reverse-engineer-slidedeck

reverse-engineer-slidedeck is a command for Claude Code from jovaneyck/obsidian-ai-agent-stuff. It costs 0 tokens per session (1,088 once invoked), scanned A, original, MIT.

A command that turns PNG images of presentation slides into a detailed text document. It reads every slide in numerical order, including visible text, code, diagrams, and other meaningful visual details.

In plain words
What is it for?
Use it to document a folder of slides, extract presentation content, identify slide types, and save the result as a document in a vault.
Why use it?
It saves you from manually transcribing and describing a slide deck. Processing every image also reduces the risk of missing slides or important visual information.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to document a folder of slides, extract presentation content, identify slide types, and save the result as a document in a vault.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jovaneyck/obsidian-ai-agent-stuff/reverse-engineer-slidedeck
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.

Clone the repo
git clone --depth 1 https://github.com/jovaneyck/obsidian-ai-agent-stuff

Made for: Claude Code.

Wrote 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.

agentmods badge for reverse-engineer-slidedeck

README.md
[![agentmods](https://agentmods.dev/badge/commands/jovaneyck/obsidian-ai-agent-stuff/reverse-engineer-slidedeck/github.svg)](https://agentmods.dev/commands/jovaneyck/obsidian-ai-agent-stuff/reverse-engineer-slidedeck)
Your own site
<a href="https://agentmods.dev/commands/jovaneyck/obsidian-ai-agent-stuff/reverse-engineer-slidedeck"><img src="https://agentmods.dev/badge/commands/jovaneyck/obsidian-ai-agent-stuff/reverse-engineer-slidedeck/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.

agentmods 80×15 button for reverse-engineer-slidedeck

Your own site · 80×15
<a href="https://agentmods.dev/commands/jovaneyck/obsidian-ai-agent-stuff/reverse-engineer-slidedeck"><img src="https://agentmods.dev/badge/commands/jovaneyck/obsidian-ai-agent-stuff/reverse-engineer-slidedeck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,088 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01088
Opus 5 $0.00000 $0.00544
Sonnet 5 $0.00000 $0.00218
Haiku 4.5 $0.00000 $0.00109

Measured 9d ago against content hash 4fba93a062f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reverse-engineer-slidedeck 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 9d 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.

reverse-engineer-slidedeck/.claude/commands/reverse-engineer-slidedeck.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reverse Engineer Slide Deck

Convert a folder of PNG slide images into a comprehensive text document following Jo Van Eyck's writing style.

Command Parameters

Slide Folder: {{slide_folder}} (required - absolute path to folder containing PNG slide images)

Output Document: {{output_document}} (required - path to output document in vault, e.g., "projects/my-presentation.md")

Instructions

1. Slide Discovery and Validation

  • List all PNG files in the specified folder
  • Sort slides numerically (Slide1.PNG, Slide2.PNG, etc.) to ensure proper order
  • Validate that slides exist and are readable
  • Report total number of slides found

2. Systematic Slide Processing

CRITICAL: Process EVERY slide individually and systematically in batches of 10 slides:

  • Read each slide image one by one in numerical order
  • Extract all text content, concepts, code examples, and visual information
  • Identify slide type (title, section header, content, code example, diagram, etc.)
  • Note any visual elements that provide context (charts, diagrams, images)
  • MANDATORY: If a slide contains no parsable text or meaningful content, add the marker: <SLIDE X WAS NOT PROCESSED AUTOMATICALLY> where X is the slide number
  • BATCH PROCESSING: Process slides in batches of 10, writing accumulated content to output file after each batch to prevent context loss and enable resumption if interrupted

3. Content Analysis and Structure

For each slide, analyze:

  • Main topic or concept being presented
  • Key points or bullet items
  • Code examples with proper syntax highlighting
  • Quotes or references to experts/sources
  • Visual information (diagrams, charts, images) and their meaning
  • Progression from previous slides and connection to next slides

4. Text Generation Following Specific Writing Style

Read and utilize the style found in writing-style.md.

5. Document Structure

Create a comprehensive document with:

  • Title and metadata (based on first slide or inferred from content)
  • Table of contents or overview section
  • Major sections corresponding to slide groups/topics
  • Subsections for detailed concepts
  • Code examples properly formatted
  • Conclusion synthesizing key takeaways
  • References to sources mentioned in slides

Read the full file on GitHub · 100 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. 9d ago First seen · 100 lines · 0 tokens per session scan A 4fba93a062f7

Subscribe to this mod's changes

reverse-engineer-slidedeck is a command published in the GitHub repository jovaneyck/obsidian-ai-agent-stuff (99 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,088 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 2026-08-30.