aztec-starter: Instructions file for Codex

AGENTS.md

aztec-starter AGENTS.md is an instructions file for Codex, OpenCode from AztecProtocol/aztec-starter. It costs 528 tokens per session, scanned C, original, Apache-2.0.

Repository instructions for an Aztec network starter project containing TypeScript scripts and Noir smart contracts. They explain its Node.js, Yarn, Aztec CLI, local-network, compilation, code-generation, and testing requirements.

In plain words
What is it for?
Use them when compiling or testing Noir contracts, generating TypeScript code, running local Aztec end-to-end tests, deploying to a devnet, or changing project scripts.
Why use it?
They help a coding agent use matching tool versions, keep generated files out of source changes, and test contracts against the correct local network state.

Instructions file for CodexOpenCode

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

This is AztecProtocol/aztec-starter's own configuration. It tells Codex and OpenCode how to work on aztec-starter 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 aztec-starter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AztecProtocol/aztec-starter. 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/AztecProtocol/aztec-starter/next/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/AztecProtocol/aztec-starter

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 aztec-starter AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aztecprotocol/aztec-starter/agents-md/github.svg)](https://agentmods.dev/instructions/aztecprotocol/aztec-starter/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/aztecprotocol/aztec-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/aztecprotocol/aztec-starter/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 aztec-starter AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aztecprotocol/aztec-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/aztecprotocol/aztec-starter/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 528 This file is loaded in full into every session.
When invoked 528 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.00528 $0.00528
Opus 5.5 $0.00211 $0.00211
Sonnet 5.5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 2mo ago against content hash 9b4f3fbb6eec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

aztec-starter AGENTS.md scanned grade C with 1 finding 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 2mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- After restarting the local network, always run `rm -rf ./store` to clear stale PXE data.
AGENTS.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository guidelines for Codex agents

This repository contains TypeScript scripts and Noir contracts for the Aztec network. Follow these guidelines when contributing:

Setup

  • Use Node.js v22 with Yarn.
  • Install dependencies with yarn install.
  • The Aztec CLI (aztec) must be installed at the version matching Nargo.toml and package.json.
  • Start the Aztec local network with aztec start --local-network before running E2E tests or scripts. This is not needed for compilation or Noir unit tests.
  • After restarting the local network, always run rm -rf ./store to clear stale PXE data.

Development

  • This is an ESM project ("type": "module" in package.json).
  • Compile contracts with yarn compile and generate TypeScript artifacts with yarn codegen.
  • Use four spaces for indentation in TypeScript and scripts.
  • Do not commit generated artifacts (src/artifacts, target, or store folders).
  • Never edit src/artifacts/PodRacing.ts directly; it is generated by yarn codegen.
  • To target devnet instead of local network, set AZTEC_ENV=devnet (e.g. AZTEC_ENV=devnet yarn deploy).

Testing

There are two independent test systems:

  • Noir TXE tests (yarn test:nr): Run in the TXE simulator, no network required.
  • TypeScript E2E tests (yarn test:js): Require a running local network.
  • yarn test runs both. Ensure tests pass before committing.

Simulate Before Send

Always call .simulate() before .send() for every state-changing transaction. Simulation runs the transaction locally and surfaces revert reasons immediately instead of waiting for the send timeout with an opaque error.

// Simulate first
await contract.methods.create_game(gameId).simulate({ from: address });
// Then send
await contract.methods.create_game(gameId).send({
    from: address,
    fee: { paymentMethod },
    wait: { timeout }
});

For deployments, store the deploy request to reuse it:

const deployRequest = MyContract.deploy(wallet, ...args);
await deployRequest.simulate({ from: address });
const contract = await deployRequest.send({ ... });

Read the full file on GitHub · 53 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. 2mo ago First seen · 53 lines · 528 tokens per session scan C 9b4f3fbb6eec

Subscribe to this mod's changes

aztec-starter AGENTS.md is an instructions file published in the GitHub repository AztecProtocol/aztec-starter (123 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 528 tokens to every session, about $0.0021 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

aztec-starter AGENTS.md compared with instructions from other repositories

aztec-starter AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aztec-starter AGENTS.mdAztecProtocol/aztec-starterInstructions file1233mo agoApache-2.0C528Codex, 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