventions.
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).
agenticpay CLAUDE.md
Claude Code instructions for agenticpay-dev/agenticpay, covering agenticpay, merge do main nie wdraża produkcji, brak sieci w /supported bywa poprawny and kody odrzucenia z @x402/svm wychodzą na drucie.
ar-agents AGENTS.md
AGENTS.md instructions for ar-agents/ar-agents: This repo improves itself. If you are an agent session working on this repo.
x402watch CLAUDE.md
Claude Code instructions for printmoneylab/x402watch, covering x402watch, project overview, tech stack, coding style and kr crypto 학습 사항 (반드시 적용).