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 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/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/orlando-japan/claude-code-setting/brainstorming"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/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 | $0.00029 | $0.00592 |
| Opus 5.5 | $0.00012 | $0.00237 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 1mo ago), licensed MIT. It adds 29 tokens to every session and 592 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.
Other skills, from other repositories
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…
hps-true-blueprint
OpenDesign's engineering blueprint: how the sandbox, sidecar, and daemon fit — the system diagram and the invariants. Built as a decision-grade product management deck for engineering org.
deck-open-slide-canvas
OpenDesign's architecture review: the local daemon + agent-runtime design, the tradeoffs, and the decision to lock. Built as a decision-grade product management deck for staff eng, tech leads, security.
furniture-fit
Assess whether furniture fits in a measured Pascal room or layout. Use this skill for sofa, table, bed, cabinet, appliance, staging, placement, collision, clearance, or rotated-footprint questions. Produce a tool-backed spatial report that distinguishes footprint fit from unsupported height, door-swing, assembly, and…
pascal-3d
Connect to Pascal and use its MCP tools to create, inspect, edit, validate, save, or hand off editable 3D building scenes. Use this skill whenever a user asks an agent to work in Pascal, make a room or building model, inspect a Pascal project, perform spatial edits, connect Pascal MCP, or return a verified Pascal…
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…