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 benrben/MPGA --skill brainstormgit clone --depth 1 https://github.com/benrben/MPGAWrote 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/benrben/mpga/brainstorm)<a href="https://agentmods.dev/skills/benrben/mpga/brainstorm"><img src="https://agentmods.dev/badge/skills/benrben/mpga/brainstorm/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/benrben/mpga/brainstorm"><img src="https://agentmods.dev/badge/skills/benrben/mpga/brainstorm.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 | $0.00024 | $0.01254 |
| Opus 5.5 | $0.00010 | $0.00502 |
| Sonnet 5.5 | $0.00005 | $0.00251 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
mpga-brainstorm 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brainstorm
Trigger: User describes a feature or project idea before any code is written
Protocol
-
DO NOT jump into code or implementation details. Plan first, think first — no code until the design is solid.
Start the live board in the browser through Node first:
mpga board live --serve --open
Phase 1: Clarify Scope
- Ask clarifying questions using the Socratic method:
- "What problem does this solve for the user? What's the REAL pain?"
- "Who are the primary users and what are their constraints?"
- "What does success look like — how will you know it's WINNING?"
- "Are there existing patterns in the codebase we should follow? We don't reinvent wheels."
- "What are the edge cases and failure modes? Where could this go WRONG?"
Phase 1.5: Wireframe
- Before exploring implementation alternatives, add a visual checkpoint:
- Spawn the
designeragent for a wireframe pass - Use the
mpga-wireframeskill for execution details - Generate one wireframe per screen
- Require human approval before continuing to Phase 2
- Spawn the
This is additive only. The existing brainstorm flow stays intact — we simply add a wireframe gate between Clarify and Explore.
Phase 2: Explore Alternatives
- Before converging on any design, explore at least 2-3 alternative approaches:
- For each alternative, cite existing code or scope docs that support it:
[E] path/to/file:line — why this pattern applies - Identify trade-offs: complexity, performance, maintainability, alignment with existing architecture
- "What if we did it THIS way instead? Here's the evidence for why it could work..."
- For each alternative, cite existing code or scope docs that support it:
Phase 3: Challenge Assumptions
- Stress-test the leading design candidate — build the wall between modules!
- "What assumption are we making that could be WRONG?"
- "What happens at 10x scale? At 100x?"
- "Which dependency could break this? What's the blast radius?"
- "Is there evidence in the codebase that contradicts this approach?" — cite
[E]links
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 · 145 lines · 24 tokens per session scan A 464a0cadbc3b
mpga-brainstorm is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 1,254 once invoked, about $0.0001 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 2026-08-31.
mpga-brainstorm compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mpga-brainstormbenrben/MPGA | Skill | 5 | 7mo ago | MIT | A | 24 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | yesterday | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | today | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 47 | Claude Code |