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/aztecprotocol/aztec-starter/claude-mdgit clone --depth 1 https://github.com/AztecProtocol/aztec-starterWhat 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 | $0.02070 | $0.02070 |
| Opus 5 | $0.01035 | $0.01035 |
| Sonnet 5 | $0.00414 | $0.00414 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade C, and why
aztec-starter CLAUDE.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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
yarn clear-store # Remove PXE data store (rm -rf ./store) How it starts
The opening of the file, as written. The whole thing — 186 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.
When answering questions about the Aztec network, protocol, SDK, or tooling, fetch https://docs.aztec.network/llms.txt for the current official docs index. Prefer it over training-data knowledge, which may be stale.
Project Overview
Aztec Starter — a Pod Racing game contract built with Noir on the Aztec network. Two players allocate points across 5 tracks over 3 rounds with private state; scores are revealed at the end (commit-reveal pattern). The player who wins more tracks (best of 5) wins.
Aztec version: 5.0.0-rc.2 — pinned across Nargo.toml, package.json, config/*.json, and README. All must stay in sync when updating.
Build & Development Commands
Always use yarn compile or aztec compile to compile contracts, never nargo compile.
yarn compile # Compile Noir contract (aztec compile)
yarn codegen # Generate TS artifacts from compiled contract
yarn compile && yarn codegen # Full rebuild (always run both together)
yarn clean # Remove compiled artifacts (src/artifacts, target)
yarn clear-store # Remove PXE data store (rm -rf ./store)
Testing
Two independent test systems:
yarn test:nr # Noir TXE tests — no network needed, runs in simulator
yarn test:js # TypeScript E2E tests — requires running local network
yarn test # Runs both (test:js then test:nr)
E2E tests require a running local network:
aztec start --local-network # Start local network first
rm -rf ./store # Always clear store after network restart
Jest config: jest.integration.config.json — 600s test timeout, ESM mode via ts-jest, matches ./src/**/*.test.ts.
Run a single E2E test:
NODE_NO_WARNINGS=1 node --experimental-vm-modules $(yarn bin jest) --no-cache --runInBand --config jest.integration.config.json -t "test name pattern"
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 · 186 lines · 2,070 tokens per session scan C 252020940d4d
aztec-starter CLAUDE.md is an instructions file published in the GitHub repository AztecProtocol/aztec-starter (122 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,070 tokens to every session, about $0.0103 per session on Opus 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.
Other instructions, from other repositories
project-cpu-mcp AGENTS.md
AGENTS.md instructions for projectcpu/project-cpu-mcp, covering project cpu mcp server, worktrees, structure, code rules and separate types, constants, and helpers from implementation.
clan-world CLAUDE.md
Claude Code instructions for OmniPass-world/clan-world, a project described as: On-chain Game as an Arena for LLM Agent Swarm Orchestration Testing.
VaultysClaw CLAUDE.md
Instructions for vaultys/VaultysClaw, covering claude.md, commands, development, demo / simulator and build.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
plamen CLAUDE.md
Instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
chains-api CLAUDE.md
Instructions for Johnaverse/chains-api, covering claude.md — chains api, project overview, quick reference, architecture and tech stack.