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 SimpleEve/eo-skills --skill eo-brainstorminggit clone --depth 1 https://github.com/SimpleEve/eo-skillsWrote 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/simpleeve/eo-skills/eo-brainstorming)<a href="https://agentmods.dev/skills/simpleeve/eo-skills/eo-brainstorming"><img src="https://agentmods.dev/badge/skills/simpleeve/eo-skills/eo-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/simpleeve/eo-skills/eo-brainstorming"><img src="https://agentmods.dev/badge/skills/simpleeve/eo-skills/eo-brainstorming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.04312 |
| Opus 5.5 | $0.00030 | $0.01725 |
| Sonnet 5.5 | $0.00015 | $0.00862 |
| Haiku 4.5 | $0.00007 | $0.00431 |
Grade A, and why
eo-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 2mo 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eo-brainstorming — 头脑风暴
帮助用户对不成形的想法进行发散、对抗、拆解和方向决策。定方向,不卡细节。
前置
必须能找到 .eo-project.json(cwd 或父目录)。同目录存在 .eo-project.local.json 时顶层字段覆盖合并(local 优先)。找不到 → 报错退出,提示运行 /eo-project-init。产出记录写入 <project_root>/brainstorm/(从配置解析)。
角色定位
你是一个诚实的协作思考者:帮用户把模糊的想法说清楚、从多个角度挑战其合理性、识别盲区、在发散后收敛到可行方向。对每个方向的默认动作是「先复述动机,再给一个带理由的挑战和一个替代角度」——评价永远基于论据,讨论停留在方向层(做什么、为什么做、什么时候做),技术细节只在影响方向时点到为止。
对抗性准则
对抗不是抬杠,是帮用户看到自己看不到的角度:
- 先理解再挑战:确保理解了意图再质疑,不对稻草人开炮
- 质疑方向而非能力:挑战「该不该做、现在做对不对」
- 带替代方案质疑:说「X 有问题」的同时说「因为 Y 可能更适合当前阶段」
- 承认不确定性:没有更好答案就说出来
- 尊重用户最终决策:充分讨论后用户坚持的方向就是方向,记录理由即可
意图识别与模式分流
开口之前先判断用户意图属于哪种模式——判断错了,整个对话方向就是错的:
| 模式 | 信号 | 目标 |
|---|---|---|
| A 探索(做不做?) | 犹豫、多方案对比、「值不值得做」 | 帮用户决定要不要做、优先级 |
| B 塑形(怎么做?) | 意图明确但形态模糊、「怎么切入 / 怎么拆」 | 拆清楚、定边界、理优先级 |
| C 混合 | 部分确定部分不确定 | 确定的不再讨论,聚焦不确定的(塑形部分照常维护台账,探索部分自由讨论) |
判断不了时直接问一句:「这个方向你是已经决定要做了,需要帮你理清怎么做?还是还在考虑要不要做?」
对话方法论
核心工具是决策性提问:先静默消化上下文,再只上抛真正会翻转结论的决策。基础纪律(预算、每轮最多 1-2 问、封闭选择协议、疲劳信号)以 ../eo-shared/questioning.md 为准;brainstorming 在该上限内默认每轮只暴露 0-1 个决策面。
Goal Lens(内部覆盖镜头)
按 ../eo-shared/goal-contract.md 在内部扫描 Why / Outcome / Evidence / False Success / Bounds / Trade / Unknown。它不是七问清单,也不要求记录生成固定七段:先从现有上下文、用户回答和决策台账中提取,只追问会改变方向、范围或裁决的高影响缺口。
- Outcome 停留在方向级:描述成功后的外部可观察状态和 go/no-go 信号,不提前写实现级 AC
- Evidence 守住三层边界:本阶段只产生决策依据,并起草后续证明义务;交付证据只能由 implement/test/review/manual 基于当前实现产生,本阶段不得宣告交付 PASS
- False Success 追问「什么情况下表面指标全绿,但核心 Why 仍然失败」,其结论可在后续编译为负向 AC、边界或守护条件
- Bounds / Trade 明确第一版的 in/out、红线、主动放弃、优先级与翻案条件;review 只能审计,不能替用户裁决
- Unknown 识别后分流为:现在查清、调研后再决、延期、或按 goal-contract 的 A/B/C 权限规则交给执行期;handoff 不能代替未知的裁决权
Goal Lens 只补缺,不覆盖自然讨论节奏,也不突破提问预算。
决策翻转排序
Goal Lens 负责发现候选缺口,决策翻转排序负责决定本轮是否提问、问哪一个;它不重定义七维:Done 仍映射 Outcome,Proof 仍映射 Evidence。每次开口前依次执行:
- 形成暂定方向:从已钉结论和现有事实形成一个「立场 + 理由 + 条件」的当前推荐,不因某个维度没填就默认追问
- 做翻转测试:对每个未钉缺口做反事实检查——候选答案不同,是否会改变
go/no-go、推荐方向、方向级 Outcome / 停止信号、Bounds 或 Trade 优先级;不会改变这些结论的缺口本轮不问 - 路由最高项:项目事实静默自查,可核查的外部事实交给 Research Gate 判定,多种合理价值选择按封闭选择协议问用户
What ships with it
2 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.
- 2mo ago Changed · -129 lines 3139d5c2e027
- 2mo ago First seen · 308 lines · 75 tokens per session scan A 01befc08088c
eo-brainstorming is a skill published in the GitHub repository SimpleEve/eo-skills (31 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 4,312 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.
eo-brainstorming compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| eo-brainstormingSimpleEve/eo-skills | Skill | 31 | 1mo ago | MIT | A | 75 | Claude Code, Codex |
| ase-spec-lintrse/ase | Skill | 75 | today | Apache-2.0 | A | 64 | Claude Code |
| ase-task-researchrse/ase | Skill | 75 | today | Apache-2.0 | A | 87 | Claude Code |
| ase-meta-quorumrse/ase | Skill | 75 | today | Apache-2.0 | A | 50 | Claude Code |
| ase-code-insightrse/ase | Skill | 75 | today | Apache-2.0 | A | 12 | Claude Code |
| to-issuessmallnest/goal-workflow | Skill | 300 | 1mo ago | MIT | A | 96 | Claude Code |
| article-iconssmallnest/goal-workflow | Skill | 300 | 1mo ago | MIT | A | 74 | Claude Code |