FloatSpec: Instructions file for Claude Code

CLAUDE.md

FloatSpec CLAUDE.md is an instructions file for Claude Code from Beneficial-AI-Foundation/FloatSpec. It costs 7,737 tokens per session, scanned A, original, Apache-2.0.

Project instructions for FloatSpec, a Lean 4 project that develops a formally verified floating-point implementation and its specifications and tests.

In plain words
What is it for?
Use them when implementing floating-point operations, writing formal specifications, or adding property-based tests in Lean 4.
Why use it?
They provide the project context and working rules needed to make changes consistently and use compiler and linter feedback.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Beneficial-AI-Foundation/FloatSpec's own configuration. It tells Claude Code how to work on FloatSpec 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 FloatSpec configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Beneficial-AI-Foundation/FloatSpec. 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/Beneficial-AI-Foundation/FloatSpec/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Beneficial-AI-Foundation/FloatSpec

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 FloatSpec CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/beneficial-ai-foundation/floatspec/claude-md/github.svg)](https://agentmods.dev/instructions/beneficial-ai-foundation/floatspec/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/beneficial-ai-foundation/floatspec/claude-md"><img src="https://agentmods.dev/badge/instructions/beneficial-ai-foundation/floatspec/claude-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 FloatSpec CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/beneficial-ai-foundation/floatspec/claude-md"><img src="https://agentmods.dev/badge/instructions/beneficial-ai-foundation/floatspec/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,737 This file is loaded in full into every session.
When invoked 7,737 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 $0.07737 $0.07737
Opus 5 $0.03868 $0.03868
Sonnet 5 $0.01547 $0.01547
Haiku 4.5 $0.00774 $0.00774

Measured 11d ago against content hash 38a211098dcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

FloatSpec 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 11d 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 · 608 lines

How it starts

The opening of the file, as written. The whole thing — 608 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FloatSpec Project Overview

You are a functional programmer working in Lean 4.

Main Goal: Create a provable Lean float implementation with formal verification. Use bootstrapping from feedback like compiler error messages to guide development.

IMPORTANT: "Keep Going" Context

If you're told to "keep going" without context, you're likely working on:

  1. Float Implementation - Developing provable floating-point arithmetic
  2. Specification Writing - Creating formal specifications for float operations
  3. Test Writing - Add more property-based tests using Plausible

General Programming Philosophy

Programming is about onomastics (naming), composition (functoriality), and caching. Think conformally at every scale and across scales.

Build a pit of success: internal systems that grow as a whole outwards, never allowing the fallible external world to leak in except at boundaries. Meet the external world at well-defined interfaces.

When solving problems, write tooling/linters/auto-fixers to widen the pit of success. Use rigid compiler error messages and linter warnings to guide future users (including AI) toward correct solutions.

Favor statically typed functional programming but use mutability where it makes sense or is easier to port.

Project Structure

  • FloatSpec.lean and FloatSpec/ directory - core float functionality and specifications.
  • lakefile.lean - Lean 4 project configuration.

Development Commands

just is our main program runner. It provides a unified interface for all common development tasks. Run just without arguments to see all available commands.

Key commands:

  • just build - Build Lean project
  • just test - Run the Python test suite
  • just bootstrap - Bootstrap developer environment (Rust, Elan, UV)

You can also run underlying tools directly:

  • lake build - Build Lean project (use frequently for constant feedback)
  • uv run -m pytest - Run Python tests directly

Commit Logging Process

After making a commit, create a log entry:

Read the full file on GitHub · 608 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. 11d ago First seen · 608 lines · 7,737 tokens per session scan A 38a211098dcc

Subscribe to this mod's changes

FloatSpec CLAUDE.md is an instructions file published in the GitHub repository Beneficial-AI-Foundation/FloatSpec (21 stars, last pushed yesterday), licensed Apache-2.0. It adds 7,737 tokens to every session, about $0.0387 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

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 · 5,153 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

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

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