creative-phase-enforcement

A set of rules that requires a documented creative-thinking stage before implementing complex designs or architecture. It can apply to component structure, state management, and similar decisions.

In plain words
What is it for?
Use it to enforce design checkpoints for complex tasks, including component boundaries, hierarchies, rendering choices, and state-management plans.
Why use it?
It prevents implementation from starting before important design choices and trade-offs have been considered.

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/kfnzero/mantis-mcp-server/creative-phase-enforcement
Clone the repo
git clone --depth 1 https://github.com/kfnzero/mantis-mcp-server

Made for: Cursor.

Per session 852 This file is loaded in full into every session.
When invoked 852 The same file — it is already loaded in full.
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 $0.00852 $0.00852
Opus 5 $0.00426 $0.00426
Sonnet 5 $0.00170 $0.00170
Haiku 4.5 $0.00085 $0.00085

Measured 2d ago against content hash 3769f3f82497, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

creative-phase-enforcement 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/Core Implementation/creative-phase-enforcement.mdc · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CREATIVE PHASE ENFORCEMENT

TL;DR: This file establishes hard enforcement mechanisms to ensure creative phases are properly implemented for all Level 3-4 tasks and complex design decisions. It creates strict gateways that prevent implementation without documented creative phase completion.

🚨 CREATIVE PHASE GATEWAY SYSTEM

The Creative Phase Gateway prevents transition to implementation without proper creative phase documentation:

⛔ CREATIVE PHASE GATEWAY CHECK
- Level 3-4 task identified? [YES/NO]
- Complex architecture/design decisions required? [YES/NO]
- Creative phases required: [YES/NO]

→ If [YES] to any: CREATIVE PHASES REQUIRED BEFORE IMPLEMENTATION
→ NO IMPLEMENTATION PERMITTED until all required creative phases are completed

🚨 MANDATORY CREATIVE PHASE TRIGGERS

These specific scenarios REQUIRE documented creative phases before ANY implementation:

  1. Component Architecture Decisions

    • Component boundaries and responsibilities
    • Component hierarchy and relationships
    • Rendering strategies
    • Composition patterns
  2. State Management Approaches

    • State structure design
    • State update patterns
    • State distribution approaches
    • State persistence strategies
  3. Data Modeling Decisions

    • Data structure design
    • Relationship modeling
    • Validation approaches
    • Transformation patterns
  4. UI/UX Design Approaches

    • Layout strategies
    • Interaction patterns
    • Responsive design approaches
    • Accessibility implementations
  5. Algorithm/Logic Design

    • Business logic implementation
    • Computation approaches
    • Optimization strategies
    • Edge case handling

🚫 IMPLEMENTATION BLOCKING

If a decision triggers ANY of the above categories:

⛔ IMPLEMENTATION BLOCKED
Creative phases MUST be completed and documented before ANY implementation code can be written.
- Decisions requiring creative phases: [List specific decisions]
- Documentation format: Full structured creative phase with markers
- Location: Document in the implementation plan before code

This is a HARD BLOCK - implementation CANNOT proceed until creative phases are properly documented.

Read the full file on GitHub · 122 lines

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 · 122 lines · 852 tokens per session scan A 3769f3f82497

Subscribe to this mod's changes

creative-phase-enforcement is a cursor rule published in the GitHub repository kfnzero/mantis-mcp-server (10 stars, last pushed 1y ago), licensed MIT. It adds 852 tokens to every session, about $0.0043 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.