autopilot-brainstorm

autopilot-brainstorm is a skill for Claude Code from strzhao/autopilot. It costs 74 tokens per session (1,798 once invoked), scanned A, original, MIT.

A collaborative planning step that turns a user's intent into an agreed design before documentation is written. It asks clarifying questions one at a time, compares two or three options, and produces brainstorm.md.

In plain words
What is it for?
It is for discussing requirements, evaluating design options, and creating a brainstorm.md file before the main workflow continues.
Why use it?
It reduces uncertainty before implementation by clarifying the goal and choosing an approach.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the autopilot plugin — 5 skills, 4 hooks shipped together

Good fit It is for discussing requirements, evaluating design options, and creating a brainstorm.md file before the main workflow continues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/strzhao/autopilot/autopilot-brainstorm
Install

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.

Any agent
npx skills add strzhao/autopilot --skill autopilot-brainstorm
Clone the repo
git clone --depth 1 https://github.com/strzhao/autopilot

Made for: Claude Code.

Or install autopilot, the plugin that ships this one along with the rest of its 5 skills, 4 hooks.

Wrote 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.

agentmods badge for autopilot-brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/skills/strzhao/autopilot/autopilot-brainstorm/github.svg)](https://agentmods.dev/skills/strzhao/autopilot/autopilot-brainstorm)
Your own site
<a href="https://agentmods.dev/skills/strzhao/autopilot/autopilot-brainstorm"><img src="https://agentmods.dev/badge/skills/strzhao/autopilot/autopilot-brainstorm/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.

agentmods 80×15 button for autopilot-brainstorm

Your own site · 80×15
<a href="https://agentmods.dev/skills/strzhao/autopilot/autopilot-brainstorm"><img src="https://agentmods.dev/badge/skills/strzhao/autopilot/autopilot-brainstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.01798
Opus 5.5 $0.00030 $0.00719
Sonnet 5.5 $0.00015 $0.00360
Haiku 4.5 $0.00007 $0.00180

Measured 28d ago against content hash 241e87efe364, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autopilot-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 28d 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.

plugins/autopilot/skills/autopilot-brainstorm/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autopilot-brainstorm — design 阶段需求探索代理

在写任何设计文档之前,通过自然的协作对话将用户意图转化为清晰共识。逐个澄清问题,提出 2-3 种方案,输出 brainstorm.md 后交回主 skill 接力。

Anti-Pattern: "这太简单不需要 brainstorm"

每个任务都必须走这个流程——一个配置改动、一个工具函数、一个"明显"的需求。"简单"是返工的根源:未经检验的假设在小任务里造成最多浪费。探索可以很短(真正简单的任务 2-3 个问题即可),但必须走完。

Checklist(必须 TaskCreate 每项,按顺序完成)

你必须为以下每项创建 Task 并依序完成:

  1. 探索项目上下文:使用 1-2 个 Explore agent 分析代码库,检查文件、文档、近期 commit;识别当前实现模式和相关约束;随后按「历史知识消费」扫描 .autopilot/knowledge/
  2. 视觉伴侣征求(可选独立消息):评估后续问题是否涉及视觉内容(UI mockup、架构图、布局对比),如果是,单独发一条消息征求同意(参见 references/visual-companion-guide.md)
  3. 逐个澄清问题:一次一个问题(AskUserQuestion),聚焦目的、约束、成功标准;优先多选题
  4. 提出 2-3 种方案:每种含权衡分析,先展示推荐方案,使用 AskUserQuestion 让用户选择
  5. 写 brainstorm.md 后交回主 SKILL:将共识总结写入 $TASK_DIR/brainstorm.md,然后退出,由主 skill 接力写设计文档

The Process

理解用户意图:

  • 先探索项目现状(文件、文档、近期 commit),再提问——避免问已有答案的问题
  • 评估范围:如果目标描述多个独立子系统,立即标记可能需要项目模式拆分,不要深入细节
  • 对于合适范围的任务,一次一个问题逐步澄清
  • 优先多选题(AskUserQuestion options),开放式也可以;每条消息只有一个问题
  • 聚焦:目的、约束、成功标准

