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.
git clone --depth 1 https://github.com/fourleafai/clover-publicWrote 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/fourleafai/clover-public/practice)<a href="https://agentmods.dev/commands/fourleafai/clover-public/practice"><img src="https://agentmods.dev/badge/commands/fourleafai/clover-public/practice/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.
<a href="https://agentmods.dev/commands/fourleafai/clover-public/practice"><img src="https://agentmods.dev/badge/commands/fourleafai/clover-public/practice.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01355 |
| Opus 5.5 | $0.00000 | $0.00542 |
| Sonnet 5.5 | $0.00000 | $0.00271 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
practice 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 28d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
practice
Generate calibrated practice questions, score the user's answers against the real rubric, and coach from what came back.
When to run
- User says "let me practice some questions" or "give me a few behavioral questions for a senior PM role".
- User wants to drill questions, not just read about formats.
The loop
Generate a question, let the user answer in chat, call score_answer, coach from the dimensions it returns. One question at a time. score_answer runs the same scoring the Four-Leaf practice page applies to typed answers, so the score is real. Your job is what to do with it.
Flow
-
Get the role. Validate against
list_rolesif needed. If the user came from prep-role, you already know it. Hold onto the role id: bothgenerate_practice_questionsandscore_answertake it, and passing it toscore_answercalibrates the rubric instead of scoring against a generic one. -
Get the question type.
generate_practice_questionsaccepts:behavioralfor STAR-format stories, leadership, communicationtechnicalfor domain knowledge, including system design promptssituationalfor "what would you do if" scenarioscodingfor algorithmic and implementationcasefor consulting, PM, and strategy
Ask which:
What kind of questions do you want? Behavioral, technical, situational, case, coding?
(Recruiter screens and standalone system design rounds are voice mock rounds, not generation types. If the user asks for one of those, generate the nearest type and mention the voice mock covers the round properly.)
-
Get difficulty and seniority.
difficultyis easy / medium / hard, defaults to medium. Seniority is entry / mid / senior / staff and matters more: it's what you pass toscore_answerasexperienceLevel, and a senior answer scored as entry-level is flattering and useless. -
Call
generate_practice_questions. Ask for 3, not 10. Pacing matters, and three answers scored properly beats ten skimmed.
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.
- 28d ago Changed · +17 lines 0a05b71a4fb5
- 1mo ago First seen · 50 lines · 0 tokens per session scan A 56251fcd132c
practice is a command published in the GitHub repository fourleafai/clover-public (8 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,355 tokens. 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
explain
Explain the subject in depth using the fixed four-part structure: What, Why, Example, Consequences. Treat the subject as the thing to be explained, not as a literal question.
interview
Prepare for the interview from the filed application — predicted questions, STAR answers from real evidence, and gap-defence.
create-onboarding-guide
Command "create-onboarding-guide" from qdhenry/Claude-Command-Suite, covering create onboarding guide and instructions.
init-notebook
A command for creating a NotebookLM notebook containing documentation for a project and its technologies. NotebookLM is a research workspace that answers questions using sources added to a notebook.
ctx7
Quick Context7 Library Documentation Lookup.
diagram-coordinator
Coordinate with agents to generate comprehensive educational diagrams.