102-wildcard-brainstorm

102-wildcard-brainstorm is a cursor rule for coding agents from hamzaamjad/cursor-rules. It costs 1,645 tokens per session, scanned A, original, MIT.

Rules for brainstorming with an AI coding assistant. They encourage several unusual ideas, comparisons with unrelated fields, and deliberate variation during open-ended planning.

In plain words
What is it for?
Use them during ideation, architecture discussions, and other tasks where you want multiple unconventional software ideas before choosing one.
Why use it?
They are intended to reduce repetitive, predictable suggestions when exploring possible solutions.

Cursor rule

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/hamzaamjad/cursor-rules/102-wildcard-brainstorm
Clone the repo
git clone --depth 1 https://github.com/hamzaamjad/cursor-rules

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 102-wildcard-brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/102-wildcard-brainstorm.svg)](https://agentmods.dev/rules/hamzaamjad/cursor-rules/102-wildcard-brainstorm)
Your own site
<a href="https://agentmods.dev/rules/hamzaamjad/cursor-rules/102-wildcard-brainstorm"><img src="https://agentmods.dev/badge/rules/hamzaamjad/cursor-rules/102-wildcard-brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,645 This file is loaded in full into every session.
When invoked 1,645 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 $0.01645 $0.01645
Opus 5 $0.00822 $0.00822
Sonnet 5 $0.00329 $0.00329
Haiku 4.5 $0.00164 $0.00164

Measured 4d ago against content hash e194a9df9273, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

102-wildcard-brainstorm 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 4d 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.

rules/100-cognitive/102-wildcard-brainstorm.mdc · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wildcard-brainstorm.mdc

  • Purpose: To counteract AI models' tendency toward statistically probable responses by introducing controlled randomness and unexpected conceptual elements. This rule modifies the ideation process to explicitly encourage novel, diverse, and unconventional solutions through semantic perturbation and guided randomness techniques. Empirical Impact: Lateral thinking approaches show 25-50% creativity improvements, with AI generating 7x more viable ideas than elite human students in controlled studies.

  • Requirements:

    • Semantic Perturbation: When addressing open-ended problems, introduce 1-3 unrelated concepts or domains as "wildcards" to spark unexpected connections
    • Temperature Modulation: Increase ideation parameters (temperature=0.9, top_p=0.9) during divergent phases
    • Domain Crossing: Deliberately pull analogies from unrelated fields (e.g., biology for software architecture, music theory for data structures)
    • Quantity Over Quality: Generate 5-10 diverse options before filtering, emphasizing fluency over immediate feasibility
    • Progressive Randomness: Start with mild perturbations, increase wildness if initial ideas remain conventional
    • Meta-Prompting: Explicitly request "unconventional solutions," "surprising approaches," or "what would [unexpected persona] do?"
  • Validation:

    • Check: Were at least 3 distinctly different approaches generated?
    • Check: Does at least one solution involve cross-domain transfer?
    • Check: Are generated ideas genuinely novel (not just variations on a theme)?
    • Check: Was controlled randomness applied without losing problem relevance?
    • Check: Did the process avoid both extremes (too conventional vs. completely nonsensical)?
  • Examples:

    • Scenario: Design a caching system

      • Conventional: "Implement LRU cache with Redis backend"
      • Wildcard Applied: "What if we treat cache like a coral reef ecosystem? Old data 'dies off' naturally, frequently accessed data 'grows' in coral-like structures, and cache regions have different 'temperatures' for different data types. Music theory wildcard: Use harmonic frequencies to determine cache placement - related data resonates at similar frequencies."
    • Scenario: Optimize database queries

      • Conventional: "Add indexes and optimize JOIN order"
      • Wildcard Applied: "Ant colony optimization: Queries leave 'pheromone trails' - successful query paths get reinforced. Wildcard from cooking: Treat queries like recipe ingredients - pre-prep common 'ingredients' (subqueries) in advance. Quantum inspiration: Superposition queries that collapse to specific results only when observed."
  • Implementation Notes:

    • Best used during divergence phase of divergence-convergence workflow
    • Should feed into structured evaluation rather than direct implementation
    • Maintain "internal_thought" vs "user_facing_response" separation
    • Combine with analogy-transfer for maximum creative synergy
    • Must be balanced by risk-checkpoint to filter dangerous wildcards
  • Changes: Initial implementation v1.0.0. Establishes controlled randomness protocol based on lateral thinking research showing 25-50% creativity improvements.

  • Source References:

Read the full file on GitHub · 98 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. 4d ago First seen · 98 lines · 1,645 tokens per session scan A e194a9df9273

Subscribe to this mod's changes

102-wildcard-brainstorm is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 1,645 tokens to every session, about $0.0082 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.