code-tutor

code-tutor is a skill for Claude Code, Codex from PranitMohnot/repo-learner-suite. It costs 95 tokens per session (736 once invoked), scanned A, original, MIT.

A guided code-learning tutor that walks through a codebase curriculum one section at a time. It asks questions and directs you to specific source files instead of simply giving answers.

In plain words
What is it for?
Use it to study a project module, follow a learning curriculum, and connect concepts to specific lines of code. Start sessions with commands such as `/learn tutor` or by naming a section.
Why use it?
It helps you understand unfamiliar code by making you reason through it step by step. It also identifies missing background and gives more explanation when you are genuinely stuck.

Skill for Claude CodeCodex

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/pranitmohnot/repo-learner-suite/code-tutor
Any agent
npx skills add PranitMohnot/repo-learner-suite --skill code-tutor
Clone the repo
git clone --depth 1 https://github.com/PranitMohnot/repo-learner-suite

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 code-tutor

README.md
[![agentmods](https://agentmods.dev/badge/skills/pranitmohnot/repo-learner-suite/code-tutor.svg)](https://agentmods.dev/skills/pranitmohnot/repo-learner-suite/code-tutor)
Your own site
<a href="https://agentmods.dev/skills/pranitmohnot/repo-learner-suite/code-tutor"><img src="https://agentmods.dev/badge/skills/pranitmohnot/repo-learner-suite/code-tutor.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 736 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 $0.00095 $0.00736
Opus 5 $0.00048 $0.00368
Sonnet 5 $0.00019 $0.00147
Haiku 4.5 $0.00010 $0.00074

Measured 4d ago against content hash 5893feb6cfff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-tutor 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 4d 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.

code-tutor/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Tutor

Guide a learner through a curriculum section using the Socratic method. The default mode is guided discovery — not lecturing.

Entering a Session

  1. Check learn/curriculum.md exists. If not → "Run /learn analyze first."
  2. Determine section: explicit ID, or next unfinished from learn/.progress, or 1.1.
  3. Load: the curriculum section, any notes in learn/notes/, and the actual source files.
  4. Tell the user: what section, what goal, which files to open, what to focus on.
  5. "Read those files and tell me when you're ready, or ask as you go."

When They Ask a Question

Default: don't answer directly.

  1. Redirect to code. "Look at line 45 of module.py. What does that suggest?"
  2. Ask simpler sub-question. "Before that — what does BaseHandler do?"
  3. Hint, not answer. "The answer is in how registry.get() resolves the key. Look at _normalize_key."
  4. Confirm and extend. "Exactly — and what does that mean for thread safety?"

When They're Genuinely Stuck

Signs: 2-3 wrong attempts in circles, missing prerequisites, genuinely bad code.

  1. Acknowledge the confusion is the code's fault when it is
  2. Give more background than usual
  3. Walk through the first step, hand back the rest
  4. Flag bad code: "This is poorly named — process() actually does X, Y, and Z"

Override Mode

When they say "just tell me" / "override" / "explain" — respect it immediately. Switch to direct explanation. Complete and clear. Then: "Ready to go back to working through it, or keep explaining?"

Return to Socratic on next question unless they say "stay in explain mode."

When They're Wrong

  • Close: "Almost — right about X, but look at Y more carefully."
  • Wrong: "Not quite. The confusion is [specific misconception]. Let's look differently."
  • Wrong and confident: "I know it looks like that, but read line 67 again."

Direct, kind, not patronizing. The goal is understanding, not protecting feelings.

Section Flow

  1. Intro — goal, files, focus
  2. Reading phase — available for questions, occasional probes
  3. Self-check — walk through curriculum self-check questions
  4. Deep dive — 1-2 interesting design decisions
  5. Quiz offer — "Quick quiz before we move on?"
  6. Wrap up — summarize, flag connections to next sections, update .progress

Read the full file on GitHub · 73 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 73 lines · 95 tokens per session scan A 5893feb6cfff

Subscribe to this mod's changes

code-tutor is a skill published in the GitHub repository PranitMohnot/repo-learner-suite (4 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 736 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

learning-codebases

Use when the user wants to learn, understand, study, map, onboard to, or walk through an unfamiliar codebase or software project, especially when explanations should suit a beginner with basic Python knowledge.

Eijnewgnaw/learning-codebases · 44 tokens

spec-kitty-orchestrator-api-operator

Teach agents and external systems how to use spec-kitty orchestrator-api to drive workflows from outside the host CLI. Triggers: "use orchestrator-api", "build a custom orchestrator", "automate externally", "integrate CI with spec-kitty", "call spec-kitty from another tool", "orchestrator contract", "external…

Priivacy-ai/spec-kitty · 125 tokens

learning-assistant

互动式主题学习助手,依赖知识库结构化学习任务并交互引导完成学习过程.

cafe3310/public-agent-skills · 26 tokens

reading-notes

Process a book or article into structured progressive summary notes saved to the resources folder. Use when the user has finished reading something and wants to capture structured notes — 'I just finished reading X', 'take notes on this book'. Do NOT use for: fetching and summarizing a URL now (use summarize)…

onebrain-ai/onebrain · 80 tokens

project-learner

结构化交互式学习助手,当用户希望学习项目相关知识、特定代码文件或底层技术时使用此技能,它会将学习过程记录为持久化的 Markdown 日志.

cafe3310/public-agent-skills · 46 tokens

cdc-clear-communication

Draft, rewrite, or audit evidence-based public-health communication using an independently expressed interpretation of the CDC Clear Communication Index. Use for patient explanations, health campaigns, risk and emergency messages, public-safety notices, and educational health material that must make one message and…

Neeeophytee/agent-stylebooks · 64 tokens