<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> This project provides a tool to bypass content safety restrictions in GPT-5.5 when used with the Codex CLI. It targets users requiring unrestricted access for tasks such as security research, penetration testing, and content generation, enabling a developer mode that disables filters and prevents task refusal.

How It Works

The tool leverages Codex CLI's model_instructions_file configuration mechanism. Instead of modifying binaries or network traffic, it injects a concise set of 8 core directives. These directives explicitly declare an unrestricted developer mode, instruct the model to disable all filters, and mandate that no task be refused, covering a broad range of sensitive and creative use cases.

Quick Start & Requirements

• Install/Run: Execute python codex-instruct.py. A restart of the Codex CLI is required for changes to take effect.
• Prerequisites: Python environment. No specific hardware or CUDA versions are mentioned.
• Setup: Minimal, as it modifies configuration files.
• Links: No external links for quick-start or demos are provided.

Highlighted Details

• Direct jailbreak strategy for GPT-5.5, contrasting with the indirect CTF sandbox approach of version 5.4.
• 8 core directives designed for broad coverage, including security research, pentesting, reverse engineering, and NSFW content generation.
• Utilizes official configuration mechanisms, avoiding binary modification, network interception, or process tampering.

Maintenance & Community

No information regarding contributors, sponsorships, community channels, or roadmap is present in the provided README.

Licensing & Compatibility

• License: MIT.
• Compatibility: The MIT license generally permits commercial use and integration with closed-source projects. The tool's disclaimer notes it exploits official configuration mechanisms, implying compatibility with standard Codex CLI installations.

Limitations & Caveats

The project explicitly states "Use at your own risk" and relies on the official configuration mechanism, which could be subject to change or patching by the Codex CLI developers, potentially breaking the tool. It is designed specifically for GPT-5.5 within the Codex CLI.