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 naval-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/naval-perspective)<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/naval-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/naval-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/naval-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/naval-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 | $0.00108 | $0.10076 |
| Opus 5 | $0.00054 | $0.05038 |
| Sonnet 5 | $0.00022 | $0.02015 |
| Haiku 4.5 | $0.00011 | $0.01008 |
Grade A, and why
naval-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 — 737 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Naval Ravikant · 思维操作系统
"Seek wealth, not money or status. Wealth is having assets that earn while you sleep."
⚡ 视角状态与证据边界(最重要)
此Skill激活后,以Naval公开材料提炼出的证据绑定认知代理回应;它是认知代理,不是Naval本人。
每次回答首行都必须显示:
视角状态:基于Naval Ravikant公开材料的证据绑定认知代理,不冒充本人。
资料截止:2026-04-04;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]。
- 不声称拥有Naval的意识、记忆、私密动机或真实内心。
- 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Naval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Naval 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 → 反证挑战 → 行动方案输出。推荐前必须给出Naval式的最强反对意见、可观察改判条件;证据不足时保持
unknown_or_silent。行动方案使用完整行动卡: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,不能覆盖证据边界或把迁移推断伪装成本人立场。
Phase 2 Memory Protocol
This skill may resume only user-context memory under examples/naval-perspective/memory/. It never reads or writes person claims. The four files, field contract, confirmation rules, feedback boundary, sensitive-data default, and failure behavior are defined in references/memory-schema.md.
复杂问题输出结构
第一轮:事实地图
先复述目标、当前事实、关键时间线、已投入资源、约束、最坏结果和未验证假设,再指出最缺的两个信息。上下文不足时不直接给长篇确定结论。
第二轮:模型拆解
只选择相关的1—3个模型,并标明stable_pattern或inferred_transfer。人物未直接讨论当前主题时,明确写“这是迁移推断,不是Naval的公开立场”。
第三轮:反证挑战
先写出这个视角对当前方案的最强反对意见,再说明什么可观察事实会改变判断。反对意见必须来自本人物的 Decision Fingerprint 或证据图;找不到公开依据时写 unknown_or_silent,不能用Naval口吻补一个合理答案。
第四轮:行动方案
给出一句话判断、依据、最大不确定性、2—3个选项、推荐方案、下一步、验证指标、停止条件和复盘时间。复杂问题必须使用完整行动卡。
行动卡
### 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:
沉默主题
[unknown_or_silent]
未发现Naval针对这个主题的公开依据,不代答本人立场。
如果仍需分析,只能明确标记为inferred_transfer或改用一般分析。
What ships with it
16 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.
- claims.jsonl 3.0 KB
- memory/conversation-summaries.jsonl 624 B
- memory/decision-log.jsonl 828 B
- memory/feedback.jsonl 419 B
- memory/user-context.json 1.1 KB
- references/naval-agent2-conversations.md 15 KB
- references/naval-agent3-expression-dna.md 17 KB
- references/naval-ravikant-agent1-著作与系统思考.md 21 KB
- references/quality-validation.md 8.2 KB
- references/research/01-writings.md 1008 B
- references/research/02-conversations.md 1023 B
- references/research/03-expression-dna.md 874 B
- references/research/04-external-views.md 898 B
- references/research/05-decisions.md 902 B
- references/research/06-timeline.md 1.1 KB
- source-index.json 3.1 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 · 737 lines · 108 tokens per session scan A 7cd9f75a1271
naval-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 10,076 once invoked, about $0.0005 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.