Compressed file read for CONTEXT ONLY — strips comments, docstrings, types, and whitespace. Typical savings: 10-50% depending on comment density (up to 80% on heavily documented code, as low as 8% on minimal-comment code). Shows virtual line markers where content was stripped. NEVER use for files you plan to edit — comments and formatting are permanently removed from output. Use the built-in Read tool when you need to Edit a file.

Ultra-compressed file read showing ONLY function/class/method signatures with IMPORTS and EXPORTS summary — all implementation bodies are replaced with expand handles. Strong on function-heavy code (80-99% savings), weaker on flat data/config files. Use when you need to understand a module API surface without reading implementation details. NEVER use for files you plan to edit. For implementation details, use fullscope_context. For editing, use the built-in Read tool.

Drill into a specific function from a fullscope_skeleton output. Takes a file path + expand handle (e.g. "fn:login" from the skeleton placeholder). Returns just that function body with context-level compression (comments stripped, logic preserved). Use this to progressively disclose detail: start with fullscope_skeleton (cheapest), then fullscope_expand only for functions you care about.

Search files with compressed results — runs ripgrep and filters output through fullscope to save tokens. Use instead of Grep/Bash for exploratory searches where you need to scan many results. For precise searches where you need exact line content, use the built-in Grep tool.

Find where a symbol (function, class, variable) is imported or referenced across the project. Returns results grouped by file. Complements fullscope_skeleton — skeleton shows what a file provides, usages shows where those exports are consumed. Best for: debugging "who calls this?", understanding dependencies.

Read multiple files in one call, each minified. Saves tool-call overhead. Supports: (1) intent parameter — tell the tool WHY you're reading these files and it biases minification to preserve relevant content; (2) token budgeting — files auto-downshift from context to skeleton using information density; (3) cross-file import dedup; (4) dependency-ordered output (leaf deps first as skeleton, importers after with full context).

Compressed codebase orientation — returns filtered directory tree, key config files (package.json/Cargo.toml/etc compressed), git status, and detected entry points with their critical-path dependencies. Use this as the first call when exploring a new codebase.

Verify a line number from a compressed view against the raw file. Since compressed output preserves original line numbers via virtual markers, this confirms the line content matches. Returns the raw line with ±5 lines of context. Optionally pass expected_content to verify the match. Use before editing to confirm the exact location.

Show session savings: total files compressed, tokens saved, estimated cost savings, and context-rot warnings for files read too many times.