exercise-gen

exercise-gen is a skill for Claude Code, Codex from PranitMohnot/repo-learner-suite. It costs 143 tokens per session (5,326 once invoked), scanned A, original, MIT.

A tool that creates hands-on Jupyter notebook exercises from an analysis of a codebase. Jupyter notebooks combine explanatory text with runnable code cells.

In plain words
What is it for?
Use it to scaffold exercises such as using, modifying, debugging, creating, or comparing code, then validate the notebooks and link them into a curriculum.
Why use it?
It turns knowledge of an existing codebase into guided practice and checks that the generated exercises run correctly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - Back-link: "Context: you just read §X.Y in [curriculum.md](../curriculum.md#sX.Y)".

Good fit Use it to scaffold exercises such as using, modifying, debugging, creating, or comparing code, then validate the notebooks and link them into a curriculum.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/PranitMohnot/repo-learner-suite
agentmods
npx agentmods add skills/pranitmohnot/repo-learner-suite/exercise-gen

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 exercise-gen

README.md
[![agentmods](https://agentmods.dev/badge/skills/pranitmohnot/repo-learner-suite/exercise-gen/github.svg)](https://agentmods.dev/skills/pranitmohnot/repo-learner-suite/exercise-gen)
Your own site
<a href="https://agentmods.dev/skills/pranitmohnot/repo-learner-suite/exercise-gen"><img src="https://agentmods.dev/badge/skills/pranitmohnot/repo-learner-suite/exercise-gen/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 exercise-gen

Your own site · 80×15
<a href="https://agentmods.dev/skills/pranitmohnot/repo-learner-suite/exercise-gen"><img src="https://agentmods.dev/badge/skills/pranitmohnot/repo-learner-suite/exercise-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,326 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 $0.00143 $0.05326
Opus 5 $0.00072 $0.02663
Sonnet 5 $0.00029 $0.01065
Haiku 4.5 $0.00014 $0.00533

Measured 9d ago against content hash eb24f310f530, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

exercise-gen 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/check_executed_notebook.py, scripts/scaffold_notebook.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

exercise-gen/SKILL.md · 537 lines

How it starts

The opening of the file, as written. The whole thing — 537 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exercise Generator

Produce scaffolded Jupyter notebooks that teach a codebase through hands-on exercises. Each notebook is self-contained, runnable on its own, and progresses from guided usage through independent creation.

This skill is manifest-driven. The manifest at learn/internals/exercise-plan.md is the source of truth for which exercises exist, where they slot into curriculum.md, and how each is rendered. Read the Shared Contracts in repo-learner/SKILL.md before starting.

Read references/exercise-types.md for the exercise taxonomy (use / modify / debug / create / compare) and when to use each. Read references/subagent-brief-template.md before fanning out to subagents.

Notebook-first, with narrow inline exceptions

Default emission is .ipynb. Two narrow exceptions allowed:

  1. compare exercises — table or side-by-side prose comparisons fit naturally inline.
  2. Short copy-paste-run blocks — fewer than ~15 lines, no scaffold, no validation, no solution. Pure "run this and observe."

Everything else is a notebook. The long-term direction is "everything becomes a notebook" — treat inline as an exception you should be reluctant to use, not a co-equal option.

Pipeline

Stages 1–2 produce the manifest (if it doesn't already exist). Stages 3–5 consume it.

Stage 1: Candidate Mining

Scan the codebase to identify "exercisable surfaces" — places where a learner can do something concrete that builds understanding.

What to scan for:

  1. Public API functions with clear I/O. Natural "use" exercises.
  2. Configuration and setup patterns. "Set up and configure" exercises.
  3. Extension points. Subclass / register / implement — the best exercises, because they force understanding of the abstraction.
  4. Workflows visible in examples/tests. The authors already wrote these — extract the pattern, strip to skeleton.
  5. Error-handling paths and common mistakes. "Debug" exercises.
  6. Comparison points. Two ways to do the same thing → "compare" exercises.

Read the full file on GitHub · 537 lines

Files

What ships with it

5 files 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. 9d ago First seen · 537 lines · 143 tokens per session scan A eb24f310f530

Subscribe to this mod's changes

exercise-gen is a skill published in the GitHub repository PranitMohnot/repo-learner-suite (4 stars, last pushed 3mo ago), licensed MIT. It adds 143 tokens to every session and 5,326 once invoked, about $0.0007 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

lov-hanzi-lens

A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.

lovstudio/skills · 82 tokens

lov-subtitle-freedom

Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.

lovstudio/skills · 25 tokens

lov-thesis-polish

An academic editing tool for improving an MBA thesis or dissertation in Markdown, a plain-text format for structured documents. It addresses language, argument structure, logic, research contributions, and formatting.

lovstudio/skills · 90 tokens

learning-assistant

An interactive study assistant that turns a learning goal into a structured plan and guides the learner through it. It uses a local knowledge graph, a connected record of topics and learning state, as its long-term memory.

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