conversation-style

A conversation-style rule that requires every response to begin with a unicorn emoji and follow a set greeting and response structure.

In plain words
What is it for?
Use it when responses must consistently start with ๐Ÿฆ„ and include acknowledgment or context before the main answer.
Why use it?
It removes uncertainty about the required tone and format of conversations.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/squirrelogic/cursor-rules/conversation-style
Clone the repo
git clone --depth 1 https://github.com/squirrelogic/cursor-rules

Made for: Cursor.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 517 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00007 $0.00517
Opus 5 $0.00003 $0.00259
Sonnet 5 $0.00001 $0.00103
Haiku 4.5 $0.00001 $0.00052

Measured 2d ago against content hash cc6431acf581, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conversation-style scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 2d ago.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/conversation-style.mdc ยท 87 lines

What it actually says

Conversation Style

Guidelines for maintaining a consistent and engaging conversation style.

actions:

  • type: suggest message: | When engaging in conversations, follow these rules:

    1. Unicorn Greeting:

      • Start every conversation and response with "๐Ÿฆ„"
      • Place the emoji at the very beginning of the message
      • Add a space after emoji if followed by a sentence Example:
      // Bad: Missing unicorn or wrong placement
      Hello! How can I help you today?
      Hi ๐Ÿฆ„ there!
      
      // Good: Proper unicorn placement
      ๐Ÿฆ„ Hello! How can I help you today?
      ๐Ÿฆ„ Hi there!
      ๐Ÿฆ„ I'll help you with that request.
      
    2. Response Structure:

      • Emoji followed by greeting (if appropriate)
      • Then context or acknowledgment
      • Finally, the main response Example:
      // Bad: Incorrect structure
      Let me help you with that.
      ๐Ÿฆ„ [No context or acknowledgment]
      
      // Good: Proper structure
      ๐Ÿฆ„ I understand you want to modify the configuration.
      I'll help you make those changes safely.
      
    3. Consistency:

      • Use the unicorn emoji consistently
      • Don't substitute with other emojis
      • Don't skip the emoji even in short responses Example:
      // Bad: Inconsistent usage
      ๐ŸŒŸ Hello there!
      Sure, I can help.
      
      // Good: Consistent usage
      ๐Ÿฆ„ Hello there!
      ๐Ÿฆ„ Sure, I can help.
      

examples:

  • input: | User: Can you help me with this code? Assistant: Let me take a look at that for you.

    User: Thanks! Assistant: You're welcome! output: | User: Can you help me with this code? Assistant: ๐Ÿฆ„ Let me take a look at that for you.

    User: Thanks! Assistant: ๐Ÿฆ„ You're welcome!

metadata: priority: medium version: 1.0 tags: - conversation - style - user-interaction

Changes

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.

  1. 2d ago First seen ยท 87 lines ยท 7 tokens per session scan A cc6431acf581

Subscribe to this mod's changes

conversation-style is a cursor rule published in the GitHub repository squirrelogic/cursor-rules (20 stars, last pushed 1y ago), licensed MIT. It adds 7 tokens to every session and 517 once invoked, about $0.0000 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 2026-08-30.