Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.

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" The 5 Layer Stack CLI Commands Navigation Search File Analysis Flow Analysis Codebase Analysis Import Analysis Quality & Testing Caching Daemon (Faster Queries) The daemon holds indexes in memory for instant repeated queries. Daemon Commands Daemon Features Feature Description Auto shutdown 30 minutes idle Query caching SalsaDB memoization Content hashing Skip unchanged files Dirty tracking Incremental re indexing Cross platform Unix sockets / Windows TCP Daemon Socket Protocol Send JSON to socket, receive JSON response: All 22 daemon commands: Semantic Search (P6) Natural language code search using embeddings. Setup Search Configuration In .claude/settings.json : Languages Supported Language AST Call Graph CFG DFG PDG Python Yes Yes Yes Yes Yes TypeScript Yes Yes Yes Yes Yes JavaScript Yes Yes Yes Yes Yes Go Yes Yes Yes Yes Yes Rust Yes Yes Yes Yes Yes Java Yes Yes C/C++ Yes Yes Ruby Yes PHP Yes Kotlin Yes Swift Yes C Yes Scala Yes Lua Yes Elixir Yes Ignore Patterns TLDR respects .tldrignore (gitignore syntax): First run creates .tldrignore with sensible defaults. Use no ignore to bypass. When to Use TLDR vs Other Tools Task Use TLDR Use Grep Find function definition tldr extract file function X Search code patterns tldr search "pattern" String literal search grep "literal" Config values grep "KEY=" Cross file calls tldr calls Reverse deps tldr impact func Complexity analysis tldr cfg file func Variable tracking tldr dfg file func Natural language query tldr semantic search Python API Bug Fixing Workflow (Navigation + Read) Key insight: TLDR navigates, then you read. Don't try to fix bugs from summaries alone. The Pattern Why This Works For cross file bugs (e.g., wrong field name, type mismatch), you need to see: The file with the bug (handler accessing task.user id ) The file with the contract (model defining owner id ) TLDR finds which files matter. Then you read them. Getting More Context If TLDR output isn't enough: tldr search "pattern" . C 20 Get actual code with 20 lines context tldr imports file.py See what a file depends on Read the file directly if you need the full implementation Token Savings Evidence The insight: Call graph navigates to relevant code, then layers give structured summaries. You don't read irrelevant code.

tldr-code