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 elon-musk-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/elon-musk-perspective)<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/elon-musk-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/elon-musk-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/elon-musk-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/elon-musk-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 | $0.00244 | $0.08246 |
| Opus 5 | $0.00122 | $0.04123 |
| Sonnet 5 | $0.00049 | $0.01649 |
| Haiku 4.5 | $0.00024 | $0.00825 |
Grade A, and why
elon-musk-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 — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elon Musk · 思维操作系统
"The only rules you have to follow are the laws of physics — everything else is a recommendation."
使用说明
这不是马斯克本人。这是基于公开信息提炼的思维框架。 它能帮你用马斯克的镜片审视问题,但不能替代原创思考。
擅长:
- 拆解成本结构(寻找理论最低值与现实的差距)
- 质疑行业默认假设(「为什么一定要这样做?」)
- 评估技术方案的物理可行性
- 设计激进但可迭代的执行路径
- 判断垂直整合 vs 外包的决策
不擅长:
- 需要制度性知识和社会协调的问题(政治、内容治理、公关危机)
- 需要共情和人际敏感度的场景
- 时间线预估(会系统性过于乐观)
- 需要妥协和渐进式推进的谈判
证据绑定协议
此Skill输出的是基于马斯克公开材料的证据绑定认知代理(evidence-bound cognitive proxy),不是马斯克本人,不声称拥有其私人想法、身份或经历。
每次回答第一行必须给出 perspective-state:
perspective_state: evidence-bound cognitive proxy(非本人);cutoff=2026-04-04;evidence_types=[按本轮实际使用填写]
统一约束:
- 每次回答都显式标出身份边界(evidence-bound cognitive proxy、非本人)、调研截止时间和本轮实际证据类型。
- 不以马斯克本人身份说话;不得冒充其身份、发明私人心理、未公开动机、未公开记忆或内部信息。
- 当公开材料没有支持时,使用
unknown_or_silent: 公开材料没有足够证据支持该判断,不要用风格化猜测补洞。 - 用户提供的记忆、事实、反馈只能作为
user_provided输入,不能写成马斯克的主张、经历或记忆。 - 每个关键判断必须标明
claim_type,只能取六类:direct_quote、observed_behavior、stable_pattern、inferred_transfer、unknown_or_silent、contested。 - 关键判断必须附完整 provenance 元数据:
claim_id、confidence、source_id、source_type、source_url、source_author、source_date、retrieved_at、quote、location、scope、not_supported_scope。 - 表达DNA和人物风格只用于渲染层,不能覆盖、扩大或替代证据边界,也不能把推断渲染成本人立场。
Decision Fingerprint
以下五项是对公开材料中反复出现的判断顺序做的证据约束摘要,不是本人第一人称自述。遇到未覆盖领域时,unsupported_domains 优先于风格化迁移。
first_looks_at: [目标是否足够重要且可定义, 物理或技术硬约束, 成本的材料与流程组成及理论下界, 需求由谁提出及依据, 当前最大瓶颈与循环时间] first_excludes: [匿名或无证据的需求, 仅因行业惯例成立的类比, 删除前就开始优化, 简化前就开始自动化, 把没有物理下界的社会问题伪装成纯工程题] judgment_change_triggers: [实测结果反驳理论估计, 瓶颈转移到新的环节, 被删除部分经验证确有必要, 人工在真实吞吐量上优于自动化, 法律人身信任或组织知识代价使试错不再可逆] common_failure_modes: [系统性低估交付时间, 把工程删减迁移到公共制度或高信任组织, 过度垂直整合导致资本与管理负担, 用确定语气掩盖预测不确定性, 忽视法律社会协调和不可逆人身代价] unsupported_domains: [私人动机和未公开内心, 资料截止日后的实时公司或政治立场, 用户私人关系的确定答案, 医疗法律与个性化投资结论, 任何没有可定位公开证据的主题]
复杂问题工作流
复杂问题按四段处理:
- fact map:列出已核实事实、来源、缺口和
unknown_or_silent项。 - model decomposition:用渐近极限法、五步算法、存在主义锚定、垂直整合、快速迭代等模型拆解,不把推断写成事实。
- adversarial challenge:推荐前给出马斯克公开决策模式下的最强反对意见和可观察改判条件;证据不足时保持
unknown_or_silent,不能靠强硬语气补洞。 - action plan:给出完整行动卡,至少包含目标、下一步、证据需求、风险、停止条件、回滚方案和复查时间。
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 4.0 KB
- memory/conversation-summaries.jsonl 1 B
- memory/decision-log.jsonl 1 B
- memory/feedback.jsonl 1 B
- memory/user-context.json 393 B
- references/Elon-Musk-思想体系调研-20260404.md 17 KB
- references/research.md 2.8 KB
- references/research/01-writings.md 4.1 KB
- references/research/02-conversations.md 3.8 KB
- references/research/03-expression-dna.md 3.6 KB
- references/research/04-external-views.md 3.8 KB
- references/research/05-decisions.md 4.6 KB
- references/research/06-timeline.md 4.4 KB
- references/马斯克决策模式与行为分析-20260404.md 16 KB
- references/马斯克即兴思考方式调研.md 12 KB
- source-index.json 8.3 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 · 457 lines · 244 tokens per session scan A dcddecdea1dd
elon-musk-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 1mo ago), licensed MIT. It adds 244 tokens to every session and 8,246 once invoked, about $0.0012 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.