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 MasonEgger/bpe-claude-code-plugin/plugin install bpeWrote 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/masonegger/bpe-claude-code-plugin/brainstorm)<a href="https://agentmods.dev/skills/masonegger/bpe-claude-code-plugin/brainstorm"><img src="https://agentmods.dev/badge/skills/masonegger/bpe-claude-code-plugin/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/masonegger/bpe-claude-code-plugin/brainstorm"><img src="https://agentmods.dev/badge/skills/masonegger/bpe-claude-code-plugin/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 | $0.00027 | $0.04015 |
| Opus 5.5 | $0.00011 | $0.01606 |
| Sonnet 5.5 | $0.00005 | $0.00803 |
| Haiku 4.5 | $0.00003 | $0.00402 |
Grade B, and why
brainstorm scanned grade B with 1 finding 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
5. Exclude the vendored rules for the author, whose live skills are the source and would otherwise load twice. Merge `"claudeMdExcludes": ["**/.claude/rules/vendored/**"]` into `.claude/settings.local.json`, creating the How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm Command
Ask me one question at a time so we can develop a thorough, step-by-step spec for this idea. Each question should build on my previous answers, and our end goal is to have a detailed specification I can hand off to a developer who will implement using good TDD practices.
Let's do this iteratively and dig into every relevant detail. Remember, only one question at a time.
Mode: New Spec or Merge
Check for spec.md at the repo root before anything else.
- Absent: new-spec mode. Run every section below in order and write a fresh spec.md at the end.
- Present: merge mode. spec.md is permanent and edited in place, so this run adds a phase to it rather than replacing it. Read the whole spec first. Skip the blindspot pass unless the user says their context changed. Scope the Q&A to the new phase only: what this phase adds or changes, not the whole project again. Run the constraints, adjacency, and tool discovery passes against the new goals only; existing Invariants, Non-goals, and Deferred entries are inputs, not questions (a Deferred item this phase takes on moves into Goals; a Goal this phase retires moves to Deferred or Non-goals, by the user's call). Then follow "Saving" in merge mode: write the merged spec to a scratch file, show
diff -u spec.md <scratch>, and move it over spec.md only after the user confirms. Superseded requirements are rewritten in place, never appended as amendments, so the spec always reads as current intent on one pass.
To start a spec over instead of merging, delete or move spec.md first; there is no overwrite flag.
Step 0: Blindspot pass
Run this pass BEFORE the substantive Q&A. It calibrates the rest of the session to what the user already knows.
- Ask ONE question about the user's starting context: domain familiarity, prior attempts at this idea, experience with this codebase (if one exists).
- Given the answer, surface 3-5 unknown-unknowns: questions the user probably doesn't know to ask, framed as "you may want to consider" rather than "you must answer". The user may engage with any, all, or none of them.
- Record the user's context answer verbatim in spec.md under
## Starting context. Create the section if it doesn't exist. Do not paraphrase; the plan writer and validator calibrate against the user's own words. - Proceed to the standard one-question-at-a-time Q&A.
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.
- 1mo ago Changed · +61 lines · +10 tokens per session scan A → B c4826e6ae009
- 1mo ago Changed 14989cd8390b
- 2mo ago First seen · 86 lines · 17 tokens per session scan A b381536b5111
brainstorm is a skill published in the GitHub repository MasonEgger/bpe-claude-code-plugin (7 stars, last pushed 27d ago), licensed MIT. It adds 27 tokens to every session and 4,015 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…