What is ouros CLAUDE.md?

Repository instructions for Ouros, a Rust-based interpreter that runs a limited form of Python inside a restricted environment. They describe its architecture and strict rules for preventing untrusted code from reaching the host system.

Use them when changing parsing, execution, memory handling, sandbox boundaries, or code that runs external functions.

They highlight the security boundaries and implementation principles that changes must preserve.

How parcadei/ouros configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to parcadei/ouros. 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/parcadei/ouros/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/parcadei/ouros

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/parcadei/ouros/claude-md/github.svg)](https://agentmods.dev/instructions/parcadei/ouros/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/parcadei/ouros/claude-md"><img src="https://agentmods.dev/badge/instructions/parcadei/ouros/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/parcadei/ouros/claude-md"><img src="https://agentmods.dev/badge/instructions/parcadei/ouros/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,555 This file is loaded in full into every session.

When invoked 5,555 The same file — it is already loaded in full.

Security scan A 2 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	$0.05555	$0.05555
Opus 5.5	$0.02222	$0.02222
Sonnet 5.5	$0.01111	$0.01111
Haiku 4.5	$0.00556	$0.00556

Measured 2mo ago against content hash 84b56bcd0ef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ouros CLAUDE.md scanned grade A with 2 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const m2 = new Ouros('fetch(url)', { inputs: ['url'], externalFunctions: ['fetch'] })

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

* subprocess/shell execution - os.system, subprocess, etc.

CLAUDE.md · 559 lines

How it starts

The opening of the file, as written. The whole thing — 559 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

Ouros is a sandboxed Python interpreter written in Rust. It parses Python code using Ruff's ruff_python_parser but implements its own runtime execution model for safety and performance. This is a work-in-progress project that currently supports a subset of Python features.

Project goals:

Safety: Execute untrusted Python code safely without FFI or C dependencies, instead sandbox will call back to host to run foreign/external functions.
Performance: Fast execution through compile-time optimizations and efficient memory layout
Simplicity: Clean, understandable implementation focused on a Python subset
Snapshotting and iteration: Plan is to allow code to be iteratively executed and snapshotted at each function call
Targets the latest stable version of Python, currently Python 3.14

Important Security Notice

It's ABSOLUTELY CRITICAL that there's no way for code run in an Ouros sandbox to access the host filesystem, or environment or to in any way "escape the sandbox".

Ouros will be used to run untrusted, potentially malicious code.

Make sure there's no risk of this, either in the implementation, or in the public API that makes it more like that a developer using the ouros package might make such a mistake.

Possible security risks to consider:

filesystem access
path traversal to access files the users did not intend to expose to the ouros sandbox
memory errors - use of unsafe memory operations
excessive memory usage - evading ouros's resource limits
infinite loops - evading ouros's resource limits
network access - sockets, HTTP requests
subprocess/shell execution - os.system, subprocess, etc.
import system abuse - importing modules with side effects or accessing __import__
external function/callback misuse - callbacks run in host environment
deserialization attacks - loading untrusted serialized Ouros/snapshot data
regex/string DoS - catastrophic backtracking or operations bypassing limits
information leakage via timing or error messages
Python/Javascript/Rust APIs that accidentally allow developers to expose their host to ouros code

Read the full file on GitHub · 559 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.

2mo ago First seen · 559 lines · 5,555 tokens per session scan A 84b56bcd0ef4

Subscribe to this mod's changes

ouros CLAUDE.md is an instructions file published in the GitHub repository parcadei/ouros (146 stars, last pushed 6mo ago), licensed MIT. It adds 5,555 tokens to every session, about $0.0222 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ouros CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ouros CLAUDE.mdparcadei/ouros	Instructions file	146	6mo ago	MIT	A	5,555	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ouros: Instructions file for Claude Code