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/orlando-japan/claude-code-setting/brainstormingnpx skills add orlando-japan/claude-code-setting --skill brainstorminggit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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/orlando-japan/claude-code-setting/brainstorming)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/brainstorming"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/brainstorming.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00592 |
| Opus 5 | $0.00015 | $0.00296 |
| Sonnet 5 | $0.00006 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming
The goal isn't "a list of ideas" — it's "enough options to know the current favorite is actually the best."
When
- Non-obvious design decisions (storage model, API shape, async strategy).
- Before a spec or ADR.
- When the first idea feels right (that's when to look hardest for alternatives).
Protocol
Phase 1 — Diverge (timebox: 10–20 min).
Generate at least three distinct approaches. Not three variants of the same idea — three approaches that would lead to different code and different trade-offs.
For each approach, write:
- The one-sentence idea.
- What it optimizes for (speed, simplicity, consistency, cost…).
- The most obvious failure mode.
If you can only think of one, you haven't thought about it. Forcing three alternatives is the point.
Phase 2 — Converge.
Compare on:
- Correctness — can this actually solve the problem, or does it punt on an important case?
- Simplicity — how much code? How many new concepts for future readers?
- Reversibility — if we're wrong, how painful is it to change?
- Operability — how does this fail in production, and how do we notice?
- Time to first value — how long before a user sees anything?
Phase 3 — Pick and record rejected options.
Write: "We chose A because X. We rejected B because Y. We rejected C because Z."
Rejected options are the most valuable output of brainstorming — future maintainers will otherwise re-derive them.
Forcing functions
- Pre-mortem. "Imagine this is 6 months old and broken. What went wrong?" Do this for each option.
- Reverse the prior. If you're leaning toward building, ask: "what if we bought it / didn't build it at all?"
- The extreme cases. What does this approach do at 10x scale? At 1/10x? At 0 users?
Anti-patterns
- Rubber-stamping. "I brainstormed and the first idea won" — suspicious, always.
- Straw-man alternatives. If your "rejected" options are all obviously bad, you stacked the deck. Steelman them.
- Analysis paralysis. Timebox the diverge phase. The goal is decision quality, not list length.
- Skipping the record of rejections. Without them, the decision looks arbitrary in six months.
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.
- 5d ago First seen · 62 lines · 29 tokens per session scan A 91a92860e22a
brainstorming is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 592 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
architecture-aware-init
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
architecture-decision-record
ADR templates in the Nygard format with context, decision, consequences, and alternatives. Use when writing ADRs, recording an architectural decision, or evaluating options.
adhd
Use when parallel divergent ideation for agents — spawns N isolated reasoning branches under different cognitive frames, then scores, clusters, prunes traps, and deepens survivors. Use for open-ended design, architecture, naming, API surface decisions, fuzzy debugging, and brainstorming. Skip for syntax lookups or…
fill-in-missing-assumptions
How to use Assumption Surfacing and Sensitivity Analysis to uncover silent presuppositions, prevent architectural failure, and stress-test recommendations.
design-decision-log
Use when a team needs to record significant technical decisions with context, rationale, and consequences for future reference.
architecture-decision-record
Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Helps teams maintain architectural memory and rationale for backend systems, API designs, database choices, and infrastructure…