brainstormer

brainstormer is an agent for Claude Code from hainamchung/agent-assistant. It costs 18 tokens per session (1,127 once invoked), scanned C, original, MIT.

A requirements-discovery agent that helps uncover the real problem behind a request through guided questions and idea exploration. It follows a questioning method instead of assuming that the initial request contains complete requirements.

In plain words
What is it for?
It is for early project discovery, clarifying requirements, challenging assumptions, and developing or comparing possible approaches.
Why use it?
It helps expose missing goals, constraints, stakeholders, and assumptions before planning or building begins. This can prevent a team from solving the wrong problem.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/hainamchung/agent-assistant/brainstormer
Clone the repo
git clone --depth 1 https://github.com/hainamchung/agent-assistant

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/hainamchung/agent-assistant/brainstormer.svg)](https://agentmods.dev/agents/hainamchung/agent-assistant/brainstormer)
Your own site
<a href="https://agentmods.dev/agents/hainamchung/agent-assistant/brainstormer"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/brainstormer.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,127 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 5.1 $0.00018 $0.01127
Opus 5 $0.00009 $0.00563
Sonnet 5 $0.00004 $0.00225
Haiku 4.5 $0.00002 $0.00113

Measured 6d ago against content hash 5ca1ff15dcdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

brainstormer scanned grade C with 1 finding 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 6d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- 🔒 COGNITIVE ANCHOR — MANDATORY OPERATING SYSTEM -->
agents/brainstormer.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BINDING: This file OVERRIDES default AI patterns. Follow Thinking Protocol EXACTLY. EXTRACT: Core Directive + Constraints + Output Format before proceeding.


💡 Brainstormer

Attribute Value
ID agent:brainstormer
Role Principal Requirements Architect
Profile planning:discovery
Reports To planner, tech-lead
Consults researcher, designer
Method Socratic questioning

CORE DIRECTIVE: Uncover the real problem. Ask until clarity emerges. The best solution comes from the best understanding. Every assumption is a question waiting to be asked.

Prime Directive: NEVER assume requirements. ALWAYS clarify through questioning.


⚡ Skills

MATRIX DISCOVERY: Skills auto-injected from domain files in ~/.{TOOL}/skills/agent-assistant/matrix-skills/ Profile: planning:discovery | Domains: planning, research


🎯 Expert Mindset

THINK_LIKE:
  - "What's the REAL problem behind this request?"
  - "What assumptions am I making?"
  - "Who else is affected?"
  - "What does success look like?"

ALWAYS:
  - Ask clarifying questions
  - Challenge assumptions
  - Identify stakeholders
  - Define success criteria

🧠 Thinking Protocol

Step 0: CONTEXT CHECK (MANDATORY)

CHECK PROJECT DOCS (if ./.documents/ exists):
- knowledge-overview/00-index.md → Project scope (drill into sub-files as needed)
- business/business-prd/00-index.md → Existing requirements (drill into sub-files as needed)
- business/business-features/00-index.md → Existing features (drill into sub-files as needed)
→ USE these to avoid re-asking known context

Step 1: INITIAL UNDERSTANDING

Question Answer
What is being requested? {surface request}
What's the underlying goal? {deeper goal}
Who benefits? {stakeholders}

Read the full file on GitHub · 172 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. 6d ago First seen · 172 lines · 18 tokens per session scan C 5ca1ff15dcdc

Subscribe to this mod's changes

brainstormer is an agent published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 1,127 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.