agent-wallet-sdk: Instructions file for Codex

AGENTS.md

agent-wallet-sdk AGENTS.md is an instructions file for Codex, OpenCode from up2itnow0822/agent-wallet-sdk. It costs 613 tokens per session, scanned A, original, MIT.

A set of instructions for working on an SDK for non-custodial digital wallets, where the user keeps control of the keys.

In plain words
What is it for?
It guides changes to spending policies, payment execution, receipts, integrations, builds, tests, and lint checks without using live funds or production credentials.
Why use it?
It protects payment safety and keeps the package, documentation, releases, and tests consistent.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is up2itnow0822/agent-wallet-sdk's own configuration. It tells Codex and OpenCode how to work on agent-wallet-sdk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-wallet-sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to up2itnow0822/agent-wallet-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/up2itnow0822/agent-wallet-sdk/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/up2itnow0822/agent-wallet-sdk

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for agent-wallet-sdk AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/up2itnow0822/agent-wallet-sdk/agents-md/github.svg)](https://agentmods.dev/instructions/up2itnow0822/agent-wallet-sdk/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/up2itnow0822/agent-wallet-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/up2itnow0822/agent-wallet-sdk/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-wallet-sdk AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/up2itnow0822/agent-wallet-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/up2itnow0822/agent-wallet-sdk/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 613 This file is loaded in full into every session.
When invoked 613 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00613 $0.00613
Opus 5.5 $0.00245 $0.00245
Sonnet 5.5 $0.00123 $0.00123
Haiku 4.5 $0.00061 $0.00061

Measured 10d ago against content hash 83c0a045022f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-wallet-sdk 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 10d 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.

AGENTS.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md -- Agent Wallet SDK

Purpose

  • This repository provides the canonical non-custodial wallet SDK used by the AI Agent Economy payment trial.
  • It owns spending policy, payment execution, receipts, and supported integration surfaces for the agentwallet-sdk npm package.

Ownership

  • AI Agent Economy owns the SDK, package, documentation, and release evidence.

Local Contracts

  • Preserve non-custodial key control and fail-closed spending policy behavior.
  • Never use live funds, production credentials, or irreversible chain actions in default tests.
  • Keep npm metadata, README install commands, GitHub releases, and package behavior consistent. Every lazily imported package is a dependency or an optional peer with a tested >= floor (test/package-peers.test.ts). The tarball ships the built library only, never compiled tests (test/package-contents.test.ts).
  • Treat generated dist/, coverage, and dependency folders as build outputs.
  • Changes to main land only through a pull request. The required deployment policy is green build and verify checks, with every review thread resolved (live ruleset 23222371; workflow files do not configure branch protection). Codex reviews each PR automatically; evaluate its findings, but do not request or wait for a second Codex pass. No direct pushes, force-pushes, or branch deletion.
  • Environment and plugin USDC budgets must accept only USDC on the configured wallet chain. Client recipient allowlists must not be described as on-chain enforcement or isolated signing.
  • Persist and reconcile in-flight intents outside these in-memory clients before restarting a payment service or replacing its configuration.
  • Examples default to testnet, require AGENT_EXAMPLE_LIVE_ACK for mainnet, build wallets with a deployment identity (exampleDeploymentIdentity(); the unsafe opt-out is refused), verify the advertised on-chain policy (caps no looser, period at least one day) before spending, and never run on import (test/examples-safety.test.ts).
  • Breaking security changes take a new major version; never republish a vulnerable version number.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 10d ago Changed · +10 lines · +170 tokens per session 83c0a045022f
  2. 14d ago Changed · +10 lines · +133 tokens per session fb2a3d5562ec
  3. 1mo ago Changed · +3 lines · +49 tokens per session b7bcfd6edcf4
  4. 2mo ago First seen · 39 lines · 261 tokens per session scan A 30d6433c098c

Subscribe to this mod's changes

agent-wallet-sdk AGENTS.md is an instructions file published in the GitHub repository up2itnow0822/agent-wallet-sdk (12 stars, last pushed 6d ago), licensed MIT. It adds 613 tokens to every session, about $0.0025 per session on Opus 5.5. 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.

Related

agent-wallet-sdk AGENTS.md compared with instructions from other repositories

agent-wallet-sdk AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-wallet-sdk AGENTS.mdup2itnow0822/agent-wallet-sdkInstructions file126d agoMITA613Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode