feynman

feynman is a skill for Claude Code, Codex from LilMGenius/paperthin. It costs 81 tokens per session (896 once invoked), scanned A, original, MIT.

A questioning method for checking whether you truly understand a decision. It asks you to explain the choice in simple words and exposes gaps in your reasoning.

In plain words
What is it for?
Use it immediately after choosing between options. It helps test decisions before they become difficult to change.
Why use it?
It prevents you from repeating a decision confidently without knowing why it was made. You get either a clear explanation or an honest list of what still needs checking.

Skill for Claude CodeCodex

Part of the paperthin plugin — 28 skills shipped together

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.

agentmods
npx agentmods add skills/lilmgenius/paperthin/feynman
Any agent
npx skills add LilMGenius/paperthin --skill feynman
Clone the repo
git clone --depth 1 https://github.com/LilMGenius/paperthin

Made for: Claude Code, Codex.

Or install paperthin, the plugin that ships this one along with the rest of its 28 skills.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/lilmgenius/paperthin/feynman.svg)](https://agentmods.dev/skills/lilmgenius/paperthin/feynman)
Your own site
<a href="https://agentmods.dev/skills/lilmgenius/paperthin/feynman"><img src="https://agentmods.dev/badge/skills/lilmgenius/paperthin/feynman.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00081 $0.00896
Opus 5 $0.00041 $0.00448
Sonnet 5 $0.00016 $0.00179
Haiku 4.5 $0.00008 $0.00090

Measured 5d ago against content hash 618a6ccc4bfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feynman 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 5d 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.

skills/depth/feynman/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Press a decision you just made until you can explain it, or the gap where you can't is named.

Goal

The moment after a choice is when understanding is cheapest to fake: you can restate an option fluently without having earned the reasons behind it, and by the time that gap matters the decision is load-bearing elsewhere. The Feynman test catches it — if you can't explain a thing plainly, you don't yet understand it. So no one hands you the rationale; a fresh critic that never made the decision presses for what you can't actually explain, and a shallow answer draws a narrower question instead of a pass. The result is a decision you can now explain under real pressure, or an honest flag that you can't yet.

Workflow

  1. Trigger: fire right after a decision is made — typically just after options were laid out with no argument for any, and one was picked.
  2. Restate, don't justify: state the decision neutrally. Do not supply the reasoning behind it, and do not let the user borrow reasoning that was never actually given.
  3. Isolate the critic: hand the decision — not any reasoning — to a fresh, context-free sub-session that never watched the decision get made. Have it press for gaps: what a skeptical outsider would ask, what is assumed but unstated, what would have to be true for the choice to hold.
  4. Return one gap at a time: give the user the sharpest unresolved gap and ask them to explain it in their own words. Never batch gaps into a checklist.
  5. Judge the explanation: if the answer actually resolves the gap, close it and move on. If it restates the question, deflects, or leans on authority ("the agent suggested it") instead of reasoning, do not accept it.
  6. Narrow, don't repeat: on a shallow answer, don't ask the same question again — narrow to the exact part that stayed vague and ask that. Keep narrowing each round; never widen back to a generic "are you sure?"
  7. Stop condition: after repeated rounds, either every gap is genuinely explained, or one isn't. Both are valid endings.
  8. On an unexplained gap: don't force a resolution or let the user paper over it. Name the unresolved point specifically and flag the decision for re-review — not a verdict that it was wrong, only that it isn't yet earned.

Read the full file on GitHub · 38 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. 5d ago First seen · 38 lines · 81 tokens per session scan A 618a6ccc4bfa

Subscribe to this mod's changes

feynman is a skill published in the GitHub repository LilMGenius/paperthin (1,054 stars, last pushed 16d ago), licensed MIT. It adds 81 tokens to every session and 896 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

mm-init-project

Инициализирует или обновляет проект для mm-системы — создаёт passport.md в корне, копию в Obsidian, dashboard.md, handoff.md (скелет), project-instructions.md для claude.ai. Use when user says "оформи проект", "сделай паспорт", "init project", "/mm-init", "/mm-init-project", "обнови паспорт", "регистрирую проект".…

mworldorg/markdown-memory · 200 tokens

content-editor

Writes and edits the portfolio's pages. Reads a brief, follows the style guide, and emits the HTML into public/.

crystian/skill-map · 28 tokens

notion-publish

Mirrors the portfolio's pages into Notion after publishing, creating one Notion page per site page via the Notion MCP. Use it from /publish, or when the user asks to sync the site to Notion.

crystian/skill-map · 52 tokens

publish

Publishes the portfolio: runs the link check, hands off to the content editor for any last fixes, then follows the deploy runbook.

crystian/skill-map · 31 tokens

check-links

Validates the portfolio's internal links before publishing. Walks every generated page and reports any link whose target is missing.

crystian/skill-map · 28 tokens

mm-setup

Онбординг/персонализация mm-системы под конкретного пользователя — спрашивает имя, чем занимается, стек, язык, путь к Obsidian vault, и записывает это в личный gitignored-оверлей config/mm-config.local.json + генерирует персональную копию claude.ai-скилла mm-web-bridge. Use when user says "/mm setup", "/mm onboard"…

mworldorg/markdown-memory · 152 tokens