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/verified-zkevm/vcvio/agents-mdgit clone --depth 1 https://github.com/Verified-zkEVM/VCVioWrote 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.
[](https://agentmods.dev/instructions/verified-zkevm/vcvio/agents-md)<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>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.
| Model | Per session | Once 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 |
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.
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
- Run
lake exe cache get && lake build. - Read
Examples/OneTimePad/Basic.leanfor a compact modern proof (correctness and privacy). - Choose the work area by task: use
VCVio/for oracle/probability/program-logic work,LatticeCrypto/for lattice schemes and reductions, andLatticeCryptoTest/for vectors or differential tests. - 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-- § Titleline. The/-!form is rendered bydoc-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 ownnamespaceor its own file. See Section Headers Within A File inCONTRIBUTING.md.
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.
- 2d ago Changed · +2 lines · +96 tokens per session 1ff1e73a2ea1
- 6d ago First seen · 271 lines · 5,618 tokens per session scan A e920569096af
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.
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.
emilia-protocol CLAUDE.md
Claude Code instructions for emiliaprotocol/emilia-protocol, covering emilia protocol - repo guide, required context, critical, build & ship and outbound & claims.
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…
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.
formal CLAUDE.md
Instructions for yamafaktory/formal, covering formal, rust, the files that judge changes, hints and lean.
leanforge-mcp AGENTS.md
AGENTS.md instructions for sandraschi/leanforge-mcp, covering agents.md -- leanforge-mcp, stack, repo layout, critical rules and lean subprocess.