tldr-code-analysis

Generate token-efficient structural summaries of codebases using AST, call graph, CFG, DFG, and PDG.

2|Updated Apr 8, 2026

Search Tags:#code analysis #token efficiency #call graph #ast #cfg #dfg #pdg

Ready to run

npx skills add https://github.com/DojoGenesis/gateway --skill tldr-code-analysis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tldr-code-analysis
Source: https://github.com/DojoGenesis/gateway/tree/main/plugins/continuous-learning/skills/tldr-code-analysis
Command: npx skills add https://github.com/DojoGenesis/gateway --skill tldr-code-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Understanding an unfamiliar codebase quickly while staying within LLM token limits is painful; reading raw files consumes too many tokens and obscures structural relationships.

Core Features & Use Cases

5‑layer analysis (AST, Call Graph, CFG, DFG, PDG) that reduces token usage by up to 95 %.
Depth modes (overview, deep, full) let you balance detail against token budget.
Multi‑language support for Python, TypeScript, JavaScript, Go, Rust and more, suitable for onboarding, refactoring, bug tracing, and code audits.

Quick Start

Ask the tldr-code-analysis skill to analyze the repository at /path/to/project with depth “deep”.

Frequently Asked Questions about tldr-code-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I analyze an unfamiliar codebase without exceeding LLM token limits?▼

To analyze an unfamiliar codebase without exceeding token limits, generate a token-efficient structural summary using AST, call graph, CFG, DFG, and PDG. This 5-layer analysis reduces token usage by up to 95% while preserving structural relationships for onboarding or refactoring.

Does multi-language code analysis support Python, TypeScript, and Rust?▼

Yes, multi-language code analysis supports Python, TypeScript, JavaScript, Go, and Rust. It uses language-aware parsers to produce structural summaries suitable for bug tracing and code audits across these languages.

What is the best way to generate a call graph and AST for a large project?▼

The best way to generate a call graph and AST for a large project is using depth modes like overview, deep, or full. These modes balance structural detail against your token budget during codebase analysis.

Do I need file-system access to generate a control flow graph from source code?▼

Yes, you need file-system access to generate a control flow graph. Language-aware parsers require direct file-system access to read source files and produce accurate CFG and data flow graph representations.

How do I start a deep code analysis on a specific repository path?▼

To start a deep code analysis, point the tool to your repository path and select the deep depth mode. This instructs the parser to produce detailed AST and program dependence graphs within your token budget.

Why does reading raw source files obscure structural relationships during code audits?▼

Reading raw source files obscures structural relationships because it consumes too many tokens and lacks explicit connections. Generating a program dependence graph and call graph instead clarifies these dependencies efficiently.