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/feiskyer/claude-code-settings/brainstormingnpx skills add feiskyer/claude-code-settings --skill brainstorminggit clone --depth 1 https://github.com/feiskyer/claude-code-settingsWhat 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 | $0.00093 | $0.02334 |
| Opus 5 | $0.00046 | $0.01167 |
| Sonnet 5 | $0.00019 | $0.00467 |
| Haiku 4.5 | $0.00009 | $0.00233 |
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 3d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
头脑风暴:从想法到设计
通过自然的协作对话,帮助用户将想法转化为完整的设计和规格文档。
先了解当前项目上下文,然后逐个提问来细化想法。一旦理解了要构建的内容,呈现设计方案并获得用户认可。
反模式:"这个太简单了不需要设计"
一旦触发了这个 skill,即使项目看起来很简单(一个 todo list、一个单函数工具),也要走设计流程。"简单"项目恰恰最容易因为未检验的假设而浪费工作量。设计可以很短(对于真正简单的项目只需几句话),但必须呈现并获得认可。
检查清单
必须为以下每一项创建任务,并按顺序完成:
- 探索项目上下文 — 检查文件、文档、最近的提交
- 适时提供可视化伴侣 — 不要一开始就提供。当某个问题用"看"比"说"更清楚时,在那个时刻提出(单独一条消息);用户同意后为他们打开浏览器标签页。如果整个过程不需要可视化,就不要提。详见下方"可视化伴侣"章节。
- 提出澄清问题 — 每次只问一个,理解目的/约束/成功标准
- 提出 2-3 个方案 — 附带权衡分析和你的推荐
- 呈现设计 — 按复杂度分节展示,每节之后获得用户认可
- 编写设计文档 — 保存到
docs/specs/YYYY-MM-DD-<主题>-design.md并提交 - 规格自审 — 快速检查占位符、矛盾、歧义、范围(见下方)
- 用户审阅规格 — 请用户审阅规格文件后再继续
- 过渡到实现 — 创建实施计划并开始工作
流程图
探索项目上下文 → 提出澄清问题 → 提出 2-3 个方案 → 分节呈现设计
↓
用户认可设计? —[否,修改]→ 返回呈现设计
↓ 是
编写设计文档 → 规格自审(就地修复) → 用户审阅规格?
↓ ↓ 需要修改 → 返回编写设计文档
↓ ↓ 通过
└──────────────────────────────────── 开始实现
终态是开始实现。 用户批准规格后,创建分步实施计划并开始编码。
流程详解
理解想法:
- 先了解当前项目状态(文件、文档、最近提交)
- 在深入提问之前先评估范围:如果需求描述了多个独立子系统(例如"构建一个有聊天、文件存储、计费和分析的平台"),立即指出这一点。不要花时间细化一个需要先拆分的项目
- 如果项目对一份规格来说太大,帮助用户分解为子项目:独立的部分有哪些,它们如何关联,应该按什么顺序构建?然后对第一个子项目走正常设计流程。每个子项目有自己的 规格 → 计划 → 实现 循环
- 对范围合适的项目,逐个提问来细化想法
- 尽量使用选择题,开放式也可以
- 每条消息只问一个问题——如果某个话题需要更多探讨,拆成多个问题
- 关注:目的、约束、成功标准
探索方案:
- 提出 2-3 个不同方案及其权衡
- 以对话方式呈现选项,附带你的推荐和理由
- 先说你推荐的方案并解释为什么
呈现设计:
- 一旦你认为理解了要构建的内容,呈现设计
- 每节的详细程度与其复杂度匹配:简单的几句话,复杂的可到 200-300 字
- 每节之后询问用户是否正确
- 覆盖:架构、组件、数据流、错误处理、测试
- 准备好在某处不清楚时回头澄清
为隔离和清晰而设计:
- 将系统拆分为更小的单元,每个单元有一个清晰的职责,通过定义良好的接口通信,可以独立理解和测试
- 对每个单元,你应该能回答:它做什么,怎么使用它,它依赖什么?
- 别人能不看内部实现就理解一个单元的功能吗?能修改内部实现而不破坏使用者吗?如果不能,说明边界需要重新划分
- 更小、边界清晰的单元也更容易处理——对能在上下文中完整容纳的代码,推理更准确,编辑更可靠。当文件变得很大时,通常意味着它做了太多事
在已有代码库中工作:
- 在提出变更之前先了解现有结构。遵循现有模式
- 如果现有代码的问题影响到当前工作(例如文件过大、边界不清、职责纠缠),将针对性改进纳入设计——就像一个好开发者在工作时顺手改善接触到的代码
- 不要提出无关的重构。专注于当前目标
设计之后
文档:
- 将验证过的设计(规格)写入
docs/specs/YYYY-MM-DD-<主题>-design.md- (用户对规格存放位置的偏好优先于此默认路径)
- 写作要清晰简洁——短句、主动语态、具体细节优于模糊概括
- 将设计文档提交到 git
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 147 lines · 93 tokens per session scan A 7dcfe706f78b
brainstorming is a skill published in the GitHub repository feiskyer/claude-code-settings (1,644 stars, last pushed 20d ago), licensed MIT. It adds 93 tokens to every session and 2,334 once invoked, about $0.0005 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
github-review-pr
Review GitHub pull requests with evidence-backed, multi-perspective analysis and false-positive filtering. Use when the user asks to review, inspect, or check a GitHub pull request by number or URL. Default to reporting findings locally; publish comments, submit reviews, or approve only when the user explicitly…
brainstorming
在构建新功能、创建新组件或设计新系统之前使用。通过协作对话探索用户意图、需求和设计方案,再进入实现阶段。当用户描述想要构建的东西且涉及设计决策时触发——不用于 bug 修复、配置变更或实现路径显而易见的任务。.
claude-skill
Use when work should be delegated to Claude Code CLI, especially headless claude -p runs, automation scripts, CI jobs, resumable sessions, or requests to use Claude/Claude Code for a task.
nanobanana-skill
Generate, remix, or edit images with Nanobanana / Nano Banana 2 through the bundled Gemini CLI wrapper. Use this whenever the user wants AI image generation or editing, especially for reference-image composition, character consistency, grounded visuals that may need live web search, style transfer, marketing graphics…
gpt-image-skill
Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Triggers: "gpt image", "openai image", "generate image with openai", "draw image", "create image", "image generation", "AI drawing", "图片生成", "AI绘图", "生成图片", "画图". Use this skill whenever the user wants to generate or edit images and…
deep-research
深度调研的多实例(多 Agent)编排工作流:把一个调研目标拆成可并行子目标,用 Codex CLI 子进程采集和分析证据,再聚合、核验并精修为完整报告。用于系统性网页或资料调研、竞品与行业分析、批量链接或数据集分片、长文证据整合,以及用户提及深度调研、Deep Research、Wide Research、多 Agent 并行调研或多进程调研的场景。.