আপনার AI তার টোকেন বাজেটের ৯০% অপ্রয়োজনীয় ফাইল পড়তে নষ্ট করে।

Read file (cached, compressed). Cached re-reads can be ~13 tok when unchanged. Auto-selects optimal mode. Modes: full|map|signatures|diff|aggressive|entropy|task|reference|lines:N-M. fresh=true forces a disk re-read.

Run shell command (compressed output, 95+ patterns). Use raw=true to skip compression. cwd sets working directory (persists across calls via cd tracking). Output redaction is on by default for non-admin roles (admin can disable).

Regex code search (.gitignore aware, compact results). Deterministic ordering. Secret-like files (e.g. .env, *.pem) are skipped unless role allows. ignore_gitignore requires explicit policy.

Semantic code search (BM25 + optional embeddings/hybrid). action=reindex to rebuild.

Directory listing with file counts.

Edit a file via search-and-replace. Works without native Read/Edit tools. Use this when the IDE's Edit tool requires Read but Read is unavailable.

Batch read files in one call. Same modes as ctx_read.

Auto-select optimal read mode for a file.

Incremental diff — sends only changed lines since last read.

Retrieve archived tool output (zero-loss). Large outputs are auto-archived; use this to retrieve full details. Actions: retrieve (default), list.

List all symbols in a file (functions, structs, classes, methods) with signatures. Much fewer tokens than reading the full file.

Read a specific symbol (function, struct, class) by name. Returns only the symbol code block instead of the entire file. 90-97% fewer tokens than full file read.

Budget-aware context fill — auto-selects compression per file within token limit.