clean AGENTS.md

clean AGENTS.md is an instructions file for Codex, OpenCode from Verified-zkEVM/clean. It costs 3,447 tokens per session, scanned A, original, MIT.

Project instructions for Clean, an embedded Lean language library for writing mathematically verified zero-knowledge circuits. Zero-knowledge circuits let someone prove a computation was correct without revealing its private inputs.

In plain words
What is it for?
Use them when working on Clean’s circuit language, reusable circuit components, proofs, tests, or project organization.
Why use it?
They give a coding agent the project structure and concepts needed to make informed changes in this specialized codebase.

Instructions file for CodexOpenCode

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/verified-zkevm/clean/agents-md
Clone the repo
git clone --depth 1 https://github.com/Verified-zkEVM/clean

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 clean AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/verified-zkevm/clean/agents-md.svg)](https://agentmods.dev/instructions/verified-zkevm/clean/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/verified-zkevm/clean/agents-md"><img src="https://agentmods.dev/badge/instructions/verified-zkevm/clean/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,447 This file is loaded in full into every session.
When invoked 3,447 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 $0.03447 $0.03447
Opus 5 $0.01724 $0.01724
Sonnet 5 $0.00689 $0.00689
Haiku 4.5 $0.00345 $0.00345

Measured 4d ago against content hash 5125decc967f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean 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 4d 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 · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - AI Agent Context for Clean

This document provides context for AI coding agents working on the clean codebase.

What is Clean?

Clean is an embedded Lean DSL for writing formally verified zk (zero-knowledge) circuits. It targets popular arithmetizations like AIR, PLONK, and R1CS. The key value proposition is producing formally verified, bug-free circuits with proofs of soundness and completeness.

Project Structure

Clean/
├── Circuit/           # Core circuit DSL and monad
│   ├── Basic.lean     # Circuit monad
│   ├── Formal.lean    # FormalCircuit, soundness/completeness definitions
│   ├── Expression.lean # Expression AST (var, const, add, mul)
│   ├── Operations.lean # Operation types (witness, assert, lookup, subcircuit)
│   ├── Provable.lean  # ProvableType, ProvableStruct - typed circuit values
│   ├── Subcircuit.lean # Composing formal circuits
│   ├── Lookup.lean    # Lookup table support
│   └── Theorems.lean  # Core theorems about circuit semantics
├── Gadgets/           # Reusable verified circuit components
│   ├── Boolean.lean   # Boolean constraints (IsBool, assertBool)
│   ├── Equality.lean  # Equality assertions (===)
│   ├── IsZero.lean    # Zero-check circuits
│   ├── ByteDecomposition/ # Byte manipulation
│   ├── BLAKE3/        # BLAKE3 hash function circuits
│   ├── Keccak/        # Keccak hash circuits
│   └── ...
├── Types/             # Domain-specific types (U32, U64, etc.)
├── Tables/            # Lookup tables and table-based circuits
├── Specs/             # Pure specifications (BLAKE3, Keccak specs)
├── Utils/             # Utilities and tactics
│   └── Tactics/
│       ├── CircuitProofStart.lean  # Main proof automation
│       └── ProvableStructDeriving.lean # Deriving handler
└── Circomlib/         # Circom library ports

Core Concepts

The Circuit Monad

Circuits are written using the Circuit F α monad, which accumulates operations:

def myCircuit (x : Expression F) : Circuit F (Expression F) := do
  let y ← witness (x + 1)  -- witness a new variable
  y === x + 1              -- add constraint: y = x + 1
  return y

Read the full file on GitHub · 310 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. 4d ago First seen · 310 lines · 3,447 tokens per session scan A 5125decc967f

Subscribe to this mod's changes

clean AGENTS.md is an instructions file published in the GitHub repository Verified-zkEVM/clean (180 stars, last pushed 5d ago), licensed MIT. It adds 3,447 tokens to every session, about $0.0172 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 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens