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/hluaguo/learn-faster-kitWrote 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/hluaguo/learn-faster-kit/generate-exam)<a href="https://agentmods.dev/commands/hluaguo/learn-faster-kit/generate-exam"><img src="https://agentmods.dev/badge/commands/hluaguo/learn-faster-kit/generate-exam.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 5.1 | $0.00011 | $0.00508 |
| Opus 5 | $0.00005 | $0.00254 |
| Sonnet 5 | $0.00002 | $0.00102 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
generate-exam 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 8d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Current topic: !
ls .learning/
Your Task
Generate a professional, printable exam paper with a separate answer key that the user can print and complete offline.
Step 1: Gather Topic Context
Identify the topic directory from the context above (ignore scripts, references, config.json).
Then read:
.learning/<topic-slug>/syllabus.md- What concepts are in the curriculum.learning/<topic-slug>/metadata.json- Progress and current phase.learning/<topic-slug>/progress.json- Completed concepts.learning/<topic-slug>/review_schedule.json- What's been learned and reviewed
Step 2: Consolidate Context
Create a summary of:
- Topic name: [Extract from metadata]
- Learning phase: [Current phase from metadata]
- Concepts covered: [List from progress.json]
- Concepts mastered: [From review_schedule.json - concepts with review_count > 2]
- Recent concepts: [Last 5-10 concepts learned]
- Weak areas: [Concepts with low review counts or marked as difficult]
Step 3: Invoke Exam Generator with Context
Use the Task tool to invoke the exam-generator agent with the consolidated context:
How to invoke a subagent:
Use the Task tool with:
subagent_type: "exam-generator"prompt: Include all the consolidated context and instructionsdescription: Short description like "Generate printable exam"
Example:
Task tool call:
- subagent_type: "exam-generator"
- description: "Generate printable exam"
- prompt: "Generate a printable exam paper with answer key.
Topic Context:
- Topic: [topic name]
- Current Phase: [phase name]
- Total concepts covered: [N]
- Concepts mastered: [list]
- Recent concepts: [list]
- Weak areas: [list]
Please:
1. Search online for real exam examples in this domain
2. Ask user preferences (type, difficulty, scope)
3. Generate exam paper covering these concepts (focus on recent and weak areas)
4. Generate separate answer key
5. Convert both to PDF using the script
6. Provide file paths and next steps"
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.
- 8d ago First seen · 70 lines · 11 tokens per session scan A 4e8402fa7e86
generate-exam is a command published in the GitHub repository hluaguo/learn-faster-kit (371 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 508 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 2026-08-30.
Other commands, from other repositories
cheatsheet
Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.
produire
Produire une fiche ou un document, puis vérifier que ça tient.
master
Master a CS or technical book — extracts code + prose, builds active recall cards, concept dependency map, typed challenges, and produces a mastery guide + slide presentation. Supports epub, PDF (including scanned), and text files.
read
Distill a single book into a reading guide and slide presentation. Supports epub, PDF (including scanned), and text files.
open
Open a PDF in the in-app viewer panel.
brief-compliance-check
Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.