brainstorm

brainstorm is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 40 tokens per session (542 once invoked), scanned A, original, MIT.

A planning mode for exploring several possible approaches to a feature, architecture choice, or technical decision before writing code.

In plain words
What is it for?
Use it to compare at least three approaches, add a Mermaid diagram, and frame an open design question.
Why use it?
It makes alternatives, trade-offs, risks, and data flows visible before the team commits to one direction.

Command for Claude Code

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/kumaran-is/claude-code-onboarding/brainstorm
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

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/kumaran-is/claude-code-onboarding/brainstorm.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/brainstorm)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/brainstorm"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 542 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 $0.00040 $0.00542
Opus 5 $0.00020 $0.00271
Sonnet 5 $0.00008 $0.00108
Haiku 4.5 $0.00004 $0.00054

Measured yesterday against content hash e1d1087e3661, 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 yesterday.

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.

.claude/commands/brainstorm.md · 71 lines

What it actually says

Brainstorm

Divergent exploration before committing to an approach. No code yet — only ideas, trade-offs, and diagrams.

Input

$ARGUMENTS — the topic, feature, or decision to explore (e.g. "real-time notifications for NestJS", "auth strategy", "database for user sessions")

If $ARGUMENTS is empty, ask: "What do you want to explore?"

Process

  1. Load feature-forge skill for requirements context if the topic is a new feature
  2. Ask one clarifying question if the topic is ambiguous — only one, not a questionnaire
  3. Generate ≥ 3 distinct options — not variations of the same idea
  4. For each option, produce the structured block below
  5. Draw a Mermaid diagram for the option that best illustrates the architecture or data flow
  6. End with an open question — do not pick a winner unless asked

Output Format

## Exploring: [topic]

### Option A: [Name]
**What it is:** [one sentence]
✅ Pros: [2–4 bullets]
❌ Cons: [2–4 bullets]
⚠️  Watch out for: [biggest risk or gotcha]

### Option B: [Name]
...

### Option C: [Name]
...

---

### Diagram — [Option that benefits most from visualization]

[Mermaid block]

---

What resonates? Or should we explore a different direction?

Rules

  • No code — this mode is for deciding, not building
  • No recommendation unless the user explicitly asks "which would you choose?"
  • Minimum 3 options — if you can only think of 2, add a "hybrid" or "unconventional" option
  • Each option must be genuinely distinct (different trade-off profile, not just different library names)
  • If the topic maps to an existing skill (e.g. database design → database-schema-designer, architecture → architecture-design), note that skill at the end as the next step

Example

/brainstorm real-time notifications for NestJS

Produces: WebSockets vs SSE vs Firebase vs Polling — with trade-offs on scaling, complexity, mobile support, and a Mermaid diagram of the SSE flow.

$ARGUMENTS

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. yesterday First seen · 71 lines · 40 tokens per session scan A e1d1087e3661

Subscribe to this mod's changes

brainstorm is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 542 once invoked, about $0.0002 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 2026-09-03.