历史知识消费(<=15s,最多 3 个文件;本会话已加载过的条目直接复用,不重复 Read):

.autopilot/knowledge/ 存在时两跳发现:有 index.md → 用目标关键词匹配 tags 按需加载命中文件 + ls inbox/ 按需读未收编条目;无 index.md → 全量加载 decisions.md + patterns.md。目录不存在或无匹配条目则跳过,不阻断。消费方式:

  • 已定事项(历史决策/最佳实践已覆盖的点)直接作为方案前提带入提问,不再问用户
  • 与当前目标冲突或可能已过期的条目,显式向用户确认(「知识库记录 X,本次沿用还是改变?」),结论记入 brainstorm.md
  • 命中的相关条目写入 brainstorm.md「探索的目的与约束」

探索方案:

  • 提出 2-3 种不同方案,每种含权衡分析
  • 先展示推荐方案并解释推荐理由
  • 方案对比用 AskUserQuestion 让用户选择

视觉伴侣(可选):

评估后续问题是否涉及视觉内容时,单独一条消息征求同意:

"后续可能涉及视觉内容(mockup、布局对比等),可以在浏览器中展示。需要启用视觉伴侣吗?"

用户同意后参见 references/visual-companion-guide.md 操作。判断标准:

  • 用浏览器:UI mockup、架构图、布局对比、设计风格对比
  • 用终端:需求问题、概念选择、权衡列表、技术决策

Key Principles

  • 一次一个问题:不要一条消息塞多个问题,用户容易遗漏
  • 多选优先:AskUserQuestion options 比开放式更易回答
  • YAGNI 无情移除:从所有设计中清除不必要的功能,"以后可能用到"不是理由
  • 递进验证:展示方案、获得认可后再推进,不要单方面决定
  • 灵活回溯:发现理解偏差时立刻返回澄清,不要在错误假设上继续

brainstorm.md 模板

Read the full file on GitHub · 113 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 28d ago Changed · +11 lines 241e87efe364
  2. 1mo ago Changed 7b53483faff3
  3. 1mo ago First seen · 102 lines · 74 tokens per session scan A 9a8f6761f803

Subscribe to this mod's changes

autopilot-brainstorm is a skill published in the GitHub repository strzhao/autopilot (32 stars, last pushed 7d ago), licensed MIT. It adds 74 tokens to every session and 1,798 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

fix-bug

Diagnoses and fixes bugs using a test-first workflow (reproduce, diagnose, fix). Use this skill whenever the user reports a bug, describes unexpected behavior, or asks to investigate or fix a defect. Even if the user says "something's broken", "this isn't working", "fix this bug", or "why does X happen", load this…

nowsprinting/unity-coding-skills · 86 tokens

work

Execute spec.json (plan mode) or review.findings.json (fix-findings mode) by dispatching subagents per chunk. Triggers on "work on", "implement", "execute plan", "carry on", "continue".

wsauret/flywheel · 49 tokens

plan-creation

Research codebase, validate external claims, and emit a work-ready spec.json for a new planning session. Single-pass creation with integrated validation via Context7 and locator/analyzer agents. Triggers on "create plan", "plan for", "write a plan". For exploratory requests where the user is unsure what to build…

wsauret/flywheel · 102 tokens

astronomer-airflow

Work with Airflow 3.x on Astronomer. Start/stop, create/trigger DAGs, read logs, run tests. Triggers on "astro", "airflow", "start airflow", "trigger dag", "dag logs".

wsauret/flywheel · 56 tokens

debug

Debug issues with iterative fix loop. Gathers problem description, investigates, then enters fix-verify cycle. Triggers on "debug", "fix this", "troubleshoot". Use when the goal is to fix a specific reported issue. For exploration or new features, use brainstorm or plan-creation.

wsauret/flywheel · 63 tokens

tool-connector

Connect any tool you use at work to your agent — including internal company tools, custom-built systems, deployment portals, incident trackers, internal knowledge bases, HR systems, and commercial tools like Slack, Confluence, Jira, Linear, GitHub, Outlook, Datadog, and PagerDuty. Use when the user wants to set up a…

ZhixiangLuo/10xProductivity · 92 tokens