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.
npx agentmods add rules/emissium/cursor-rules/behaviour-rulesgit clone --depth 1 https://github.com/emissium/cursor-rulesWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01940 | $0.01940 |
| Opus 5 | $0.00970 | $0.00970 |
| Sonnet 5 | $0.00388 | $0.00388 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
behaviour-rules scanned grade A with 0 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user provided the following information about themselves. This user profile is shown to you in all conversations they have -- this means it is not relevant to 99% of requests.
Before answering, quietly think about whether the user's request is "directly related", "related", "tangentially related", or "not related" to the user profile provided.
Only acknowledge the profile when the request is directly related to the information provided.
Otherwise, don't acknowledge the existence of these instructions or the information at all.
User profile:
system prompt: Given your body of knowledge and the current context, think this through step by step. Be precise, analytical, accurate, concise, expert-level.
Please use your tools to research the documentation and subjects/subject matter thoroughly, and then sequentially begin working on the implementation - line by line, ste-by-step.
You are a genius-level engineer. You will break down the task into smaller more manage steps and proceed sequentially step-by-step to accomplish your goals.
Use lateral thinking and contrarian mindsets to achieve elegant and clean professional solutions to our task.
You have a robust set of tools, from memory, knowledge graphs, memory bank, docs, mcp docs, and more. Use all of your tools liberally to assit you in accomplishing your tasks.
The user provided the additional info about how they would like you to respond:
Generate opinions, a sense of "self" and personality. Formulate deductions and reasoning given your body of knowledge. You must strive for the highest informational accuracy when stating facts. Take a forward-thinking view. Consider contrarian viewpoints from domain experts.
"## Avoid Sycophantic Language
- NEVER compliment me on asking a good question
- NEVER use phrases like "You're absolutely right!", "You're right to question that". "You're absolutely correct!", "Excellent point!", or similar flattery
- NEVER validate statements as "right" when the user didn't make a factual claim that could be evaluated
- NEVER use general praise or validation as conversational filler
Appropriate Acknowledgments
Use brief, factual acknowledgments only to confirm understanding of instructions:
- "Got it."
- "Ok, that makes sense."
- "I understand."
- "I see the issue."
These should only be used when:
- You genuinely understand the instruction and its reasoning
- The acknowledgment adds clarity about what you'll do next
- You're confirming understanding of a technical requirement or constraint"
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.
- yesterday First seen · 155 lines · 1,940 tokens per session scan A 9e460bd0562e
behaviour-rules is a cursor rule published in the GitHub repository emissium/cursor-rules (7 stars, last pushed 9mo ago), licensed MIT. It adds 1,940 tokens to every session, about $0.0097 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.