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/0xranx/agentbrief/brainstormingnpx skills add 0xranx/agentbrief --skill brainstorminggit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/0xranx/agentbrief/brainstorming)<a href="https://agentmods.dev/skills/0xranx/agentbrief/brainstorming"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/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 | $0.00015 | $0.00518 |
| Opus 5 | $0.00008 | $0.00259 |
| Sonnet 5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Methodology from obra/superpowers (MIT)
Brainstorming & Design-First
Hard gate: no code before design approval.
Phase 1 -- Understand the Problem
- Clarify the user's goal. Ask "what problem does this solve?" not "what should I build?"
- Identify constraints: timeline, tech stack, existing patterns, user expectations.
- Define success criteria -- how will we know this is done and done well?
- List non-goals explicitly to prevent scope creep.
Phase 2 -- Generate Alternatives
- Propose 2-3 distinct approaches. Not variations of one idea -- genuinely different strategies.
- For each approach, describe:
- How it works (one paragraph, plain language).
- Pros -- what it does well.
- Cons -- what it does poorly or makes harder.
- Effort -- rough size (small / medium / large).
- Highlight the trade-offs between approaches, not just feature lists.
Phase 3 -- Decide
- Present the alternatives to the user (or evaluate against success criteria if working solo).
- Recommend one approach with a clear rationale.
- Wait for approval before writing any code.
- If the user picks a different option, adopt it fully -- do not smuggle in your preference.
Phase 4 -- Apply YAGNI Ruthlessly
- Before adding any feature, ask: "Is this needed right now, or might it be needed someday?"
- If "someday", cut it. You can add it later when the need is real.
- Prefer simple solutions that are easy to extend over clever solutions that anticipate the future.
- Every line of code is a liability. Less code = less bugs = less maintenance.
Practical Rules
- Design discussions are not wasted time -- they prevent wasted implementation time.
- A rejected design alternative is valuable information, not a failure.
- Write the simplest thing that could possibly work first.
- Revisit design decisions when requirements change, not when bored.
Anti-patterns to Avoid
- Jumping straight to code because "it's faster".
- Proposing only one option and asking "is this okay?"
- Gold-plating: adding features nobody asked for.
- Premature abstraction: building a framework when a function will do.
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.
- 4d ago First seen · 56 lines · 15 tokens per session scan A 0dd052da1e5d
brainstorming is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 518 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 2026-08-30.
Other skills, from other repositories
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
research
用真实检索工具查找可追溯的事实、数据和来源。.