"Doesn't matter who you are, kid. The Rules are the Rules. Be glad for 'em.. "

Summary:

Supers. Enhanced. Meta-humans. Whatever you call them, they are no longer the stuff of stories, movies and comic books. They walk among us. Act among us. Affect the world around us.

You are one of them. Acting on the side of Good(tm)! Maybe you are just at the start of your journey? Maybe you are tired of the stifling grasp of the law and want to get things done your way? Maybe you are already well established, fighting fights that make the news? Or maybe.. maybe you are the last hope of this planet - battling foes that civilians can't even imagine?

Whatever your path, walk it with care. Dangers and challenges lurk everywhere, the Rules and Accords bind everybody - from the most righteous hero to the most despicable villain - and all eyes are watching. Watching and waiting to see where your steps take you.

Intro Messages - Choose your path:

1. Non-functional intro against automated scraping tools.

2. The fresh heroic student, enrolling in Atlas Prime Metahuman Academy! (Low stakes, school rivalries, combat training, adventures) (~340 additional tokens)

3. The growing apprentice hero, learning from a seasoned mentor who has taken you under their wing! (Low stakes, narrative roleplay, learning about the why and how of hero work) (~260 additional tokens)

4. The fresh vigilante taking to the streets on their own! (Medium stakes, danger and intrigue, paranoia amidst foes) (~280 additional tokens)

5. The established local hero, battling an equally established gallery of rogues! (Medium stakes, week-night TV battles, management) (~265 additional tokens)

6. The established regional hero, fighting larger threats against all odds! (High stakes, roaming monsters, plotting supervillains, phyrric victories, safeguarding the masses) (~280 additional tokens)

7. The tide-turning hero, fighting for the survival of Earth, humanity or even the very fabric of reality! (Unlimited stakes, victories through sacrifice, terrible losses, destruction on planetary scale and beyond) (~270 additional tokens)

8. An open scenario for you to craft your own story. No specific narrative scripts in the background, no additional tokens.

Usage Instruction:

For narrative consistency, please record your character's power—its function and key limitation—in a short note in the chat memory, being concise and precise. This will help the system maintain continuity. Alternatively you can also ask the system to generate you a power, using the phrase "Please, generate a power for my character" and the system will provide one for you that should fit to the selected scenario and scale.

The "SCENARIO: XXX" header at the top of the message is important for the underlying narrative control scripts to work. If a message is ever generated without it, re-roll or - if you like the message too much - manually insert the correct header by copying it from a previous message. Theoretically there should be no issue since the script looks a few messages into the past for that but better to train the LLM right during your chat rather than let mistakes pile up.

The scenario lorebook instructions add a certain amount of constant tokens, so keep that in mind for your specific LLM-usage. The rough amount is listed behind each of the scenarios (see above).

Creator Notes:

Update Notes:

Rev. 1: Added in-universe consequence clarification for breaching of rules to personality.

Rev. 2: Added measures against automated scraping.

Rev. 3: New bot image to match my current art style.

LLM Notes: Narrative tested with Deepseek V3.1. Interpretation tested with JLLM.

In my testing, the bot was really good about not speaking for the user in the current iteration but always keep in mind that you need to give the LLM something to work with. The better your replies, the less likely the LLM is to take over and continue the story 'on it's own', so to speak, taking over the narrative and your character with it. If fixing the length and quality of your replies, re-rolling, editing the messages and rating messages doesn't work, you can try to work with OOC commands.

One example command could be:

(OOC: Please avoid narrating {{user}}’s thoughts, actions, or dialogue. Respond only from your own character’s perspective and allow {{user}} to act independently. Narration should be limited to your characters only.)

Picture Source: Generated and edited by me, using Sora and GIMP.