agentmods.dev

VCVio: Instructions file for Codex

AGENTS.md

VCVio AGENTS.md is an instructions file for Codex, OpenCode from Verified-zkEVM/VCVio. It costs 10,507 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.

This is Verified-zkEVM/VCVio's own configuration. It tells Codex and OpenCode how to work on VCVio 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 VCVio configures →

not rated 172repo +4 changed today A scan 10,507 tokens original Apache-2.0
View source ↗ Verified-zkEVM/VCVio
Reuse

Borrowing it

Nothing to install: this file belongs to Verified-zkEVM/VCVio. 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/Verified-zkEVM/VCVio/main/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/github.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/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 VCVio AGENTS.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,507 This file is loaded in full into every session.
When invoked 10,507 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.10507 $0.10507
Opus 5.5 $0.04203 $0.04203
Sonnet 5.5 $0.02101 $0.02101
Haiku 4.5 $0.01051 $0.01051

Measured today against content hash 269168528c3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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 · 490 lines

How it starts

The opening of the file, as written. The whole thing — 490 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 𝒟 lemmas fail unexpectedly, check for [OracleSpec.AnswerMeasure spec] and a measurable space on the result type; oracle answer types need none. The concrete unifSpec and coinSpec have global uniform-measure instances; other specs need a chosen interpretation.

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 · 490 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. today Changed · -6 lines · -27 tokens per session 269168528c3a
  2. 2d ago Changed · +4 tokens per session f216923475f8
  3. 12d ago Changed · +17 lines · +394 tokens per session 6f1854d43135
  4. 13d ago Changed · +18 lines · +493 tokens per session 92ae93799a19
  5. 15d ago Changed · -1 lines · -5 tokens per session 104e3c72882a
  6. 17d ago Changed · +18 lines · +256 tokens per session 378e345f5853
  7. 26d ago Changed · +3 lines · +151 tokens per session e8fea681d0ec
  8. 1mo ago Changed · +16 lines · +273 tokens per session c1ac18e64972
  9. 1mo ago Changed · +5 lines · +103 tokens per session c536c392eab4
  10. 1mo ago First seen · 420 lines · 8,865 tokens per session scan A 8335330569fe

Subscribe to this mod's changes

VCVio AGENTS.md is an instructions file published in the GitHub repository Verified-zkEVM/VCVio (172 stars, last pushed today), licensed Apache-2.0. It adds 10,507 tokens to every session, about $0.0420 per session on Opus 5.5. 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.

cryptographyformal-verificationlean4post-quantum-cryptographyprogram-logicproof-assistant
Related

VCVio AGENTS.md compared with instructions from other repositories

VCVio AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
VCVio AGENTS.mdVerified-zkEVM/VCVioInstructions file172todayApache-2.0A10,507Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode