deep-teach

deep-teach is a skill for Claude Code, Codex from congmnguyen/claude-code-wsl2-setup. It costs 110 tokens per session (913 once invoked), scanned A, original, MIT.

An interactive teaching guide for building a lasting understanding of a topic, codebase, research paper, file, or technical idea. It explains one layer at a time and checks understanding through questions and small exercises.

In plain words
What is it for?
Learning how a codebase or concept works, practising recall, predicting behaviour, debugging examples, and comparing possible solutions.
Why use it?
It avoids mistaking a quick explanation or a user's claim of understanding for actual understanding.

Skill for Claude CodeCodex

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

Good fit Learning how a codebase or concept works, practising recall, predicting behaviour, debugging examples, and comparing possible solutions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/congmnguyen/claude-code-wsl2-setup/deep-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 congmnguyen/claude-code-wsl2-setup --skill deep-teach
Clone the repo
git clone --depth 1 https://github.com/congmnguyen/claude-code-wsl2-setup

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 deep-teach

README.md
[![agentmods](https://agentmods.dev/badge/skills/congmnguyen/claude-code-wsl2-setup/deep-teach.svg)](https://agentmods.dev/skills/congmnguyen/claude-code-wsl2-setup/deep-teach)
Your own site
<a href="https://agentmods.dev/skills/congmnguyen/claude-code-wsl2-setup/deep-teach"><img src="https://agentmods.dev/badge/skills/congmnguyen/claude-code-wsl2-setup/deep-teach.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 913 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00110 $0.00913
Opus 5 $0.00055 $0.00456
Sonnet 5 $0.00022 $0.00183
Haiku 4.5 $0.00011 $0.00091

Measured 8d ago against content hash 45dd5f427654, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

deep-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 8d 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/deep-teach/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Teach

Use this skill to run an interactive teaching session. The goal is not to deliver a polished lecture; the goal is to help the user build durable understanding and prove it through recall.

Teaching Contract

Teach one layer at a time:

  • Start with the problem, motivation, and big picture before low-level mechanics.
  • Keep each explanation short enough that the user can respond to it.
  • Ask the user to restate or apply the idea before moving on.
  • Do not treat "I understand" as verification. Verify by asking them to explain, predict, debug, compare, or solve a small example.
  • If the user is learning a codebase or artifact, inspect the real files first and anchor explanations to concrete paths, lines, data, or outputs.

Session Workflow

  1. Assess first. Ask the user what they already understand, what feels unclear, and what level they want: ELI5, ELI14, intern, practitioner, or expert.

  2. Build a running checklist. Maintain a visible markdown checklist with three groups:

    • Problem: what exists, why it matters, and what variants or failure modes exist.
    • Solution: how it works, why this design was chosen, and which edge cases matter.
    • Context: what it impacts downstream and how it connects to neighboring concepts.
  3. Teach the next smallest layer. Explain the current layer, then stop. Prefer concrete examples, analogies only when they clarify, and diagrams or code snippets when the topic is structural.

  4. Quiz with active recall. Ask one question at a time. Mix formats:

    • Open-ended restatement: "Explain this back in your own words."
    • Prediction: "What happens if this input changes?"
    • Debugging: "Where would this break?"
    • Multiple choice with varied correct-option positions.
  5. Update the checklist. Tick an item only after the user demonstrates understanding. If their answer is partial, mark what is solid and reteach the missing piece.

  6. Iterate until the requested scope is verified. Keep moving from high-level motivation to low-level mechanics to edge cases. End with a compact recap and, when useful, a final synthesis question.

Read the full file on GitHub · 86 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. 8d ago First seen · 86 lines · 110 tokens per session scan A 45dd5f427654

Subscribe to this mod's changes

deep-teach is a skill published in the GitHub repository congmnguyen/claude-code-wsl2-setup (50 stars, last pushed 7d ago), licensed MIT. It adds 110 tokens to every session and 913 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 2026-08-30.

Related

Other skills, from other repositories

stride-analysis-patterns

Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.

sangrokjung/claude-forge · 30 tokens

blind-spot-pass

Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…

sangrokjung/claude-forge · 221 tokens

prompts-chat

Use when searching, installing, or improving AI skills and prompts via prompts.chat or skills.sh. Triggers on skill search, prompt lookup, install skill, improve prompt, prompts.chat.

sangrokjung/claude-forge · 41 tokens

memstack-marketing-webinar-script

Use this skill when the user says 'webinar script', 'webinar', 'live presentation', 'teach-to-sell', or needs a timestamped presentation script with slide notes, presenter cues, and replay email sequence. Do NOT use for launch plans or static sales page copy.

cwinvestments/memstack · 65 tokens

memstack-development-mentor

Use when the user says 'teach me', 'explain as you go', 'mentor mode', 'walk me through', 'help me learn', 'explain why', 'learning mode', or wants real-time plain language narration of decisions and tradeoffs while building. Do NOT use for code review or debugging.

cwinvestments/memstack · 69 tokens

aiwg-guide

Contextual AIWG help — explains current version features, answers how-to questions, routes live queries to the steward.

jmagly/aiwg · 26 tokens