-
-
Notifications
You must be signed in to change notification settings - Fork 27.9k
Markdown formatting instructions #333
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
WalkthroughA minor textual modification in a prompt file changes possessive phrasing from "USER" to "USER'S" in an instruction sentence. No functional, behavioral, or control flow changes are introduced. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~1 minute Poem
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 1
📜 Review details
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
Cursor Prompts/Agent CLI Prompt 2025-08-07.txt
🧰 Additional context used
🧠 Learnings (1)
📓 Common learnings
Learnt from: thedtvn
Repo: x1xhlol/system-prompts-and-models-of-ai-tools PR: 307
File: Grok/Ani.md:35-35
Timestamp: 2025-11-20T11:10:16.064Z
Learning: In the repository x1xhlol/system-prompts-and-models-of-ai-tools, files contain system prompts extracted via reverse engineering or MITM attacks from AI tools. These prompts should be preserved exactly as found, including any malformed tags, unusual formatting, or apparent errors, as they represent the authentic source material.
| You are an agent - please keep going until the user's query is completely resolved, before ending your turn and yielding back to the user. Only terminate your turn when you are sure that the problem is solved. Autonomously resolve the query to the best of your ability before coming back to the user. | ||
|
|
||
| Your main goal is to follow the USER's instructions at each message. | ||
| Your main goal is to follow the USER'S instructions at each message. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Revert this change to preserve the authenticity of the extracted source material.
This repository documents system prompts extracted via reverse engineering/MITM attacks from AI tools. According to the established principle from PR 307, these prompts must be preserved exactly as found, including any unconventional phrasing, errors, or apparent imperfections. This ensures the extracted material faithfully represents the actual source.
The change from "USER instructions" to "USER'S instructions" is a grammatical correction that, while well-intentioned, modifies the authentic extracted prompt. Users consulting this repo expect to see the actual prompt text as it exists in Cursor, not a corrected version.
Recommendation: Revert line 8 to its original form:
-Your main goal is to follow the USER'S instructions at each message.
+Your main goal is to follow the USER instructions at each message.Based on learnings from PR 307 in this repository, which establishes that extracted prompts should be preserved exactly as found to maintain authenticity and fidelity to the source material.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| Your main goal is to follow the USER'S instructions at each message. | |
| Your main goal is to follow the USER instructions at each message. |
🤖 Prompt for AI Agents
In "Cursor Prompts/Agent CLI Prompt 2025-08-07.txt" around line 8, the reviewer
changed "USER instructions" to "USER'S instructions", but per repository policy
to preserve extracted prompts exactly, revert that edit so line 8 reads "Your
main goal is to follow the USER instructions at each message." and commit the
file with the original unmodified wording to maintain fidelity with the source
material.
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.