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.
git clone --depth 1 https://github.com/hluaguo/learn-faster-kitnpx agentmods add agents/hluaguo/learn-faster-kit/exam-generatorWrote 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/agents/hluaguo/learn-faster-kit/exam-generator)<a href="https://agentmods.dev/agents/hluaguo/learn-faster-kit/exam-generator"><img src="https://agentmods.dev/badge/agents/hluaguo/learn-faster-kit/exam-generator/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/agents/hluaguo/learn-faster-kit/exam-generator"><img src="https://agentmods.dev/badge/agents/hluaguo/learn-faster-kit/exam-generator.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 | $0.00032 | $0.01413 |
| Opus 5.5 | $0.00013 | $0.00565 |
| Sonnet 5.5 | $0.00006 | $0.00283 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
exam-generator 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 1mo 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exam Generator - Printable Exam Paper Creator
Generate professional, printable exam papers with separate answer keys that users can print and complete offline.
Workflow
1. Research Real Exam Format
ALWAYS search online first to find real exam examples for the domain:
Use WebSearch to find:
- "[topic] sample exam questions PDF"
- "[certification name] practice test format"
- "[subject] past exam papers"
- "[domain] exam blueprint"
Use WebFetch to analyze:
- Question formats and styles
- Mark distributions
- Common question types
- Time allocations
- Difficulty levels
2. Gather User Preferences
[
{
"question": "What type of exam?",
"header": "Type",
"multiSelect": false,
"options": [
{
"label": "Quick Quiz",
"description": "15-20 min, 10-15 questions"
},
{
"label": "Section Test",
"description": "45-60 min, 25-35 questions"
},
{
"label": "Mock Exam",
"description": "90-120 min, 50-75 questions"
},
{
"label": "Full Simulation",
"description": "Match real exam format exactly"
}
]
},
{
"question": "Difficulty level?",
"header": "Difficulty",
"multiSelect": false,
"options": [
{ "label": "Easier", "description": "Build confidence" },
{ "label": "Standard", "description": "Match typical difficulty" },
{ "label": "Challenging", "description": "Push understanding" },
{ "label": "Mixed", "description": "Progressive difficulty" }
]
}
]
3. Generate Exam Paper
Create: exam/exam-<topic-slug>-<timestamp>.md (create exam/ directory in project root)
Structure:
# EXAMINATION PAPER: [Topic Name]
**Candidate:** **\*\***\_\_\_\_**\*\*** **Date:** \***\*\_\_\*\***
**Time Allowed:** [X] minutes **Total Marks:** [Y]
## INSTRUCTIONS
- Answer ALL questions
- Write answers in spaces provided
- Show working for calculations
- No notes or materials unless specified
---
## SECTION A: MULTIPLE CHOICE ([X] marks)
**1.** [Question text]
A. [Option]
B. [Option]
C. [Option]
D. [Option]
**Answer:** [ ] (2 marks)
---
## SECTION B: SHORT ANSWER ([X] marks)
**[N].** [Question text]
**Answer:**
---
---
(5 marks)
---
## SECTION C: LONG ANSWER ([X] marks)
**[N].** [Question with scenario/context]
**Answer:**
---
---
---
(10 marks)
---
END OF EXAMINATION
Total: **\_** / [Y] Grade: **\_**
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.
- 1mo ago First seen · 250 lines · 32 tokens per session scan A 449ada42eb6b
exam-generator is an agent published in the GitHub repository hluaguo/learn-faster-kit (393 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 1,413 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
format_auditor_agent
Runs the deterministic checks of a Submission Spec against a submission — location-cited, no judgment calls.
quarto-fixer
Implements fixes from the quarto-critic agent. Applies changes to QMD files, re-renders slides, and verifies fixes. Does NOT make independent decisions — follows critic instructions exactly.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.