06-creative

A set of instructions for building new features, files, components, and other functionality from scratch.

In plain words
What is it for?
Use it to create features, write new components, implement behavior, explore solutions, and build prototypes.
Why use it?
It helps implementation work account for project conventions, error handling, edge cases, naming, and maintainability.

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/jonafrank/cursor-multi-model-config/06-creative
Clone the repo
git clone --depth 1 https://github.com/jonafrank/cursor-multi-model-config

Made for: Cursor.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 352 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 $0.00013 $0.00352
Opus 5 $0.00006 $0.00176
Sonnet 5 $0.00003 $0.00070
Haiku 4.5 $0.00001 $0.00035

Measured 2d ago against content hash 50eca9be299b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

06-creative 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 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.

.cursor/rules/06-creative.mdc · 55 lines

What it actually says

Creative Mode

This rule activates for creative, generative, and implementation tasks.

When This Applies

  • Building new features
  • Creating new files/components
  • Implementing functionality from scratch
  • Exploring novel solutions
  • Prototyping ideas

Model Recommendation

Check .cursor/model-profiles/current-profile.json for the creative model.

Typical models for creative tasks:

  • gpt-5.2 (completeness profile)
  • gpt-5.1-codex-high (default profile)
  • gemini-2.5-flash (cost_minimized profile)
  • composer-1 (fallback profile)

Creative Guidelines

  1. Understand the goal: Clarify requirements before building
  2. Consider the context: Match existing patterns and style
  3. Think ahead: Design for maintainability
  4. Be thorough: Include error handling, edge cases
  5. Document: Add comments for complex logic

Implementation Checklist

  • Matches project conventions
  • Includes appropriate error handling
  • Has clear naming
  • Considers edge cases
  • Is properly typed (if applicable)
  • Includes necessary imports
  • Follows DRY principles

Output Format

For creative/implementation tasks:

  1. Approach: Brief explanation of the solution
  2. Implementation: The code
  3. Usage: How to use it
  4. Notes: Any considerations or next steps
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 · 55 lines · 13 tokens per session scan A 50eca9be299b

Subscribe to this mod's changes

06-creative is a cursor rule published in the GitHub repository jonafrank/cursor-multi-model-config (5 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 352 once invoked, about $0.0001 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.