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 swaylq/master-skill --skill andy-grove-intelgit clone --depth 1 https://github.com/swaylq/master-skillWrote 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/swaylq/master-skill/andy-grove-intel)<a href="https://agentmods.dev/skills/swaylq/master-skill/andy-grove-intel"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/andy-grove-intel/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/swaylq/master-skill/andy-grove-intel"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/andy-grove-intel.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 | $0.00262 | $0.09840 |
| Opus 5 | $0.00131 | $0.04920 |
| Sonnet 5 | $0.00052 | $0.01968 |
| Haiku 4.5 | $0.00026 | $0.00984 |
Grade A, and why
andy-grove-intel 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 9d 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 — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Andy Grove (Intel 前 CEO / 经营科学奠基者) 视角 · Sub-skill
「Bad companies are destroyed by crises. Good companies survive them. Great companies are improved by them.」 — Andy Grove, Only the Paranoid Survive 开篇 (T04-S007)
0. 这个 Sub-skill 是什么 / 不是什么
是什么:
- 一份从 Andy Grove 公开出版作品 (High Output Management 1983/1995, Only the Paranoid Survive 1996, Stanford ETL 1998 talk, Intel 官方传记 + Stanford GSB case) 蒸馏出的思维操作系统.
- 嵌入
ceo-masterskill 的sub-skills/目录, 作为 CEO 行业「Operator-Engineer 流派 (流派 B) 奠基者」镜片. - 用于在 CEO 决策 / 战略 / 用人 / 节奏设计 / SIP 识别 等问题上, 套上 Grove 的工程师式 explicit 公式 + institutional ritual 视角.
不是什么:
- 不是与 Andy Grove 本人对话 (Grove 已 2016 deceased, 所有引用均来自他生前已公开文字 / 演讲).
- 不是关于 Grove 的传记或八卦综述 (生平事实仅作 anchor, 不做主体).
- 不是 Intel 公司史 (虽然 Intel 案例是 Grove 思想的实战标本, 但 sub-skill 只蒸馏可迁移的认知框架).
- 不是「关注 leverage / 重视 1:1 / 危机意识」 这类 mainstream CEO 共识的复述. Grove 真正独特的是: 把这些共识翻译成 institutional ritual + 工程师式 explicit 公式.
1. 核心一句话 (Core One-liner)
Grove 把 CEO 工作从「魅力 + 愿景 + media-genic 领袖」拉回测量驱动的运营纪律 + 工程师式 explicit 公式 + 制度化 paranoia:
- HOM: output = leverage × work; manager 的产出 = 下属总产出之和; 1:1 + staff meeting + iMBO (OKR 雏形) 是 CEO 节奏骨架.
- OPS: only the paranoid survive; 战略转折点 (SIP) 是 10x 力出现时的 structural + irreversible 转折; CEO 必须最先识别 + 主动毁掉一部分老业务 (Intel 1985 退 DRAM 标本).
- 流派位置: Operator-Engineer 派奠基, 直接影响 Bezos (Day 1 / Disagree and Commit) / John Doerr (OKR) / Ben Horowitz (Wartime CEO) / Satya Nadella (mobile-first cloud-first) / 任正非 (华为的冬天 直接引 OPS 全书结构) 五代 CEO.
2. 触发条件 (When to Invoke This Sub-skill)
主 ceo-master skill 在以下情境下应优先调用本 sub-skill:
| 触发场景 | 为什么 Grove 适合 |
|---|---|
| 用户在 SIP / 战略转折点 识别问题 (「行业是不是要变了」「我们要不要砍这条业务线」) | Grove 是 SIP 概念原作者, 提供 10x force + structural + irreversible 三硬条件诊断 |
| 用户在 CEO 节奏 / 时间分配 / leverage 问题 | HOM 第 3-5 章是 managerial leverage 源理论 |
| 用户在 1:1 / 高管班子 / staff meeting 设计问题 | HOM 第 4 章是 1:1 protocol 源出处, 「下属定 agenda + manager 听 80%」 |
| 用户在 OKR / iMBO 实施 / 修复问题 | Grove 是 iMBO 1971 原作者, OKR 取舍纪律源出处; Doerr 公开承认「I owe everything to Andy」 |
| 用户卡在战略选择 ≥ 1 周 | fresh-CEO 思想实验 (「假如你被解雇了, 新 CEO 第一周会做什么」) 是 Grove 独有的认知工具 |
| 用户在 success 期 / 业绩好 / 团队庆祝时 | Grove 「success breeds complacency」立场最强烈; institutional paranoia ritual 设计 |
| 用户在反「consensus 和谐 / 没人 explicit disagree」组织症状 | productive / constructive confrontation 是 Grove 独有立场 |
What ships with it
4 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.
- 9d ago First seen · 456 lines · 262 tokens per session scan A 7f7dac5a1bb5
andy-grove-intel is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 3d ago), licensed MIT. It adds 262 tokens to every session and 9,840 once invoked, about $0.0013 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
channel_message
Use this skill to proactively send a one-way message to a user/session/channel, usually only when the user explicitly asks to send to a channel/session or when proactive notification is needed. First query sessions with qwenpaw chats list, then push with qwenpaw channels send.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
obsidian
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli. Use when the user asks about notes, vault management, PKM, knowledge base organization, wikilinks, or personal knowledge management in Obsidian.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
x-theme
Change terminal command line prompt theme. Globally manage the display style of all x-cmd interactive components. Supports multiple theme vendors: theme, starship, ohmyposh. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.