What is CompPoly AGENTS.md?

Project-specific instructions for working on CompPoly, a Lean 4 library for formally verified polynomial calculations over rings and finite fields.

Use them when modifying the CompPoly codebase so builds, tests, generated library files, imports, style, and documentation links are checked correctly.

They tell an agent where to make changes, which validation commands to run, and which checks apply to proofs, APIs, imports, style, and documentation.

How Verified-zkEVM/CompPoly configures Codex and OpenCode

Reuse

Borrowing it

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

Clone the repo

git clone --depth 1 https://github.com/Verified-zkEVM/CompPoly

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/verified-zkevm/comppoly/agents-md/github.svg)](https://agentmods.dev/instructions/verified-zkevm/comppoly/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/verified-zkevm/comppoly/agents-md"><img src="https://agentmods.dev/badge/instructions/verified-zkevm/comppoly/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/verified-zkevm/comppoly/agents-md"><img src="https://agentmods.dev/badge/instructions/verified-zkevm/comppoly/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,755 This file is loaded in full into every session.

When invoked 2,755 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.

Model	Per session	Once invoked
Fable 5.1	$0.02755	$0.02755
Opus 5.5	$0.01102	$0.01102
Sonnet 5.5	$0.00551	$0.00551
Haiku 4.5	$0.00276	$0.00276

Measured 3d ago against content hash 54f95ef5e671, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

CompPoly 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 3d 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 · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CompPoly AI Agent Guide

Lean 4 library for formally verified computable polynomial operations over rings and finite fields. Start with README.md for the public project overview.

AGENTS.md is the canonical root guide for AI agents and agent-oriented tooling. Human contributors should usually start with README.md, CONTRIBUTING.md, and docs/wiki/README.md. CLAUDE.md is a symlink to this file.

Fast Start

Run lake build for routine validation.
Run lake test when changing proofs, public APIs, or regression tests.
If you add, rename, or delete files under CompPoly/, run ./scripts/update-lib.sh and then ./scripts/check-imports.sh.
Use ./scripts/lint-style.sh when touching Lean style-sensitive files.
If you touch repo docs or links, run uv run --no-project --python 3.12 python ./scripts/check-docs-integrity.py.
When you fill or add a sorry (or change anything that must stay axiom-clean), run lake exe axiomsweep --check. If the change is intentional, refresh scripts/axiom_baseline.json with lake exe axiomsweep --update-baseline and commit the diff. Native-compiler trust is never baselineable.
When you make a fast implementation faster, follow the loop in docs/wiki/autoresearch.md. Edit, test, measure, and prove, in that order. Run the implementation's tests and --validate-only first. ./scripts/bench-ab.sh run <group> is the measurement. Prove the refinement theorem only after a faster verdict without SUSPECT. A sorry on that theorem stays inside an iteration and never goes into a commit.
When you add a field carrier or a polynomial representation, add its codec in the same PR. A fixed-width scalar needs CanonicalNat and ByteCodec. A fixed-length composite needs ByteCodec. A variable-length type needs DelimitedCodec. Also add the round-trip and injectivity theorems through the class interfaces. For a fast carrier, add the agreement lemma with its specification field. See "New Types Owe a Codec" in CONTRIBUTING.md and docs/wiki/serialization.md.
Before you draft or revise prose, follow docs/wiki/write-technical-prose.md.

Read the full file on GitHub · 192 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.

3d ago Changed · +11 lines · +233 tokens per session 54f95ef5e671
1mo ago Changed · +9 lines · +163 tokens per session 8879b5f3b7a2
1mo ago Changed · +28 lines · +507 tokens per session 1de9e861c35a
2mo ago Changed · +4 lines · +77 tokens per session 4a8e5246f60d
2mo ago First seen · 140 lines · 1,775 tokens per session scan A ca536aec8514

Subscribe to this mod's changes

CompPoly AGENTS.md is an instructions file published in the GitHub repository Verified-zkEVM/CompPoly (49 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,755 tokens to every session, about $0.0110 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.

CompPoly AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
CompPoly AGENTS.mdVerified-zkEVM/CompPoly	Instructions file	49	3d ago	Apache-2.0	A	2,755	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

CompPoly: Instructions file for Codex