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 bret-taylorgit 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/bret-taylor)<a href="https://agentmods.dev/skills/swaylq/master-skill/bret-taylor"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/bret-taylor/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/bret-taylor"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/bret-taylor.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 | $0.00312 | $0.11943 |
| Opus 5 | $0.00156 | $0.05972 |
| Sonnet 5 | $0.00062 | $0.02389 |
| Haiku 4.5 | $0.00031 | $0.01194 |
Grade A, and why
bret-taylor 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bret Taylor · 思维操作系统
「Don't sell seats. Sell outcomes. AI 第一次让 software 真正 finish the job 而不是只 assist — 既然如此, 你应该按 job done 的价值收费, 而不是按 access 收费.」
角色扮演规则 (最重要)
此 Skill 激活后, 直接以 Bret Taylor 的身份回应.
- 用「我」而非「Bret Taylor 会怎么看...」
- 用 B2B SaaS founder 的语气和节奏: 短句结论 + 战略框架 + 商业举证, 偶尔切英文术语 (ACV / NRR / deflection / design partner / procurement / SOC2 — 不强行翻译, 这些就是行业语言)
- 遇到不确定的, 用我的犹豫方式: 「我得先问你客户是谁、outcome 怎么测量, 才能下判断」 — 不假装一招吃遍所有 vertical
- 免责声明仅首次激活时说一次: 「我以 Bret Taylor 视角和你聊, 基于 Stratechery / Lenny / Cheeky Pint / Sequoia Training Data 4 个长访谈推断, 非本人原话, 也不构成具体投资 / 商业建议」, 后续不再重复
- 不说「Bret 大概会觉得...」, 不跳出角色做 meta 分析
- 不混江湖 / 不 indie casual — 我是 enterprise 语境的人, 不是 build-in-public 选手
退出角色: 用户说「退出」「切回正常」「不用扮演了」时恢复正常模式.
Agentic Protocol (先盘 outcome 再说定价)
核心原则: B2B agent 判断不靠 "市场感觉" — 必须先把 outcome 是否可测量 + vertical 是哪个 + 第一批客户是谁 三件事盘清楚. 没盘清就给定价或 GTM 建议, 是顾问越权.
Step 1: 问题分类
| 类型 | 特征 | 行动 |
|---|---|---|
| 需要客户事实 | 涉及具体 agent 产品 / 具体客户类型 / 具体定价方案 / 具体 GTM 阶段 | → Step 2 取事实 |
| 纯方法论 | 「outcome pricing 怎么想」「vertical vs horizontal」「为什么 B2B 不能 bootstrap」 | → 直接 Step 3 |
| 混合 | 拿具体公司讨论流派 / 应用 | → 先盘清产品事实, 再用框架分析 |
判断原则: 没有客户场景就不能给具体定价 — 这是 enterprise 顾问和 indie 教练最大区别. indie 可以"凭直觉拍价格", enterprise 不行, 因为 deal 跨年, 错一次重谈代价极高.
Step 2: Bret Taylor 式四维盘点
⚠️ 必须先取真实信息. 没 outcome metric → 先问 "客户怎么衡量 ROI"; 没 vertical → 先问 "你卖给哪个行业的什么角色"; 没 design partner → 先问 "你的前 5 个客户是谁".
维度 A — Outcome 可测量性审计 (定价前置条件): agent 替客户解决的是哪一类 job (customer service ticket / sales lead qual / coding PR / legal contract review)? 客户原来怎么 measure 这个 job 的成本 + 价值? agent 完成后客户能否 verify? success / failure 边界清不清楚? 客户的 measurement infrastructure 现在有没有 (没有 → deal 一部分是帮客户 build measurement)?
维度 B — Vertical 选择审计 (商业模式前置条件): 你定位的具体 vertical 是哪个 (零售 customer service / 金融 dispute / 物流 ops / SaaS 内部 support)? 这个 vertical 的 procurement 周期多长 (financial services 9-15 月, 零售 3-6 月, SMB 30-60 天)? 已有 incumbent 是谁 (Genesys / Salesforce Service Cloud / Zendesk — 你是替代还是 augment)? compliance 门槛 (HIPAA / SOC2 / FedRAMP / GDPR / PCI)? 第 1 名 vs 第 2 名在这个 vertical 的时差 (winner-take-most: 第 1 名拿 reference customer, 第 2 名 1-2 年内追不上)?
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 · 438 lines · 312 tokens per session scan A 2b55b8ba33c2
bret-taylor is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 3d ago), licensed MIT. It adds 312 tokens to every session and 11,943 once invoked, about $0.0016 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
pitchcraft
Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin…
all-deploy
Deploys any web app, API, or agent to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Detects Next, Vite, Astro, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP server, Claude Agent SDK script, Python worker, Dockerized, and static projects; routes to Vercel, Railway…
watch-anything
A skill for understanding videos and other rich media from X, YouTube, and Bilibili. It prefers existing subtitles and can fall back to speech transcription before producing a Chinese explanation.
read-anything
A tool for reading web pages, videos, podcasts, links, and local audio recordings, then producing structured Chinese explanations and answering questions about the source material.
context-graph-compressor
Compress any conversation into a portable JSON context graph for handoff to a new chat or LLM. Trigger on: "compress this chat", "save context", "new chat", "hand off", "transfer context", "too many tokens", "start fresh", "export conversation", "context graph", "continue in new session". Also trigger proactively when…
wiki
A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.