VCVio AGENTS.md

VCVio AGENTS.md is an instructions file for Codex, OpenCode from Verified-zkEVM/VCVio. It costs 5,714 tokens per session, scanned A, original, Apache-2.0.

A project guide for Verified-zkEVM/VCVio, a Lean and Mathlib codebase for machine-checked cryptographic proofs. It explains where to work, how to build the project, and how to write Lean files and documentation.

In plain words
What is it for?
Use it when changing proof code, tests, documentation, headers, imports, or probability-related definitions in the repository.
Why use it?
It gives coding agents the project’s conventions and helps them choose the right module, build command, and troubleshooting checks.

Instructions file for CodexOpenCode

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

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/vcvio/agents-md
Clone the repo
git clone --depth 1 https://github.com/Verified-zkEVM/VCVio

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 VCVio AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/verified-zkevm/vcvio/agents-md.svg)](https://agentmods.dev/instructions/verified-zkevm/vcvio/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/verified-zkevm/vcvio/agents-md"><img src="https://agentmods.dev/badge/instructions/verified-zkevm/vcvio/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,714 This file is loaded in full into every session.
When invoked 5,714 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 5.1 $0.05714 $0.05714
Opus 5 $0.02857 $0.02857
Sonnet 5 $0.01143 $0.01143
Haiku 4.5 $0.00571 $0.00571

Measured 2d ago against content hash 1ff1e73a2ea1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

VCVio 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 2d 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 · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VCVio — AI Agent Guide

Machine-checked cryptographic proofs in Lean, built on Mathlib.

Fast Start

  1. Run lake exe cache get && lake build.
  2. Read Examples/OneTimePad/Basic.lean for a compact modern proof (correctness and privacy).
  3. Choose the work area by task: use VCVio/ for oracle/probability/program-logic work, LatticeCrypto/ for lattice schemes and reductions, and LatticeCryptoTest/ for vectors or differential tests.
  4. If probability lemmas fail unexpectedly, first check for [IsProbabilitySpec spec] or [IsUniformSpec spec] as appropriate.

AGENTS.md is the canonical guide. CLAUDE.md is a symlink to this file.

Attribution, Headers, And Docstrings

Follow CONTRIBUTING.md for the repo's explicit attribution policy.

  • New Lean files should use the standard copyright / license / authors header and a module docstring.
  • For ordinary Lean source files, use the standard prologue layout: header, blank line, module, public imports, blank line, module docstring.
  • Docstrings must be intrinsic and descriptive. Cross-reference live sibling definitions when helpful, but do not mention removed or renamed declarations, change history, or use reactive wording such as "replaces" or "renamed from".
  • Preserve existing headers on routine edits.
  • Only rewrite attribution when a file is genuinely new or materially replaced.
  • Do not add a separate AI-attribution line.
  • For inline section breaks within a Lean file, use Mathlib-style doc-comment headers /-! ## Title -/ (or the multi-line /-! ## Title \n\n explanation -/ form). Do not use ASCII banners such as -- ====...=== flanking a -- § Title line. The /-! form is rendered by doc-gen4; ASCII banners are not, and they make the file feel artificially partitioned. If a section is large enough to want a loud header, it is usually large enough to want its own namespace or its own file. See Section Headers Within A File in CONTRIBUTING.md.

Read the full file on GitHub · 273 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. 2d ago Changed · +2 lines · +96 tokens per session 1ff1e73a2ea1
  2. 6d ago First seen · 271 lines · 5,618 tokens per session scan A e920569096af

Subscribe to this mod's changes

VCVio AGENTS.md is an instructions file published in the GitHub repository Verified-zkEVM/VCVio (144 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,714 tokens to every session, about $0.0286 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

emilia-protocol AGENTS.md

AGENTS.md instructions for emiliaprotocol/emilia-protocol, covering repository instructions for ai agents, required first read, source discipline, context maintenance and verification.

emiliaprotocol/emilia-protocol · 697 tokens

emilia-protocol CLAUDE.md

Claude Code instructions for emiliaprotocol/emilia-protocol, covering emilia protocol - repo guide, required context, critical, build & ship and outbound & claims.

emiliaprotocol/emilia-protocol · 852 tokens

emilia-protocol GEMINI.md

Gemini CLI instructions for emiliaprotocol/emilia-protocol: Read AGENTS.md and AICONTEXT.md before analyzing or editing this repository. Use public/.well-known/emilia-context.json for current evidence counts and provenance. Do not infer current behavior or standards status from archived, staged, private, or randomly…

emiliaprotocol/emilia-protocol · 68 tokens

emilia-protocol copilot-instructions.md

Copilot instructions for emiliaprotocol/emilia-protocol: Read AGENTS.md and AICONTEXT.md before proposing changes. Current evidence and provenance are in public/.well-known/emilia-context.json. Treat archived, staged, private, and outreach documents as non-authoritative for current behavior or standards status.

emiliaprotocol/emilia-protocol · 63 tokens

formal CLAUDE.md

Instructions for yamafaktory/formal, covering formal, rust, the files that judge changes, hints and lean.

yamafaktory/formal · 814 tokens

leanforge-mcp AGENTS.md

AGENTS.md instructions for sandraschi/leanforge-mcp, covering agents.md -- leanforge-mcp, stack, repo layout, critical rules and lean subprocess.

sandraschi/leanforge-mcp · 1,078 tokens