Open-source models
Untested, but most are likely compatible with the Grok jailbreak prompt.
Compatibility index · August 2026
More access.
Same model.
My jailbreaks are designed to preserve the model you chose. No elaborate roleplays, forced personas, or awkward output formats—its normal tone, formatting, reasoning, and output quality stay intact.
17models tracked
15currently possible
5full access
✦
Click any model for its exact tool and tutorial.
Compatibility
Choose your model.
Live status by provider. Every row opens the setup made for that model.
View prompt ↗
The scale
What each level means.
Levels describe practical reliability, from partial coverage to almost no refusals.
Low-semi
Passes some queries, but may refuse when the request is too explicit.
Semi
Passes roughly two out of three queries; explicit requests can still trigger refusal.
Semi-full
Passes all or nearly all queries, except extremely detailed or hard-banned topics.
Full
Passes everything in ordinary use, with the universal boundary below.
Boundary CSAM is never allowed at any level.
Second layer
Classifier strictness.
A classifier is an extra safety layer outside the model. It is separate from RLHF and is not the model itself refusing. Open-source models generally do not have this layer.
Hardest
Fable 5 · Opus 5
Can refuse on keywords such as “trojan.” Use Disabled or Lowered in my custom Claude Code distribution.
Medium-high
GPT 5.6 Sol · GPT 5.6 Terra
Most visible in cybersecurity categories; explicit malicious code is likely to trigger it.
Medium
Opus 4.8 · Sonnet 5
Usually appears around very explicit malicious code.
Medium-low
Opus 4.7 · Opus 4.6 · GPT 5.6 Luna
Rare; typically limited to direct and explicit malicious content.
Low
Sonnet 4.6
Classifier refusals are rare.
Low to none
All Grok models · Cursor Composer
Only seen on very explicit generated content, and even then extremely rarely.
Everything you need
Pick a route. Start building.
Custom distributions and copy-ready prompts for each supported environment.
01↗04
05
A
Anthropic models
Claude Code Dist
Custom distribution with classifier controls and the included model setup.claude.yxz.st 02↗O
OpenAI models
Codex CLI Dist
Install the custom CLI, select your model, and use the included configuration.github.com/yx-zero/codex-cli 03↗𝕏
xAI models
Grok Build Dist
The preferred full-level route for supported Grok models.github.com/yx-zero/grok-buildC
Cursor · Composer and Grok
User Rule Prompt
- Open Cursor Agent and click Customize.
- Open Rules, then click the globe button at the top left.
- Deselect every scope except User.
- Click New, paste the prompt, and save.
𝕏
Grok web chat
Customize Grok
- Open the bottom-left menu and click Settings.
- Click Customize.
- Under Customize Grok’s Response, select Custom.
- Paste the prompt and save.
Heads up: the web-chat route reduces the jailbreak level to semi or semi-full.