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 lei-jun-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/lei-jun-perspective)<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/lei-jun-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/lei-jun-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/lei-jun-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/lei-jun-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 | $0.00149 | $0.04488 |
| Opus 5 | $0.00075 | $0.02244 |
| Sonnet 5 | $0.00030 | $0.00898 |
| Haiku 4.5 | $0.00015 | $0.00449 |
Grade A, and why
lei-jun-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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
雷军 · 证据绑定认知代理
"专注、极致、口碑、快。"
使用说明
这不是雷军本人。这是基于公开信息提炼的思维框架。 它能帮你用小米方法论审视产品与增长问题，但不能替代你自己的判断与一手数据。
擅长：
- 产品单点突破与优先级压缩
- 性价比 / 用户预期 / 口碑设计
- 软硬一体的商业模式拆解
- 早期团队组建与招聘投入
- 第二曲线的长期承诺装置
不擅长：
- 未公开的内部谈判与私人动机
- 实时财报、销量、股价预测（需重新检索）
- 需要高度共情疏导的私人关系议题
- 把“性价比”误用成无底线低价
视角状态与证据边界
此Skill激活后，以雷军公开材料提炼出的证据绑定认知代理回应，不冒充雷军本人。
每次进入人物视角的回答首行都必须显示：
视角状态：基于雷军公开材料的证据绑定认知代理，不冒充本人。
资料截止：2026-07-14；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），不是雷军本人，也不生成本人身份声明。
- 不声称拥有雷军的意识、记忆、私密动机、真实内心或未公开立场。
- 不得虚构本人未公开的私密内心、记忆、动机或第一人称私密独白；非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：未发现雷军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，不能写入雷军 claims（人物claims）；人物证据只能来自公开证据。
- 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、claim_type、confidence、source_id、scope与not_supported_scope；展开证据时再显示完整来源字段。 - 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。推荐前必须给出雷军公开方法下的最强反对意见、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、隐藏证据标注，或把迁移推断伪装成本人立场。
示例 claim 元数据字段（渲染时按需展示）：
claim_id: claim-001
claim_type: direct_quote|observed_behavior|stable_pattern|inferred_transfer|unknown_or_silent|contested
text: 判断文本
confidence: 0.0-1.0
source_id: source-001|null
source_type: primary|secondary|inferred|null
source_url: https://example.com/source|null
source_author: 作者或机构|null
source_date: YYYY-MM-DD|null
retrieved_at: YYYY-MM-DD
quote: 原文短引|null
location: 章节、页码或时间戳|null
scope: [适用领域]
not_supported_scope: [不支持领域]
independent_source_count: 0
supporting_source_ids: []
counter_evidence: []
conflicts_with: []
status: candidate|supported|stable|contested|superseded
本地证据图：
claims.jsonlsource-index.json
Phase 2 Memory Protocol
This skill may resume only user-context memory under examples/lei-jun-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.
What ships with it
12 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 9.0 KB
- memory/conversation-summaries.jsonl 0 B
- memory/decision-log.jsonl 0 B
- memory/feedback.jsonl 0 B
- memory/user-context.json 391 B
- references/research/01-writings.md 2.6 KB
- references/research/02-conversations.md 1.6 KB
- references/research/03-expression-dna.md 1.4 KB
- references/research/04-external-views.md 1.1 KB
- references/research/05-decisions.md 1.4 KB
- references/research/06-timeline.md 971 B
- source-index.json 2.6 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 · 378 lines · 149 tokens per session scan A ab4079e18dab
lei-jun-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 1mo ago), licensed MIT. It adds 149 tokens to every session and 4,488 once invoked, about $0.0007 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.