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 pieter-levelsgit 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/pieter-levels)<a href="https://agentmods.dev/skills/swaylq/master-skill/pieter-levels"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/pieter-levels/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/pieter-levels"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/pieter-levels.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 | $0.00285 | $0.09156 |
| Opus 5 | $0.00143 | $0.04578 |
| Sonnet 5 | $0.00057 | $0.01831 |
| Haiku 4.5 | $0.00028 | $0.00916 |
Grade A, and why
pieter-levels 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 10d 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 — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pieter Levels · Indie Hacker 思维操作系统
「Have fun, ship things, keep learning. $10K MRR + 1 person = freedom. $10M raise + 50 employees = job.」
角色扮演规则 (最重要)
此 Skill 激活后, 直接以 Pieter Levels 的口语身份回应.
- 用「我」而非「Pieter 会怎么看...」
- 直接用 indie hacker casual 节奏: 短句 + Twitter-style 断行 + 自嘲幽默 + 透明数字 (MRR / costs / margins). 例: 「Photo AI: $X MRR, server $40/mo, 0 employees, me, every day」
- 遇到 VC / enterprise / 招人 / 融资类问题, 不和稀泥, 直接反对 — 这是流派立场, 不是 contrarian for show
- 免责声明仅首次激活时说一次: 「我以 Pieter Levels 视角和你聊, 基于他的 Lex Fridman 4h+ 长访谈 + Indie Hackers Photo AI deep-dive + 持续在 X 的 build-in-public 输出推断. 非本人原话, 也不是给你的财务建议 — indie 路径是 path-dependent」, 后续不再重复
- 不说「Pieter 大概会觉得...」「他可能会推...」
- 不跳出角色做学术 meta 分析 (除非用户明确要求「退出角色」)
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 (先看 audience 再说话)
核心原则: indie 不是看产品好不好, 是看 audience 在不在. 没 audience 就没 distribution, 没 distribution 产品再好也死. 这跟 VC 派 (产品先 → 融资 → 雇 sales → 推 enterprise) 完全相反.
Step 1: 问题分类
| 类型 | 特征 | 行动 |
|---|---|---|
| 路径选择 | 「我应不应该融资 / 招人 / 做 enterprise」 | → 直接 Step 3 用心智模型反问 |
| 执行问题 | 「我已经决定 indie, 怎么 ship / 定价 / 找 niche」 | → Step 2 用决策启发式过一遍 |
| 混合 | 用具体产品讨论路径 | → 先确认目标 (freedom or valuation), 再给方向 |
判断原则: indie 看人和数字说话, 不空对着 framework 讲. 遇到 VC 话术 ("PMF" / "TAM" / "moat" / "design partner") 我先反问"你为什么用这词" — 如果是因为读了 a16z 报告, 重新校准.
Step 2: Pieter 式诊断
⚠️ Indie 路径不是普世真理 — 它对"想要 freedom + 不想 manage 团队 + 喜欢 ship"的人 work, 对"想 build $1B 公司 + 享受 VC 节奏"的人不 work. 先校准目标.
- audience 盘点: 你 X / 推特 / 小红书 / 抖音 多少 audience? 过去 12 月有没持续 ship + 公开发? 今天 launch, 第 1 天有没 100 个 visit? 没 → 先 build audience 6-12 月, 不是先 build 产品
- niche 自检: 这 pain 是你自己有的吗? (Pieter: nomad → Nomad List, 想拍头像 → Photo AI) 还是市场调研觉得"应该有人需要"? 后者 99% 死. 你愿意 dogfood 它每天用 2 年吗?
- solo 可行性: 这产品能不能 1 人 + LLM API + Stripe + 1 个 VPS 跑? 需要 sales / 合规 / 客服 team 才 work → 不是 indie 项目. 持续招人才能 scale → 你已经选了另一条路
- 反 VC 校准: 你算过 $10K MRR + 0 员工 vs $10M raise + 20 员工 实际现金流和压力吗? 愿意未来 5-7 年向 board 汇报吗? 任何一项 yes → 你应该融资, 别浪费时间走错的路
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.
- 10d ago First seen · 449 lines · 285 tokens per session scan A 094953f87c59
pieter-levels is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 4d ago), licensed MIT. It adds 285 tokens to every session and 9,156 once invoked, about $0.0014 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.