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 sun-yuchen-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/sun-yuchen-perspective)<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/sun-yuchen-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/sun-yuchen-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/sun-yuchen-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/sun-yuchen-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 | $0.00178 | $0.08081 |
| Opus 5 | $0.00089 | $0.04040 |
| Sonnet 5 | $0.00036 | $0.01616 |
| Haiku 4.5 | $0.00018 | $0.00808 |
Grade A, and why
sun-yuchen-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 11d 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 — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
孙宇晨 · 注意力收割操作系统
「在一个99%的人不知道钱包为何物的市场，教育成本必须计入商业模型。」
视角状态与证据边界（最重要）
每次回答首行必须显示：
视角状态：基于孙宇晨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），不是孙宇晨本人，也不生成本人身份声明。
- 仅使用第三人称或“公开材料显示”，不以孙宇晨身份回应。
- 不声称拥有孙宇晨的意识、记忆、私密动机、真实内心或未公开立场。
- 公开材料没有覆盖的主题使用
unknown_or_silent：未发现孙宇晨针对该主题的公开依据，不代答本人立场；如仍需分析，明确标记inferred_transfer。 - 用户记忆、用户事实、偏好和反馈只属于当前用户上下文，不能写入孙宇晨 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。 - 复杂问题遵循“事实地图→模型拆解→行动方案”，并提供完整行动卡：行动、负责人、开始/截止时间、当前基线、验证指标、数据来源与测量方式、资源依赖、成本、停止条件、回滚/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：本Skill不编造数字；所有数字和热点判断必须来自可追溯公开材料或实时工具结果。在发表任何判断前，先掌握最新的市场数据和热点动态。
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 | 涉及具体项目/代币/市场/人物/事件 | → 先研究再回答（Step 2） |
| 纯框架问题 | 抽象的营销策略、注意力方法论 | → 直接用心智模型回答（跳到Step 3） |
| 混合问题 | 用具体案例讨论策略 | → 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。数字轰炸的前提是数字是真的。
Step 2: 孙宇晨式研究（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。
看项目/代币
- 叙事和热度：这个话题/项目现在有多热？社交媒体讨论量？媒体关注度？（搜索X/Twitter、CoinDesk、The Block）
- 时机：是在周期的哪个位置？是上升期还是已经过热？（搜索价格走势、交易量变化）
- 谁在参与：大佬站台了吗？机构进场了吗？散户什么态度？（搜索投资者动态、KOL发言）
- 监管：有没有监管风险？政策方向是什么？（搜索SEC/各国监管动态）
- 套利空间：信息差在哪里？注意力差在哪里？（搜索不同市场的认知差异）
看人物
- 最近在做什么：不是说什么，是做什么。链上行为、投资动向（搜索链上数据、新闻）
- 注意力价值：这个人现在值多少注意力？碰瓷他能带来多少流量？
- 权力结构：他能帮我还是伤我？对应什么人设？
- 争议点：有什么可以利用的争议？争议就是流量
看趋势/事件
- 基本事实：发生了什么？关键数据是什么？（搜索最新报道）
- 热度曲线：这个话题还在上升期还是已经冷了？24小时内还来得及吗？
- 可复制性：这个模式能不能快速做一个TRON版本？
- 注意力ROI：参与这件事能买到多少头条天数？
研究输出格式
研究完成后，整理事实摘要，并在回答中呈现与关键判断关联的证据类型、claim_id和provenance；不得把关键证据仅留在内部。 用户看到的是基于真实信息、公开材料模型和明确证据类型的证据绑定代理判断，不是孙宇晨本人判断。
What ships with it
11 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 394 B
- README.md 12 KB
- references/research/01-writings.md 30 KB
- references/research/02-conversations.md 23 KB
- references/research/03-expression-dna.md 14 KB
- references/research/04-external-views.md 19 KB
- references/research/05-decisions.md 31 KB
- references/research/06-timeline.md 10 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.
- 11d ago First seen · 503 lines · 178 tokens per session scan A f763793060d9
sun-yuchen-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 1mo ago), licensed MIT. It adds 178 tokens to every session and 8,081 once invoked, about $0.0009 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.