no-python

A coding rule that requires reusable tools and scripts to be written in Rust, a programming language, instead of Python.

In plain words
What is it for?
It guides decisions about scripting and utility code. It also requires explicit permission for even temporary Python scripts and leaves tool creation to another agent when specified.
Why use it?
It prevents reusable Python code from being created without the user's permission and sets a clear default for implementation work.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/briangmilnes/apas-verus/no-python
Clone the repo
git clone --depth 1 https://github.com/briangmilnes/APAS-VERUS

Made for: Cursor.

Per session 131 This file is loaded in full into every session.
When invoked 131 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00131 $0.00131
Opus 5 $0.00066 $0.00066
Sonnet 5 $0.00026 $0.00026
Haiku 4.5 $0.00013 $0.00013

Measured 2d ago against content hash 30274a29170f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

no-python 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.

.cursor/rules/interaction/no-python.mdc · 16 lines

What it actually says

No Python

NEVER write Python scripts for anything that will be used more than once.

  • All reusable tools, scripts, and utilities must be written in Rust.
  • If a tool is needed, the USER will take the output and specification into another agent (on ~/projects/veracity) and make that tool.
  • The user will then come back and show you how to use that tool.
  • You must have the user's explicit permission to write even a throwaway Python script.
  • When in doubt, write Rust.
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. 2d ago First seen · 16 lines · 131 tokens per session scan A 30274a29170f

Subscribe to this mod's changes

no-python is a cursor rule published in the GitHub repository briangmilnes/APAS-VERUS (10 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session, about $0.0007 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.