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 agentmods add skills/masonegger/bpe-claude-code-plugin/brainstormnpx skills add MasonEgger/bpe-claude-code-plugin --skill brainstormgit clone --depth 1 https://github.com/MasonEgger/bpe-claude-code-pluginWhat 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 | $0.00017 | $0.01756 |
| Opus 5 | $0.00009 | $0.00878 |
| Sonnet 5 | $0.00003 | $0.00351 |
| Haiku 4.5 | $0.00002 | $0.00176 |
Grade A, and why
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 2d 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 — 86 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.
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.
Critical Focus Areas
TDD Implementation Ready: Ensure the spec includes requirements for YOUR application logic that can be converted into failing tests first. Focus on business rules, data validation, error handling, and custom algorithms that YOU will implement, not framework or library behavior. Think about what application-specific behaviors need verification.
Component Boundaries: Identify clear, testable components that can be implemented independently and then integrated together. Each component should have well-defined inputs, outputs, and responsibilities.
Global Claude Config Integration: Follow the established development patterns and preferences from the user's global Claude configuration (found in ~/.claude/CLAUDE.md and related files). Respect their preferred tools, coding standards, and project structure approaches.
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.
- 2d 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 10d ago), licensed MIT. It adds 17 tokens to every session and 1,756 once invoked, about $0.0001 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.