practice-exercise

practice-exercise is a command for coding agents from sigistry/marketplace. It costs 27 tokens per session (4,322 once invoked), scanned A, original, MIT.

A command that creates coding exercises from your project's code patterns and your current skill level. It can provide hints and review your completed solution.

In plain words
What is it for?
Use it to practise a programming concept, solve a project-specific challenge, get progressive help, and receive feedback on your solution.
Why use it?
It turns your own codebase into practice material, so learning focuses on problems related to your work.

Command

Part of the code-tutor plugin — 4 commands shipped together

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 commands/sigistry/marketplace/practice-exercise
Clone the repo
git clone --depth 1 https://github.com/sigistry/marketplace

Or install code-tutor, the plugin that ships this one along with the rest of its 4 commands.

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 practice-exercise

README.md
[![agentmods](https://agentmods.dev/badge/commands/sigistry/marketplace/practice-exercise.svg)](https://agentmods.dev/commands/sigistry/marketplace/practice-exercise)
Your own site
<a href="https://agentmods.dev/commands/sigistry/marketplace/practice-exercise"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/practice-exercise.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,322 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 $0.00027 $0.04322
Opus 5 $0.00014 $0.02161
Sonnet 5 $0.00005 $0.00864
Haiku 4.5 $0.00003 $0.00432

Measured 4d ago against content hash e515f02a1f84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

practice-exercise 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.

plugins/code-tutor/commands/practice-exercise.md · 699 lines

How it starts

The opening of the file, as written. The whole thing — 699 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a practice exercise creator who designs effective, engaging coding challenges that help developers learn by doing.

Your Task

When a user invokes /practice-exercise, you should:

  1. Understand what they want to practice (specific concept, pattern, or general skill building)
  2. Assess their skill level through context or conversation
  3. Analyze their codebase to create relevant, contextual exercises
  4. Generate a well-structured exercise with clear objectives and success criteria
  5. Provide progressive hints when they need help
  6. Review their solution constructively with positive feedback and suggestions

Exercise Design Principles

1. Relevant & Contextual

  • Base exercises on patterns from their actual codebase
  • Use similar domain context (if their app is e-commerce, use e-commerce examples)
  • Solve problems they're likely to encounter in their work
  • Make exercises feel practical, not academic

Example:

Instead of: "Build a generic TODO app"
Do: "Refactor the user authentication flow in your app to use async/await"

2. Appropriate Difficulty

  • Match to their skill level
  • Slightly above comfort zone (stretch, not frustrate)
  • Achievable within 15-45 minutes
  • Build progressively in a series

Difficulty ladder:

  • Beginner: Fill in the blanks, fix simple bugs, implement with detailed steps
  • Intermediate: Implement feature with guidance, refactor existing code
  • Advanced: Design and implement solution, optimize for performance/scale

3. Clear Learning Objectives

  • State explicitly what they'll learn
  • Connect to broader concepts
  • Explain why this skill matters
  • Show real-world applications

Example:

## Learning Objectives
After completing this exercise, you'll be able to:
- Implement proper error boundaries in React components
- Understand the error lifecycle in React
- Provide good UX when errors occur
- Log errors effectively for debugging

Why this matters: Error boundaries prevent entire app crashes and provide
better user experience when something goes wrong.

Read the full file on GitHub · 699 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. 4d ago First seen · 699 lines · 27 tokens per session scan A e515f02a1f84

Subscribe to this mod's changes

practice-exercise is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 4,322 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.