phodal

phodal / claude-code-codex-slide

Public

a analysis source code from claude code by codex with GPT Slide SKILL

31
37
69% credibility
Found Apr 01, 2026 at 31 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

This repository reconstructs the source code of Anthropic's Claude Code terminal AI agent from public npm package source maps and generates presentation slides analyzing its architecture for research purposes.

How It Works

1
🔍 Discover the hidden code explorer

You find this special collection on GitHub that uncovers the inner workings of a powerful coding helper.

2
📖 Read the guide

You learn it's a research tool that rebuilds and studies the brain of an AI coding assistant from public clues.

3
🧩 Uncover the pieces

With a simple run, you rebuild thousands of code files to see how everything fits together.

4
📊 Build your story slides

You create beautiful presentations that map out the assistant's thinking paths, tools, and safety guards.

💡 Master the magic

You now deeply understand how the AI coding helper plans, acts safely, and teams up with others.

Sign up to see the full architecture

3 more

Sign Up Free

Star Growth

See how this repo grew from 31 to 31 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is claude-code-codex-slide?

This TypeScript project reverse-engineers the source code of Anthropic's Claude Code CLI—an AI agent for terminal-based coding tasks—from its npm package source map, restoring thousands of files for analysis. It generates professional PPTX slide decks that visualize the architecture, like query loops, tool execution paths, permissions, and multi-agent swarms, using AI tools such as Codex for code analysis and GPT for slide creation. Developers get a deep dive into a production agent runtime without official docs, ideal for claude code analysis on github repos.

Why is it gaining traction?

Unlike scattered codeql analysis github actions or basic code analysis tools, it produces polished, AI-assisted decks that map complex systems like MCP integrations and permission stacks, saving hours of manual diagramming. The hook is turning opaque source maps into shareable architecture stories, appealing to devs dissecting closed-source AI agents amid rising interest in codex analysis and github analysis code.

Who should use this?

AI agent builders reverse-engineering tools like Claude Code for inspiration on runtime orchestration; security researchers probing permission models in terminal CLIs; teams auditing github repos for agent patterns, such as mcp code analysis or multi-agent flows in coding assistants.

Verdict

Grab it if you're deep into claude analysis—its ~0.7% credibility score reflects the unofficial, research-only nature and 31 stars, signaling niche maturity without tests or production polish. Pair with official docs for a full picture, but it's a solid starting point for agent runtime breakdowns.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.