ouros CLAUDE.md

ouros CLAUDE.md is an instructions file for coding agents from parcadei/ouros. It costs 5,555 tokens per session, scanned A, original, MIT.

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.

In plain words
What is it for?
Use them when changing parsing, execution, memory handling, sandbox boundaries, or code that runs external functions.
Why use it?
They highlight the security boundaries and implementation principles that changes must preserve.

Instructions file

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 instructions/parcadei/ouros/claude-md
Clone the repo
git clone --depth 1 https://github.com/parcadei/ouros

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 ouros CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/parcadei/ouros/claude-md.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.svg" alt="Measured on agentmods" 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. 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 $0.05555 $0.05555
Opus 5 $0.02778 $0.02778
Sonnet 5 $0.01111 $0.01111
Haiku 4.5 $0.00556 $0.00556

Measured 5d ago against content hash 84b56bcd0ef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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.

  1. 5d 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 4mo ago), licensed MIT. It adds 5,555 tokens to every session, about $0.0278 per session on Opus 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.

Related

Other instructions, from other repositories

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

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 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens