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/themobiusstrip/agentpay-guard/agents-mdgit clone --depth 1 https://github.com/theMobiusStrip/agentpay-guardWrote 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/themobiusstrip/agentpay-guard/agents-md)<a href="https://agentmods.dev/instructions/themobiusstrip/agentpay-guard/agents-md"><img src="https://agentmods.dev/badge/instructions/themobiusstrip/agentpay-guard/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 | $0.02426 | $0.02426 |
| Opus 5 | $0.01213 | $0.01213 |
| Sonnet 5 | $0.00485 | $0.00485 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade A, and why
agentpay-guard 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 3d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — agentpay-guard
Guidance for AI agents (Claude Code, Codex, Cursor, …) working in this repo.
CLAUDE.md imports this file, so this is the single source of truth.
What this is
A stateful, agent-agnostic x402 v2 policy plugin (agentpay-guard) + a
server-side replay middleware + DrainBench, a reproducible adversarial
harm-metric benchmark. npm workspaces monorepo. See README.md for the full story.
Layout
packages/agentpay-guard/ client plugin + restart-safe SQLite entry (publishable)
packages/x402-idempotency-middleware/ server replay middleware (publishable)
packages/agentpay-proxy/ guarded payment proxy service (publishable; CLI + MCP)
packages/drainbench/ benchmark harness + agent scaffold (private)
examples/ claude-proxy + raw-viem (offline) + paid-site merchant demo
spike/ G0 hook probe (offline) + e2e harness (needs funds)
bench/ reproducibility bundle, arm-A baseline, results
docs/reference/ durable: threat model + attack taxonomy
SECURITY.md authoritative security model (read before custody edits)
(docs/process/ — milestone notes — and docs/tutorials/ are private/gitignored,
absent in a fresh clone.)
Commands
npm ci && npm run build # build all publishable packages
npx vitest run # full test suite (all packages)
npx tsc -b # typecheck published packages
npx tsc -p spike/tsconfig.json # typecheck spike
npx tsc -p packages/drainbench/tsconfig.json --noEmit # typecheck bench harness
npx tsc -p examples/tsconfig.json # typecheck examples
npx tsc -p bench/tsconfig.json # typecheck pinned arm-A
npm run lint # type-aware eslint, all projects
npm run -w @agentpay-guard/spike hook-probe # offline SDK probe (no funds)
npm run -w @agentpay-guard/drainbench bench # deterministic A/B -> bench/results/
npm run -w @agentpay-guard/drainbench agent-demo # stochastic demonstration
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.
- 3d ago First seen · 177 lines · 2,426 tokens per session scan A 33b72bd68ce1
agentpay-guard AGENTS.md is an instructions file published in the GitHub repository theMobiusStrip/agentpay-guard (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,426 tokens to every session, about $0.0121 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
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.
xenarch-mcp CLAUDE.md
Claude Code instructions for xenarch-ai/xenarch-mcp, covering xenarch-mcp, structure, stack, commands and design principle.
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.
x402-stellar-kit CLAUDE.md
Claude Code instructions for CodeStrux/x402-stellar-kit, a project described as: x402 payment primitives for Stellar: intent binding, a deterministic policy engine, a pluggable approver, and an agent surface. Apache-2.0.
mobilegym AGENTS.md
Instructions for Purewhiter/mobilegym, covering agents.md, project overview, type-checking strategy, eslint and with data graph generation.
ClawBench AGENTS.md
Instructions for TIGER-AI-Lab/ClawBench, covering clawbench -- agent context, what this is, project structure, setup and 2. configure at least one model.