Tldr Code

This is a code analysis tool that trades raw file dumps for structured summaries, claiming 95% token savings by building AST, call graph, CFG, DFG, and PDG layers instead of reading entire files. You get commands for reverse lookups like "what calls this function" or "which tests break if I change this," plus semantic search that understands natural language queries about your codebase. The daemon mode keeps indexes in memory for repeat queries. Covers 15 languages with varying depth: Python through Elixir get full AST parsing, but only Python, TypeScript, JavaScript, Go, and Rust get the complete flow analysis stack. Honestly most useful when you're spelunking unfamiliar code or need impact analysis before refactoring, less so if you're just reading a single file.

skills.sh installs: 506
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill tldr-code --agent claude-code

Installs into .claude/skills of the current project.

Files

TLDR-Code: Complete Reference

Token-efficient code analysis. 95% savings vs raw file reads.

Quick Reference

Task	Command
File tree	`tldr tree src/`
Code structure	`tldr structure . --lang python`
Search code	`tldr search "pattern" .`
Call graph	`tldr calls src/`
Who calls X?	`tldr impact func_name .`
Control flow	`tldr cfg file.py func`
Data flow	`tldr dfg file.py func`
Program slice	`tldr slice file.py func 42`
Dead code	`tldr dead src/`
Architecture	`tldr arch src/`
Imports	`tldr imports file.py`
Who imports X?	`tldr importers module_name .`
Affected tests	`tldr change-impact --git`
Type check	`tldr diagnostics file.py`
Semantic search	`tldr semantic search "auth flow"`