What is claude-brainstorm CLAUDE.md?

A Claude Code plugin that keeps an interaction in brainstorming mode instead of allowing an immediate jump to implementation. It uses commands and automatic hooks to manage ideas and discussion threads.

Starting and managing brainstorming sessions, creating forks for related ideas, checking progress, and producing a summary when the session ends.

It helps explore alternatives and tangents systematically before choosing a solution.

How MadeByTokens/claude-brainstorm configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to MadeByTokens/claude-brainstorm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MadeByTokens/claude-brainstorm/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/MadeByTokens/claude-brainstorm

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/madebytokens/claude-brainstorm/claude-md/github.svg)](https://agentmods.dev/instructions/madebytokens/claude-brainstorm/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/madebytokens/claude-brainstorm/claude-md"><img src="https://agentmods.dev/badge/instructions/madebytokens/claude-brainstorm/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/madebytokens/claude-brainstorm/claude-md"><img src="https://agentmods.dev/badge/instructions/madebytokens/claude-brainstorm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 682 This file is loaded in full into every session.

When invoked 682 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00682	$0.00682
Opus 5	$0.00341	$0.00341
Sonnet 5	$0.00136	$0.00136
Haiku 4.5	$0.00068	$0.00068

Measured 10d ago against content hash 8d9f7a2ee7e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-brainstorm CLAUDE.md 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 10d 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.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Claude Brainstorm is a Claude Code plugin that enforces brainstorming mode, preventing Claude from jumping to solutions. It uses hooks to intercept interactions and keep Claude in divergent thinking mode.

Architecture

The plugin consists of three core components:

Commands (commands/*.md) - Slash commands that users invoke:
- /brainstorm:start <topic> - Initialize session, present technique menu
- /brainstorm:fork <topic> - Create nested thread for tangent exploration
- /brainstorm:back - Return to parent thread
- /brainstorm:status - Show progress (current thread, forks, top ideas)
- /brainstorm:done - End session, generate summary file
- /brainstorm:help - Show commands and techniques
Hooks (hooks/) - Automatic enforcement:
- brainstorm-enforcer.sh (UserPromptSubmit) - Injects rules reminder on every prompt when session active
- hooks.json - Configures PreToolUse hooks for Write, Bash, WebSearch
Scripts (scripts/) - Session management and auto-approval:
- start-session.sh - Creates .brainstorm-state and brainstorm-*.md session file
- end-session.sh - Cleans up state file
- approve-brainstorm-*.sh - Auto-approve hooks for plugin operations

State Management

Active sessions create .brainstorm-state in the working directory containing:

BRAINSTORM_ACTIVE, SESSION_FILE, TOPIC, STARTED
CURRENT_THREAD, THREAD_STACK, FORK_COUNT, IDEA_COUNT

The enforcer hook sources this file on every prompt. Presence of BRAINSTORM_ACTIVE=1 triggers rule injection.

Hook Flow

User prompt → UserPromptSubmit → brainstorm-enforcer.sh checks .brainstorm-state
                                          ↓
                               If active: injects rules to Claude
                                          ↓
                               Claude processes in brainstorm mode
                                          ↓
Tool calls → PreToolUse → approve-*.sh scripts auto-approve:
  - Writes to brainstorm-*.md (includes *-summary.md files)
  - Bash: start-session.sh, end-session.sh, tree commands
  - WebSearch (during active sessions)

Read the full file on GitHub · 69 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.

10d ago First seen · 69 lines · 682 tokens per session scan A 8d9f7a2ee7e9

Subscribe to this mod's changes

claude-brainstorm CLAUDE.md is an instructions file published in the GitHub repository MadeByTokens/claude-brainstorm (13 stars, last pushed 7mo ago), licensed MIT. It adds 682 tokens to every session, about $0.0034 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.

Planning

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-brainstorm: Instructions file for Claude Code