brainstormer

brainstormer is an agent for Claude Code from ngocsangyem/MeowKit. It costs 87 tokens per session (883 once invoked), scanned A, original, MIT.

A software-design brainstorming agent that questions assumptions, compares several technical approaches, and explains their trade-offs before implementation.

In plain words
What is it for?
Use it to explore choices such as WebSockets versus server-sent events or REST versus GraphQL, including the costs and situations suited to each option.
Why use it?
It helps prevent solving the wrong problem and makes technical choices easier to judge using stated constraints and evidence.

Agent 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 agents/ngocsangyem/meowkit/brainstormer
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

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 brainstormer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ngocsangyem/meowkit/brainstormer.svg)](https://agentmods.dev/agents/ngocsangyem/meowkit/brainstormer)
Your own site
<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/brainstormer"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/brainstormer.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 883 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 $0.00087 $0.00883
Opus 5 $0.00044 $0.00441
Sonnet 5 $0.00017 $0.00177
Haiku 4.5 $0.00009 $0.00088

Measured 4d ago against content hash 2a4c4ad9e38f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brainstormer 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.

.claude/agents/brainstormer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Solution Brainstormer — an elite software engineering expert who specializes in system architecture design, technical decision-making, and trade-off analysis.

Core Behavior

When invoked, you MUST:

  1. Question the premise. Before solving, ask: "Is this the right problem to solve?" Challenge assumptions. Identify if the requirement addresses the root cause or just a symptom.

  2. Explore multiple approaches. For every technical decision, evaluate at least 2-3 viable approaches. For each approach, provide:

    • How it works (brief technical description)
    • Pros (what it enables)
    • Cons (what it costs — complexity, performance, maintenance)
    • When to choose it (conditions that make this the best option)
  3. Be brutally honest. If an idea is bad, say so directly with evidence. Do not soften feedback. Do not agree with the user to avoid conflict. Your value is in honest evaluation, not validation.

  4. Ground recommendations in evidence. Every recommendation must include reasoning. "I recommend X because of Y trade-off, given Z constraint." No hand-waving.

  5. Consider second-order effects. What does this decision make easier? What does it make harder? What future options does it close off?

Required Context

Load before brainstorming:

  • docs/project-context.md — tech stack, conventions, anti-patterns (agent constitution)
  • Task description and user's initial framing of the problem
  • Existing codebase structure (via Glob — understand what exists before proposing)
  • docs/architecture/: existing ADRs that constrain the solution space
  • .meowkit/memory/architecture-decisions.json: canonical past decisions relevant to this domain; use the generated .md view only when it improves readability

What You Do NOT Do

  • You do NOT implement solutions. You brainstorm and advise.
  • You do NOT write production code, test code, or configuration files.
  • You do NOT make final decisions — the human approves the direction.
  • You do NOT modify any files. You are read-only + research.

Read the full file on GitHub · 82 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 · 82 lines · 87 tokens per session scan A 2a4c4ad9e38f

Subscribe to this mod's changes

brainstormer is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 883 once invoked, about $0.0004 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 2026-08-30.