AI Blocks › Keep your code secure
Code deep reader
Point it at code you need to understand. Get a line-by-line map of how it works before you hunt bugs.
Code deep reader is a free AI skill for the job "Keep your code secure". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · CC BY 4.0 licence · Made by sickn33 · Level: expert · Thinking: high
Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.
What it does
Before you hunt for bugs, you get a slow, line-by-line understanding of what the code does. That cuts guessing, mixed-up facts and lost context in the later audit. It reads each block on its own and asks why it exists, how it works and what it assumes. For every function it notes inputs, outputs, side effects and what must hold true. Then it links each insight to the module and the whole system, so the picture grows from the bottom up. It keeps one clear model and updates it when new evidence appears. It does not report vulnerabilities or suggest fixes.
You give it
- The code or module to study
- The area you care about most (optional)
- Any docs or notes on intent (optional)
You get
- A block-by-block breakdown
- Notes on assumptions and rules that must hold
- A map of how functions and modules connect
- A list of spots that look risky to read
Use it when
- You must audit unfamiliar code and need to understand it first.
- You keep misreading how two modules talk to each other.
- You are preparing a security review or threat model.
- You want facts about the code, not high-level guesses.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can read your project files.