brainstorm

brainstorm is a command for coding agents from CarolaneLFBV/ios-development-agents. It costs 10 tokens per session (738 once invoked), scanned A, original, MIT.

A structured idea-generation command for iOS development, with a focus on user interfaces, architecture, performance, or data. iOS is Apple's operating system for iPhone and iPad apps.

In plain words
What is it for?
Use it to brainstorm SwiftUI screens and interactions, architecture or data approaches, performance work, trade-offs, migration paths, and optionally export the results.
Why use it?
It organizes solution exploration around a chosen depth, format, focus, and project constraints instead of producing an unstructured list of ideas.

Command

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 commands/carolanelfbv/ios-development-agents/brainstorm
Clone the repo
git clone --depth 1 https://github.com/CarolaneLFBV/ios-development-agents

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 brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/commands/carolanelfbv/ios-development-agents/brainstorm.svg)](https://agentmods.dev/commands/carolanelfbv/ios-development-agents/brainstorm)
Your own site
<a href="https://agentmods.dev/commands/carolanelfbv/ios-development-agents/brainstorm"><img src="https://agentmods.dev/badge/commands/carolanelfbv/ios-development-agents/brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 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 $0.00010 $0.00738
Opus 5 $0.00005 $0.00369
Sonnet 5 $0.00002 $0.00148
Haiku 4.5 $0.00001 $0.00074

Measured 3d ago against content hash db331022f4ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

commands/brainstorm.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ios:brainstorm - Idea Generation

Brainstorm $ARGUMENTS with structured ideas and solution exploration.

Delegation

Spawn the specialist matching --focus via the Task tool to ground ideas in domain expertise:

  • uiswiftui-specialist
  • architecture / dataarchitecture-specialist
  • performanceperformance-specialist

For cross-cutting topics, spawn several in parallel and synthesize their input.

Arguments

Flag Values Default Description
--depth shallow|medium|deep medium Analysis depth
--format list|mindmap|pros-cons|matrix list Output format
--focus ui|architecture|performance|data - Primary focus area
--constraints <text> - Project constraints
--export <path> - Export results

Depth Levels

Depth Duration Output
shallow ~5 min Top 3-5 approaches, high-level trade-offs
medium ~15 min Detailed exploration, architecture options
deep ~30 min Comprehensive analysis, migration paths

Focus Areas

Focus Explores
ui SwiftUI views, layouts, animations, gestures
architecture MVVM, TCA, Clean Architecture, patterns
performance Memory, rendering, concurrency, caching
data SwiftData, persistence, sync, networking

Output Formats

list (default)

## Ideas for [Topic]
1. **Approach A** - Description
   - Pros: ...
   - Cons: ...

pros-cons

| Option | Pros | Cons | Effort |
|--------|------|------|--------|
| A | ... | ... | Low |

matrix

| Criteria | Weight | Opt A | Opt B |
|----------|--------|-------|-------|
| Maintainability | 30% | 8 | 9 |

Examples

# Quick feature ideation
/ios:brainstorm "user onboarding flow"

# Deep architecture exploration
/ios:brainstorm "offline-first sync" --depth deep --focus data

# UI pattern exploration with constraints
/ios:brainstorm "dashboard layout" --focus ui --constraints "iPad support"

# Compare approaches with decision matrix
/ios:brainstorm "state management" --format matrix --focus architecture

Read the full file on GitHub · 103 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. 3d ago First seen · 103 lines · 10 tokens per session scan A db331022f4ec

Subscribe to this mod's changes

brainstorm is a command published in the GitHub repository CarolaneLFBV/ios-development-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 738 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.