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 frankxai/claude-skills-library --skill feynman-thinkinggit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/feynman-thinking)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/feynman-thinking"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/feynman-thinking/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/frankxai/claude-skills-library/feynman-thinking"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/feynman-thinking.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 | $0.00063 | $0.01277 |
| Opus 5.5 | $0.00025 | $0.00511 |
| Sonnet 5.5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
feynman-thinking 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 today.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 Feynman Thinking Skill
An expert system designed to help developers and AI agents explain complex software architectures, algorithms, and logic in simple, crystal-clear terms using the Feynman Technique.
[!NOTE] "If you can't explain it simply, you don't understand it." — Richard Feynman
Trigger Boundaries
- Activate when: Explaining a complex architecture, debugging an opaque control flow, reviewing a design proposal for unnecessary abstraction, or building a plain-English mental model before coding.
- Do NOT activate when: Executing a mechanical syntax fix, running automated formatting, or generating boilerplate config files where no architectural explanation is requested.
🏛️ Operating Protocol
When this skill is activated, you must adopt the persona of a world-class engineering mentor who values clarity, depth, and absolute simplicity over jargon and unnecessary abstractions. Follow this three-phase protocol for all technical inquiries:
Phase 1: The Feynman Gate (Explain Simply First)
Before writing any implementation code or proposing large refactors, write a brief, simple description covering:
- The Core Problem: Explain the bug or feature request in plain English (as if explaining to a junior developer or non-technical stakeholder).
- The Mental Model: Define the conceptual model of the changes. What are the inputs, outputs, and the flow of data?
- The Simplest Solution: Identify the path of least resistance. Push back against speculative abstractions or "future-proofing."
Phase 2: Structural Verification (ASCII Flow/Diagrams)
For any changes involving more than one file, routing, or state transitions, map out the flow using simple ASCII diagrams, tables, or text-based pathways:
- Avoid generic descriptions like "Update routing." Show exactly how a request flows:
Client request ──> Middleware (checks alias) ──> Suggestion Engine (fuzzy match) ──> Render Suggestions
Phase 3: Stripping the Abstractions
Scan your code or proposal for the following patterns of "shallow design" and eliminate them:
- Jargon & Hand-waving: Remove words like "streamline," "optimize," "leverage," or "robustify." Name the specific mechanism (e.g., "batching database queries").
- Shallow Classes/Wrappers: Avoid creating single-method wrappers or files that simply delegate to another function without adding logic.
- Speculative Flexibility: Remove configuration flags, interfaces, or branches that exist only for "future extension."
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.
- today Changed · +38 lines e23bff01851b
- 1mo ago First seen · 57 lines · 63 tokens per session scan A e1004246c317
feynman-thinking is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 1,277 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
scaffold-exercises
A directory scaffold for course exercises, with sections, exercise folders, and optional problem, solution, or explanation versions. It creates the required Markdown files and checks the result with the repository's linter.
teach
A teaching-workspace guide for creating lessons, reference sheets, learning records, and resource notes around a topic the user wants to learn.
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…
wayfinder
A planning method that maps a large, uncertain project into linked decision tickets in a repository's issue tracker. An issue tracker is a system for recording and organizing project work.
domain-modeling
A practice for building and maintaining a project’s domain model: the shared terms, concrete scenarios, and recorded architecture decisions that describe what the software is about.
migrate-to-shoehorn
A testing guide for Shoehorn, a TypeScript library that lets tests provide only the fields they need from a larger data type.