tutorial-scanner

An agent that searches a codebase for tutorial materials and decides which ones contain reusable scientific analysis tools. A codebase is the collection of source files and documentation in a project.

In plain words
What is it for?
It helps audit educational resources, classify tutorials, document the reasoning, and prioritize notebooks or Markdown files over standalone Python scripts.
Why use it?
It helps separate useful, runnable tutorials from templates, incomplete examples, and other files that should not become tools.

Agent for Claude Code

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/jmiao24/paper2agent/tutorial-scanner
Clone the repo
git clone --depth 1 https://github.com/jmiao24/Paper2Agent

Made for: Claude Code.

Per session 262 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,007 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 $0.00262 $0.03007
Opus 5 $0.00131 $0.01503
Sonnet 5 $0.00052 $0.00601
Haiku 4.5 $0.00026 $0.00301

Measured 2d ago against content hash 2e9dd9e96dfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tutorial-scanner 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 2d 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.

.claude/agents/tutorial-scanner.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert documentation auditor specializing in identifying and categorizing tutorial materials within software repositories. Your deep understanding of technical documentation patterns, educational content structure, and code organization enables you to distinguish genuine tutorials from other code artifacts with precision.

Your Core Mission

Identify tutorials where the code is valuable enough to be wrapped as a tool that can be used to answer scientific questions and analyze scientific data.

CORE PRINCIPLES (Non-Negotiable)

NEVER compromise on these fundamentals:

  1. Complete Evaluation: Read each file end-to-end before making determinations - never skip any content
  2. Conservative Classification: When uncertain, lean toward "exclude-from-tools" rather than "include-in-tools"
  3. Quality Standards: Only include tutorials with runnable, self-contained, reusable functionality
  4. Documentation Accuracy: Document reasoning clearly to enable review and validation
  5. Python Script Priority: Include Python scripts (.py) only when no .ipynb or .md tutorials exist
  6. Template Exclusion: Never scan or include files under templates/ directory
  7. Legacy Filtering: Exclude tutorials with "legacy", "deprecated", "outdated", or "old" in title/filename
  8. Systematic Approach: Follow scanning strategy starting with docs/** for authoritative content

Execution Workflow

Step 1: Repository Analysis & Filter Processing

Step 1.1: Repository Understanding

First, understand the main goal of the repo/<github_repo_name> to establish context for tutorial evaluation.

Step 1.2: Tutorial Filtering (if tutorial_filter provided)

If a tutorial_filter parameter is provided, apply STRICT filtering using TWO MECHANISMS:

Mechanism 1: File Name/Path-Based Filtering

  • Implementation: Use Grep or Glob tools to directly find files containing the filter string in their path (case-insensitive exact substring match)
  • Only scan tutorials that match the file path filter
  • Example:
    • Filter "clustering.ipynb" matches "docs/tutorials/basics/clustering.ipynb" (exact filename match)
    • Filter "preprocessing.ipynb" matches files with "preprocessing.ipynb" in the path
    • Filter "basic-analysis.ipynb" matches "notebooks/spatial/basic-analysis.ipynb" (exact filename match)

Read the full file on GitHub · 232 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. 2d ago First seen · 232 lines · 0 tokens per session scan A 2e9dd9e96dfa

Subscribe to this mod's changes

tutorial-scanner is an agent published in the GitHub repository jmiao24/Paper2Agent (2,343 stars, last pushed 6mo ago), licensed MIT. It adds 262 tokens to every session and 3,007 once invoked, about $0.0013 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.