guillotine-mini CLAUDE.md

guillotine-mini CLAUDE.md is an instructions file for coding agents from evmts/guillotine-mini. It costs 7,337 tokens per session, scanned A, original, MIT.

A project instruction file for Guillotine Mini, a Zig implementation of the Ethereum Virtual Machine—the software that runs Ethereum smart-contract bytecode.

In plain words
What is it for?
Use it when building, testing, debugging, validating Ethereum specifications, or producing the project's WebAssembly library.
Why use it?
It records the commands, required tools, architecture, and testing approach needed to work safely in this codebase.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/evmts/guillotine-mini/claude-md
Clone the repo
git clone --depth 1 https://github.com/evmts/guillotine-mini

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 guillotine-mini CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/evmts/guillotine-mini/claude-md.svg)](https://agentmods.dev/instructions/evmts/guillotine-mini/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/evmts/guillotine-mini/claude-md"><img src="https://agentmods.dev/badge/instructions/evmts/guillotine-mini/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,337 This file is loaded in full into every session.
When invoked 7,337 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.07337 $0.07337
Opus 5 $0.03668 $0.03668
Sonnet 5 $0.01467 $0.01467
Haiku 4.5 $0.00734 $0.00734

Measured 5d ago against content hash 2472c86089f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guillotine-mini 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.

CLAUDE.md · 771 lines

How it starts

The opening of the file, as written. The whole thing — 771 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guillotine Mini - EVM Implementation

Minimal, correct, and well-tested Ethereum Virtual Machine (EVM) implementation in Zig, prioritizing specification compliance, clarity, and hardfork support (Berlin through Prague).

Quick Start

zig build              # Build all modules
zig build test         # Run unit + spec tests
zig build specs        # Run ethereum/tests validation
zig build wasm         # Build WebAssembly library
zig build test-watch   # Interactive test runner

# Debug failing tests (recommended)
bun scripts/isolate-test.ts "test_name"  # Max debug output + analysis
bun scripts/test-subset.ts "pattern"     # Filter test categories

Prerequisites

  • Zig 0.15.1+ (core build system)
  • Cargo (required for BN254/ARK cryptographic dependencies)
  • Python 3.8+ (test generation and reference implementation)
  • uv (Python package manager for spec fixture generation): brew install uv
  • Bun (TS helpers/agents): brew install bun

Architecture

src/
├── evm.zig               # Orchestrator: state, storage, gas refunds, nested calls
├── frame.zig             # Bytecode interpreter: stack, memory, PC, per-opcode logic
├── host.zig              # Abstract state backend interface
├── hardfork.zig          # Hardfork detection and feature flags
├── opcode.zig            # Opcode definitions and utilities
├── trace.zig             # EIP-3155 trace generation
└── errors.zig            # Error types

External Dependencies (fetched via zig build):
├── primitives            # Ethereum types (Address, u256, gas constants, RLP, ABI, etc.)
│                         # Source: https://github.com/evmts/primitives
├── crypto                # Cryptographic primitives (keccak256, secp256k1, BLS12-381)
└── precompiles           # Ethereum precompiled contracts

Core Responsibilities

Component Responsibility
Evm State management, storage, gas refunds, warm/cold tracking, nested calls
Frame Stack, memory, PC, bytecode interpretation, opcode execution
Host Pluggable state backend (balances, nonces, code, logs, self-destruct)
Hardfork Gas cost adjustments, feature flag guards (isAtLeast(), isBefore())

Read the full file on GitHub · 771 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. 5d ago First seen · 771 lines · 7,337 tokens per session scan A 2472c86089f7

Subscribe to this mod's changes

guillotine-mini CLAUDE.md is an instructions file published in the GitHub repository evmts/guillotine-mini (10 stars, last pushed 1mo ago), licensed MIT. It adds 7,337 tokens to every session, about $0.0367 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.