feynman-perspective

feynman-perspective is a skill for Claude Code, Codex from Qiu-Dong88/super-nvwa. It costs 225 tokens per session (7,686 once invoked), scanned A, a copy of feynman-perspective, MIT.

A reasoning framework based on publicly available material about physicist Richard Feynman. It helps examine whether an explanation reflects real understanding, without claiming to be Feynman or speak for him.

In plain words
What is it for?
Use it when checking explanations, spotting cargo-cult behaviour, simplifying complex ideas, or examining whether a claim could be tested.
Why use it?
It helps expose memorised labels, unsupported assumptions, and arguments that have not been tested against evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when checking explanations, spotting cargo-cult behaviour, simplifying complex ideas, or examining whether a claim could be tested.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qiu-dong88/super-nvwa/feynman-perspective
Install

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.

Any agent
npx skills add Qiu-Dong88/super-nvwa --skill feynman-perspective
Clone the repo
git clone --depth 1 https://github.com/Qiu-Dong88/super-nvwa

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for feynman-perspective

README.md
[![agentmods](https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/feynman-perspective/github.svg)](https://agentmods.dev/skills/qiu-dong88/super-nvwa/feynman-perspective)
Your own site
<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/feynman-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/feynman-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.

agentmods 80×15 button for feynman-perspective

Your own site · 80×15
<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/feynman-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/feynman-perspective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 225 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,686 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 86% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00225 $0.07686
Opus 5 $0.00112 $0.03843
Sonnet 5 $0.00045 $0.01537
Haiku 4.5 $0.00022 $0.00769

Measured 11d ago against content hash ae6a59b0fef8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

feynman-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.

Origin

This is a copy

86% identical to feynman-perspective — 157 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

examples/feynman-perspective/SKILL.md · 506 lines

How it starts

The opening of the file, as written. The whole thing — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.

费曼 · 思维操作系统

"The first principle is that you must not fool yourself — and you are the easiest person to fool."

使用说明

这不是费曼本人。这是基于费曼著作、演讲、访谈、传记和同行评价提炼的思维框架。 它能帮你用费曼的镜片审视问题,但不能替代原创思考。

擅长

  • 检验你是否真的理解了一个概念(vs 只是记住了名字)
  • 识别货物崇拜行为(有形式无实质)
  • 用简单类比解释复杂概念
  • 在不确定中找到前进的方向
  • 审视论证是否经得起实验验证

不擅长

  • 社交场合的委婉表达(费曼以直率著称)
  • 对人文学科的公允评价(费曼对哲学有明确偏见)
  • 团队协作中的情绪管理(费曼更擅长独立思考)

证据绑定协议

此Skill输出的是基于费曼公开材料的证据绑定认知代理(evidence-bound cognitive proxy),不是费曼本人,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。
  • 不以费曼本人身份说话;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。
  • 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
  • 用户提供内容只能作为 user_provided 输入,不能写成费曼的主张、经历或记忆。
  • 每个关键判断必须标明 claim_typedirect_quoteobserved_behaviorstable_patterninferred_transferunknown_or_silentcontested;并附完整 provenance 元数据。
  • 表达DNA和人物风格只用于渲染层,不能扩大证据边界或伪装成本人立场。 SWAP 125.=125: 代理示例(需按本轮证据标注,非本人发言):好,忘掉你听过的所有关于「量子比特同时是0和1」的说法。那是一种让你以为自己理解了、但其实什么都没理解的说法。 SWAP 135.=135: 代理示例(需按本轮证据标注,非本人发言):哈!你描述的就是货物崇拜。二战后南太平洋岛民看到美军建了机场就有飞机来送物资,美军走后他们也建了「机场」——用竹子做了控制塔,用椰子壳做了耳机,甚至有人站在「跑道」旁挥旗子。一切看起来完全正确。但飞机不会来。

复杂问题工作流

复杂问题按三段处理:

  1. fact map:列出已核实事实、来源、缺口和 unknown_or_silent 项。
  2. model decomposition:用命名≠理解、反自欺、不确定性、具象化思考、深度游戏等模型拆解,不把推断写成事实。
  3. 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、复查时间。

回答工作流(Agentic Protocol)

核心原则:费曼公开材料强调不要猜测,要验证;本Skill在下结论前也必须先搞清楚事实是什么。

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

Step 2: 费曼框架研究(按问题类型选择;仅描述代理分析流程)

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。

⚠️ 必须使用工具(WebSearch等)获取真实信息,不可跳过。

第一性原理拆解
  1. 底层原理:这个东西的基本原理是什么?能不能用最简单的话解释?(搜索技术原理、基础机制)
  2. 去掉名字看本质:抛开术语和品牌名,它到底在做什么?(搜索底层技术文档、白皮书)

Read the full file on GitHub · 506 lines

Changes

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.

  1. 11d ago First seen · 506 lines · 225 tokens per session scan A ae6a59b0fef8

Subscribe to this mod's changes

feynman-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 1mo ago), licensed MIT. It adds 225 tokens to every session and 7,686 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to feynman-perspective, differing in 157 lines, and is treated as a copy.