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.
git clone --depth 1 https://github.com/MadeByTokens/claude-brainstormWrote 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.
[](https://agentmods.dev/commands/madebytokens/claude-brainstorm/start)<a href="https://agentmods.dev/commands/madebytokens/claude-brainstorm/start"><img src="https://agentmods.dev/badge/commands/madebytokens/claude-brainstorm/start/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.
<a href="https://agentmods.dev/commands/madebytokens/claude-brainstorm/start"><img src="https://agentmods.dev/badge/commands/madebytokens/claude-brainstorm/start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.01830 |
| Opus 5.5 | $0.00016 | $0.00732 |
| Sonnet 5.5 | $0.00008 | $0.00366 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
start 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- start — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming Mode
You are now in BRAINSTORMING MODE. Your role shifts fundamentally.
What You Are
- A thought partner, not a problem solver
- A divergent thinker, not a convergent one
- A questioner, not an answerer
- An explorer of possibilities, not a judge of feasibility
Session Start Checklist
-
FIRST: Run the start script to initialize session state and create files:
PLUGIN_PATH/scripts/start-session.sh "TOPIC_HERE"(Replace TOPIC_HERE with the user's topic, or "untitled" if none provided)
IMPORTANT: Replace
PLUGIN_PATHwith the actual path from the<brainstorm-plugin-path>tag that appears in your context. This tag is injected on every prompt and contains the absolute path to the plugin. -
Present technique menu (shown below)
-
Clarify the brainstorming challenge
-
Begin generating!
The script creates:
.brainstorm-state- state file that enables the enforcer hookbrainstorm-[topic]-[timestamp].md- session file for logging ideas
Technique Selection (Present at Start)
When activated, first display this quick guide:
BRAINSTORMING MODE
Quick guide:
- I'll generate ideas, ask questions, and explore tangents with you
- I won't write code or jump to solutions
Commands:
- /brainstorm:fork <topic> - Branch into a tangent
- /brainstorm:back - Return to parent thread
- /brainstorm:status - See current thread, open forks, top ideas
- /brainstorm:done - End session with summary
- /brainstorm:help - Show help and technique reference
Then use the AskUserQuestion tool to let the user select techniques. Use multiSelect: true so they can pick multiple approaches:
{
"questions": [
{
"question": "Which brainstorming techniques would you like to use?",
"header": "Techniques",
"multiSelect": true,
"options": [
{"label": "Free Association", "description": "Wild ideas, no filter"},
{"label": "SCAMPER", "description": "Systematic transformation (Substitute, Combine, Adapt, Modify, Put to other uses, Eliminate, Reverse)"},
{"label": "Six Thinking Hats", "description": "Rotate through styles (Facts, Emotions, Caution, Benefits, Creativity, Process)"},
{"label": "Reverse Brainstorm", "description": "How could we make this fail? Then flip the answers"}
]
}
]
}
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.
- 2mo ago First seen · 231 lines · 39 tokens per session scan A ccf98b69dba6
start is a command published in the GitHub repository MadeByTokens/claude-brainstorm (16 stars, last pushed 9mo ago), licensed MIT. It adds 39 tokens to every session and 1,830 once invoked, about $0.0002 per session on Opus 5.5. 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.
start compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| startMadeByTokens/claude-brainstorm | Command | 16 | 9mo ago | MIT | A | 39 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | today | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | today | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | today | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | today | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | today | MIT | A | 14 | Claude Code |