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.
npx agentmods add commands/sigistry/marketplace/practice-exercisegit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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.
[](https://agentmods.dev/commands/sigistry/marketplace/practice-exercise)<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>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.
| Model | Per session | Once 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 |
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.
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:
- Understand what they want to practice (specific concept, pattern, or general skill building)
- Assess their skill level through context or conversation
- Analyze their codebase to create relevant, contextual exercises
- Generate a well-structured exercise with clear objectives and success criteria
- Provide progressive hints when they need help
- 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.
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.
- 4d ago First seen · 699 lines · 27 tokens per session scan A e515f02a1f84
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.
Other commands, from other repositories
build
Guided feature development with approval gates at each phase.
release
Generate changelog, bump version, and create git tag.
bootstrap
Scaffold test, lint, and CI infrastructure for projects that lack it.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
validate
Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.