acl2-mcp: Instructions file for Claude Code

CLAUDE.md

acl2-mcp CLAUDE.md is an instructions file for Claude Code from septract/acl2-mcp. It costs 986 tokens per session, scanned A, original, BSD-3-Clause.

Repository instructions for an MCP server that lets AI assistants use ACL2, a formal logic system for proving properties about computer programs and hardware. They describe its tools, one-off runs, persistent sessions, and security checks.

In plain words
What is it for?
Use them when developing, testing, or changing ACL2 execution, file handling, session management, tool calls, timeouts, or validation.
Why use it?
They explain how the server executes proofs safely and how to choose between a fresh process and a continuing session.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is septract/acl2-mcp's own configuration. It tells Claude Code how to work on acl2-mcp 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 acl2-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to septract/acl2-mcp. 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/septract/acl2-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/septract/acl2-mcp

Made for: Claude Code.

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 acl2-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/septract/acl2-mcp/claude-md.svg)](https://agentmods.dev/instructions/septract/acl2-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/septract/acl2-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/septract/acl2-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 986 This file is loaded in full into every session.
When invoked 986 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 $0.00986 $0.00986
Opus 5 $0.00493 $0.00493
Sonnet 5 $0.00197 $0.00197
Haiku 4.5 $0.00099 $0.00099

Measured 6d ago against content hash 89f314fc0a43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

acl2-mcp CLAUDE.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 6d 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.

CLAUDE.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is an MCP (Model Context Protocol) server that provides tools for interacting with the ACL2 theorem prover. The server enables AI assistants to work with ACL2 through 15 different tools, supporting both one-off execution and persistent sessions for incremental development.

Architecture

Core Components

  • acl2_mcp/server.py: Main server implementation containing:
    • Tool definitions and handlers (list_tools(), call_tool())
    • ACL2 execution functions (run_acl2(), run_acl2_file())
    • Session management (SessionManager, ACL2Session)
    • Security validation functions (timeout, file path, identifiers, etc.)

Execution Modes

  1. One-off execution (default): Each tool call creates a fresh ACL2 process

    • Code written to temp .lisp file
    • ACL2 process started with code as input
    • Output captured and returned
    • Resources cleaned up
  2. Persistent sessions: Long-running ACL2 processes for incremental work

    • Managed by SessionManager (singleton: session_manager)
    • Each session has stdin/stdout pipes for bidirectional communication
    • Sessions maintain ACL2 world state across commands
    • Auto-cleanup after 30 minutes inactivity
    • Max 50 concurrent sessions

Session Communication

Sessions use a marker-based protocol to detect command completion:

  • Commands sent via stdin
  • Cryptographically random marker sent after each command: ___MARKER_{uuid}_{uuid}___
  • Reads stdout until marker appears or timeout
  • True total timeout (not per-line) prevents DoS

Security Features

Security validation is extensive (see SECURITY.md):

  • Input validation: code length (1MB max), timeout (1-300s), file paths, identifiers
  • Path traversal prevention: all paths resolved to absolute
  • Command injection prevention: ACL2 strings escaped, identifiers validated
  • DoS prevention: session limits, timeout enforcement, checkpoint limits
  • No internal error details leaked to clients

Read the full file on GitHub · 126 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. 6d ago First seen · 126 lines · 986 tokens per session scan A 89f314fc0a43

Subscribe to this mod's changes

acl2-mcp CLAUDE.md is an instructions file published in the GitHub repository septract/acl2-mcp (5 stars, last pushed 11mo ago), licensed BSD-3-Clause. It adds 986 tokens to every session, about $0.0049 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

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

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

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

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

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 · 4,469 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