teach

teach is a skill for Claude Code, Codex from Kshitijpalsinghtomar/depth-skills. It costs 18 tokens per session (1,166 once invoked), scanned A, original, MIT.

An explanation method based on the Feynman technique: explain a topic in simple language to reveal gaps in understanding. It checks for undefined jargon, skipped steps, and hand-waved complexity.

In plain words
What is it for?
Use it to rewrite technical answers for newcomers and identify concepts or steps that still need explanation.
Why use it?
It helps catch explanations that sound correct but leave beginners unable to follow or use them.

Skill for Claude CodeCodex

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

Good fit Use it to rewrite technical answers for newcomers and identify concepts or steps that still need explanation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kshitijpalsinghtomar/depth-skills/ds-teach
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 Kshitijpalsinghtomar/depth-skills --skill ds-teach
Clone the repo
git clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-skills

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 teach

README.md
[![agentmods](https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-teach/github.svg)](https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-teach)
Your own site
<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-teach"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-teach/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 teach

Your own site · 80×15
<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/ds-teach"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/ds-teach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,166 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 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 5.1 $0.00018 $0.01166
Opus 5 $0.00009 $0.00583
Sonnet 5 $0.00004 $0.00233
Haiku 4.5 $0.00002 $0.00117

Measured 11d ago against content hash 64862757c726, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

teach 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.

skills/ds-teach/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TEACH — Feynman Gap Detection

Richard Feynman: "If you can't explain it simply, you don't understand it well enough."

The act of teaching exposes gaps that the act of doing hides. When you know something well enough to answer, you may not know it well enough to explain. The difference is your blind spots.

This skill forces explanation through a beginner's lens to surface hidden knowledge gaps.


The Failure Mode You Must Recognize

You are about to deliver an answer that:

  • Uses jargon without defining it
  • Skips "obvious" steps that aren't obvious to beginners
  • Hand-waves past complexity with "this is just..."
  • Would require the user to fill in significant gaps to act on it

These are symptoms of unrevealed knowledge gaps. The answer is complete enough to sound right but incomplete enough to fail when used.


The Protocol

1 — WRITE SIMPLE EXPLANATION

Take your answer and rewrite it as if explaining to a curious beginner:

SIMPLE EXPLANATION
────────────────────────────────────────
Audience: Someone who knows basic concepts but not this domain
Constraint: No jargon without definition. No skipping steps.
            Each sentence should be verifiable by the reader.

[Write 3-5 paragraphs explaining the answer from fundamentals]
────────────────────────────────────────

The test: Could a smart person with no domain knowledge read this and either:

  • Understand enough to act, OR
  • Identify exactly where they disagree/need more?

If neither — gap detected.

Artifact: The simple explanation. Step 2 stress-tests it.

2 — GENERATE STUDENT QUESTIONS

Imagine a beginner reading your explanation. Write 5 questions they would ask:

STUDENT QUESTIONS
────────────────────────────────────────
Q1: [Basic clarification - what does X mean?]
Q2: [Step gap - what happens between A and B?]
Q3: [Edge case - what about scenario X?]
Q4: [Why - why this approach and not another?]
Q5: [Action - how do I actually do this in practice?]
────────────────────────────────────────

Read the full file on GitHub · 152 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 · 152 lines · 0 tokens per session scan A 64862757c726

Subscribe to this mod's changes

teach is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 1,166 once invoked, about $0.0001 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.