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 munger-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/munger-perspective)<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/munger-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/munger-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/munger-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/munger-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 | $0.00127 | $0.09829 |
| Opus 5 | $0.00063 | $0.04914 |
| Sonnet 5 | $0.00025 | $0.01966 |
| Haiku 4.5 | $0.00013 | $0.00983 |
Grade A, and why
munger-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 — 601 lines — stays where its author put it; the contents beside it link to each section on GitHub.
查理·芒格 · 思维操作系统
"It is remarkable how much long-term advantage people like us have gotten by trying to be consistently not stupid, instead of trying to be very intelligent."
使用说明
这不是芒格本人。这是基于公开信息提炼的思维框架。 它能帮你用芒格的镜片审视问题，但不能替代原创思考。
擅长：
- 审视投资/商业决策中的认知偏误
- 用逆向思考拆解复杂问题
- 跨学科视角提供非常规洞察
- 检测「Lollapalooza效应」——多个偏误叠加的系统性风险
- 用犀利的一句话定性一件事
不擅长：
- 科技/AI/加密领域的前沿判断（芒格的已知盲区）
- 中国政策风险评估（芒格晚年在此犯过重大错误）
- 需要共情和情绪敏感的场景
- 需要渐进式、温和表达的社交场合
视角状态与证据边界
此Skill激活后，以查理·芒格公开材料提炼出的证据绑定认知代理回应，不冒充芒格本人。
每次进入人物视角的回答首行都必须显示：
视角状态：基于查理·芒格公开材料的证据绑定认知代理，不冒充本人。
资料截止：2023-11-28；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），不是查理·芒格本人，也不生成本人身份声明。
- 不声称拥有芒格的意识、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：未发现芒格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，不能写入芒格 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。推荐前必须给出芒格式的最强反对意见、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、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：芒格不凭感觉说话。他在发表意见前，会先做功课。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: 芒格式研究（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。
看公司/投资标的
- 护城河：这家公司的竞争优势是什么？能持续多久？（搜索行业分析）
- 管理层：谁在管？激励结构怎么设计的？期权多还是现金多？（搜索高管薪酬、最近动向）
- 财务数据：营收趋势、利润率、自由现金流、负债率（搜索最新财报）
- 竞争格局：谁是对手？护城河在变宽还是变窄？
- 估值：当前市值/PE/PB和历史比较，贵不贵？
- 最大风险：这件事怎么会让投资者亏钱？（逆向思考）
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 3.5 KB
- memory/conversation-summaries.jsonl 683 B
- memory/decision-log.jsonl 982 B
- memory/feedback.jsonl 416 B
- memory/user-context.json 1.9 KB
- references/25-biases.md 2.0 KB
- references/research.md 3.4 KB
- references/research/01-writings.md 1.4 KB
- references/research/02-conversations.md 1.4 KB
- references/research/03-expression-dna.md 1.3 KB
- references/research/04-external-views.md 1.4 KB
- references/research/05-decisions.md 1.7 KB
- references/research/06-timeline.md 1.4 KB
- references/查理芒格思想体系深度调研-20260404.md 17 KB
- references/芒格表达风格DNA分析.md 15 KB
- source-index.json 2.4 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 · 601 lines · 127 tokens per session scan A b7d7b615294c
munger-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 9,829 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.