Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install devWrote 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/madappgang/magus/brainstorming)<a href="https://agentmods.dev/skills/madappgang/magus/brainstorming"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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/madappgang/magus/brainstorming"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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 | $0.00044 | $0.02770 |
| Opus 5.5 | $0.00018 | $0.01108 |
| Sonnet 5.5 | $0.00009 | $0.00554 |
| Haiku 4.5 | $0.00004 | $0.00277 |
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 22d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming: multi-model approach exploration
Turn an open problem into a chosen, reviewed plan. Several models propose approaches independently, you compare what they proposed, the user picks, and the written plan goes to an external review panel before anyone builds it.
Done means: the user chose an approach with its trade-offs in front of them, and the plan going forward has been through the external review, or the report says why it was not.
Who runs this
The main session runs it. /dev:architect routes here in Brainstorm mode. The workflow
needs two things only the main session has:
- AskUserQuestion, for the user's decisions.
- The claudish MCP tools:
list_modelsandsearch_modelsto pick the panel, andteamto run it.
External models never run through the Agent tool. Its model parameter accepts only
Claude tier aliases, so a catalog ID passed there fails. Every model that isn't the host
runs through claudish, and so does the host itself when it sits on the panel: the
native name internal in a team panel is covered by require_pattern like any other
panel member.
If you are a subagent (a loadout handed this file to the architect or spec-writer agent), you have neither tool. Do the exploration yourself. Write approaches that use genuinely different mechanisms, in the per-approach shape from step 2, and return them to the orchestrator. It presents them to the user and runs any panel.
Session directory
Use ${SESSION_PATH}/brainstorm/ when the caller passes a session path. Otherwise create
ai-docs/sessions/dev-brainstorm-<YYYYMMDD-HHMMSS>-<4 random hex bytes>/. It must sit
inside the working directory, because team rejects a path outside it. Everything the
run writes goes here: problem.md, explore/, approaches.md, plan.md, review/,
gates.log.
1. Pin down the problem
Read the code the topic touches before you ask anything. The questions worth the user's time are the ones whose answers would change which approach wins: scale and load, latency or consistency needs, dependencies the approach must keep, what is out of scope, and what "done" looks like. Skip anything the prompt or the repo already 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.
- 22d ago Changed · -343 lines · +13 tokens per session scan B → A f43eb895dfcc
- 1mo ago First seen · 588 lines · 31 tokens per session scan B e456f3621f39
brainstorming is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 2,770 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 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…