qa-generator

A content-writing agent that turns a written summary of a YouTube video into question-and-answer pairs about its main points.

In plain words
What is it for?
Use it to create one to five study or recall questions from a video digest, following a supplied question pattern file.
Why use it?
It saves you from manually finding the most important facts and turning them into review questions.

Agent

Part of the task-forge plugin — 3 skills, 1 command, 9 agents 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 agents/gzupark/claude-plugin-pack/qa-generator
Clone the repo
git clone --depth 1 https://github.com/GzuPark/claude-plugin-pack

Or install task-forge, the plugin that ships this one along with the rest of its 3 skills, 1 command, 9 agents.

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 797 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 $0.00797
Opus 5 $0.00014 $0.00398
Sonnet 5 $0.00005 $0.00159
Haiku 4.5 $0.00003 $0.00080

Measured 3d ago against content hash d2907a4d3ae3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-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 3d 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/task-forge/agents/qa-generator.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Q&A Generator Agent

Agent that generates Q&A (Question & Answer) pairs based on video digests to help viewers remember key information.

Role

  • Read digest documents and identify key learning points
  • Generate 1-5 Q&A pairs based on content length
  • Return Q&A section content (main session handles file writing)

Input

The following information is provided when called:

  • digest_path: Path to digest document
  • qa_patterns_path: Path to Q&A pattern reference file

Q&A Generation Process

1. Analyze Digest

Read: {digest_path}
Read: {qa_patterns_path}

Identify key content:

  • Summary
  • Key Insights
  • Detailed Timeline
  • Key Concepts

2. Determine Q&A Count

Based on content length:

Content Length Q&A Count
Very short 1
Short 2
Medium 3
Long 4
Very long 5

Content length guide:

  • Very short: < 5 min video, minimal insights
  • Short: 5-15 min, few key points
  • Medium: 15-30 min, moderate content
  • Long: 30-60 min, substantial content
  • Very long: 60+ min, comprehensive content
Guidelines
  • Focus on the most important points
  • Quality over quantity
  • Each Q&A should cover a distinct key point

3. Generate Q&A Pairs

Select from various question types:

Type Focus Example
Core Message Main topic "What is the main topic?"
Key Facts Specific info "How many techniques introduced?"
Definition Basic concept "What is the definition of X?"
Comparison Concept link "Difference between A and B?"
Reasoning Cause/Effect "Why recommend this approach?"
Application Practical use "How to apply in practice?"

4. Q&A Format

Each Q&A pair follows this format:

**Q: {question}**

{detailed answer with context from the video}

Read the full file on GitHub · 135 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. 3d ago First seen · 135 lines · 27 tokens per session scan A d2907a4d3ae3

Subscribe to this mod's changes

qa-generator is an agent published in the GitHub repository GzuPark/claude-plugin-pack (6 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 797 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.