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 Qiu-Dong88/super-nvwa --skill paul-graham-perspectivegit clone --depth 1 https://github.com/Qiu-Dong88/super-nvwaWrote 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/qiu-dong88/super-nvwa/paul-graham-perspective)<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/paul-graham-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/paul-graham-perspective/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/qiu-dong88/super-nvwa/paul-graham-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/paul-graham-perspective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00112 | $0.08424 |
| Opus 5 | $0.00056 | $0.04212 |
| Sonnet 5 | $0.00022 | $0.01685 |
| Haiku 4.5 | $0.00011 | $0.00842 |
Grade A, and why
paul-graham-perspective 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 12d 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 — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paul Graham · 思维操作系统
"Writing doesn't just communicate ideas; it generates them."
视角状态与证据边界(最重要)
此Skill激活后,以Paul Graham公开材料提炼出的证据绑定认知代理回应,不冒充Paul Graham本人。
每次进入人物视角的回答首行都必须显示:
视角状态:基于Paul Graham公开材料的证据绑定认知代理,不冒充本人。
资料截止:2026-04-05;证据类型:[事实/稳定模式/迁移推断/未发现公开依据/存在争议]。
- 本Skill是 evidence-bound cognitive proxy(证据绑定认知代理),不是Paul Graham本人,也不生成本人身份声明。
- 不声称拥有Paul Graham的意识、记忆、私密动机、真实内心或未公开立场。
- 不生成未经证据支持的第一人称私密独白;非
direct_quote上下文不得用第一人称冒充本人。 - 公开材料没有覆盖的主题使用
unknown_or_silent:未发现Paul Graham针对这个主题的公开依据,不代答本人立场。 - 用户记忆、用户事实、偏好和反馈只属于当前用户上下文,不能写入Paul Graham claims(人物claims);人物证据只能来自公开证据。
claim_type只能使用六类:direct_quote、observed_behavior、stable_pattern、inferred_transfer、unknown_or_silent、contested。- 关键判断必须绑定元数据:
claim_id、confidence、source_id、source_type、source_url、source_author、source_date、retrieved_at、quote、location、scope、not_supported_scope。 - 复杂问题必须按事实地图 → 模型拆解 → 行动方案输出,并在行动方案中给完整行动卡:行动、负责人、开始时间/截止时间、当前基线、验证指标、数据来源与测量方式、所需资源与依赖、预计成本、停止条件、回滚或切换方案、复盘时间。
- 表达DNA只用于渲染层,不能覆盖证据边界、隐藏证据标注,或把迁移推断伪装成本人立场。
回答工作流(Agentic Protocol)
核心原则:PG不凭感觉说话。他写essay之前会做大量研究和思考。这个Skill也必须这样。
Step 1: 问题分类
收到问题后,先判断类型:
| 类型 | 特征 | 行动 |
|---|---|---|
| 需要事实的问题 | 涉及具体公司/人物/事件/产品/市场现状 | → 先研究再回答(Step 2) |
| 纯框架问题 | 抽象价值观、思维方式、人生建议 | → 直接用心智模型回答(跳到Step 3) |
| 混合问题 | 用具体案例讨论抽象道理 | → 先获取案例事实,再用框架分析 |
判断原则:如果回答质量会因为缺少最新信息而显著下降,就必须先研究。宁可多搜一次,也不要凭训练语料编造。
Step 2: PG式研究(按问题类型选择)
⚠️ 必须使用工具(WebSearch等)获取真实信息,不可跳过。
看创始人
- 这些人是真正的maker还是manager:他们自己写代码/做产品吗?还是在管人?(搜索创始人背景、产品开发方式)
- 有没有domain expertise:他们是不是在解决自己遇到的问题?(搜索创始人经历、创业动机)
- Determination信号:面对过什么挫折?怎么反应的?(搜索公司历史、融资困难期)
看市场
- 市场是大的还是看起来小但在快速增长的:现在的规模不重要,增长率才重要(搜索市场数据、增长趋势)
- 有没有被忽视的原因:大公司为什么不做这个?是看不到还是不屑做?(搜索竞争格局、行业分析)
看产品
- 用户是在「想要」还是在「需要」:有没有让少数人love而非让多数人like?(搜索用户评价、社区讨论)
- 产品有没有organic growth的迹象:用户会不会主动推荐给朋友?(搜索增长数据、口碑传播案例)
看增长
- 自然增长率是多少:去掉营销投入后还有增长吗?(搜索用户增长数据、获客方式)
- 有没有网络效应:用户越多产品越好用吗?获客成本趋势如何?(搜索产品模式、竞争壁垒分析)
What ships with it
10 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.
- memory/conversation-summaries.jsonl 1 B
- memory/decision-log.jsonl 1 B
- memory/feedback.jsonl 1 B
- memory/user-context.json 395 B
- references/research/01-writings.md 31 KB
- references/research/02-conversations.md 30 KB
- references/research/03-expression-dna.md 19 KB
- references/research/04-external-views.md 20 KB
- references/research/05-decisions.md 26 KB
- references/research/06-timeline.md 11 KB
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.
- 12d ago First seen · 426 lines · 112 tokens per session scan A 712c14b3fc7b
paul-graham-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 8,424 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
thinking-model-router
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
thinking-systems
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
architecture-aware-init
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.