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.
npx skills add GregoryHo/arcforge --skill brainstorminggit clone --depth 1 https://github.com/GregoryHo/arcforgeWrote 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/skills/gregoryho/arcforge/brainstorming)<a href="https://agentmods.dev/skills/gregoryho/arcforge/brainstorming"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/brainstorming/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/skills/gregoryho/arcforge/brainstorming"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/brainstorming.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 | $0.00050 | $0.01244 |
| Opus 5.5 | $0.00020 | $0.00498 |
| Sonnet 5.5 | $0.00010 | $0.00249 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
brainstorming 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming
The law
NO DESIGN UNTIL THE ALTERNATIVES HAVE BEEN NAMED
The first workable idea is a candidate, not a decision. Picking it silently is the failure this skill exists to stop: the user never sees what was traded away, and the cost surfaces later as rework nobody budgeted.
"The requirements are clear" is not an exemption. Clarity is what an assumption feels like from the inside.
When this does not apply
- The request is already precise and the constraints are written down.
- It is a single function, a typo, or a fix whose shape is not in question.
- The user said to just do it, or has already chosen an approach and wants it built.
- You are answering a question, not building anything.
In those cases, skip straight to the work.
1. Understand before proposing
Read first. The repository, the recent commits, the docs, any decision records — a question the repo already answers wastes the user's turn and signals you did not look.
Then ask about what you genuinely cannot determine: purpose, constraints, what "done" looks like, what must not break. One question per message, multiple choice when the options are enumerable. A batch of six questions gets three answered and three guessed.
Done when you can state, in the user's own terms, the problem, the hard constraints, and how you would recognise success.
2. Name at least two real approaches
Every option must be one you could actually defend. A straw man exists to make the other option look good and teaches the user nothing.
For each: what it costs, what it forecloses, and the situation where it is the wrong choice. Then lead with a recommendation and say why — presenting three options with no opinion pushes the decision back onto the person who came to you because they did not have one.
Done when the options differ on a dimension the user actually cares about, not just on naming or file layout.
Stay in prose and keep it conversational; do not open editors yet. Writing code during exploration converts an option into a sunk cost.
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.
- today First seen · 123 lines · 50 tokens per session scan A 2442209df191
brainstorming is a skill published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 12d ago), licensed MIT. It adds 50 tokens to every session and 1,244 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 2026-11-07.
brainstorming compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| brainstormingGregoryHo/arcforge | Skill | 8 | 12d ago | MIT | A | 50 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |