JSungMin/vs-token-safer

**English** · 한국어
> A token-saving code layer for Claude Code, for **any** codebase. **TypeScript, JavaScript, and Python work
> with zero setup**; C# and C++ add a language server; and 30+ more languages come in on the built-in
> tree-sitter tier. Proven up to a 26k-translation-unit Unreal Engine monorepo — so your web, backend, or
> data repo is the easy case.
> Your coding agent has a small context window. Your repo is large. **vs-token-safer sits in between.**
>
> Ask where something is, what calls it, or even "how does the auth flow work?" when the name escapes you — and
> instead of pasting a wall of source into the chat, it replies with a short file:line list.
>
> - **Builds normally?** The answers are exact — it reads the same code index your editor relies on.
> - **No toolchain set up?** It still locates your functions and classes.
> - **Forgot the name, only remember what it does?** It finds it from the vocabulary your own code already uses — no AI model, nothing uploaded.
> - **Markdown or a config file?** Jump straight to one section by its heading instead of opening the whole file.
>
> A companion plugin does the same for giant editor and build logs. **None of it leaves your machine.**
Same flow on TypeScript, Python, C#, C++, Go and more (clangd · Roslyn · tsserver · pyright · tree-sitter). VTS_REWRITE=0 blocks instead of rewriting.
The built-in dashboard ( vts serve ) — your indexed repo as a live 3D graph, all on 127.0.0.1. Three modes: include graph (clangd), call graph (live LSP call hierarchy by symbol), and symbol graph — a tree-sitter map of files + import edges that needs no language server , so it renders on any of the 17 tree-sitter languages with zero setup.
Why
- **Keep the context lean.** grep on a large repo — a TypeScript/Python monorepo, a C#/.NET solution, even a 26k-TU Unreal C++ tree — floods the context. The language-server index stays token-capped — ~97–99% smaller (benchmarks).
- **Claude keeps reaching for grep.** The hook doesn't just block it — it **rewrites the command to the indexed query in place**, so the search still runs and the flow never breaks.
- **Edit by symbol, not by line.** Replace/insert-around/delete a declaration by *naming* it — the index supplies the span, so you skip reading the whole file into context.
- **Review a diff by its blast radius, not by eye.** detect_changes maps a git diff to the symbols it changed, walks each one's callers, and scores the risk **LOW/MED/HIGH** — from the blast radius, the caller-cascade depth, and which historically co-changed files this diff *left out*. A review starts from "what does this actually touch," capped to file:line, nothing uploaded. It's the code-review-context idea done the vs-token-safer way: **the official language server for the blast radius and your own git history for the coupling — no persistent graph database, no embeddings.**
- **You can't tell how much grep still slips through.** vts discover reads your recent sessions and reports exactly which searches bypassed the index and what they cost.
- The language server runs **headlessly** — no editor open, unlike an IDE-proxy approach.
Quickstart
Then **restart the Claude Code session** (the vs-search MCP server only starts on a fresh session).
Verify the tools appear and that grep src/**/*.cpp is rerouted to the index. Prerequisites: **Node ≥ 18**
and a language server — clangd (C/C++) / Roslyn (C#) you install; JS/TS + Python auto-install. Details in
Prerequisites below.
> Want only the log analyzer? /plugin install gamedev-log-analyzer@vs-token-safer.
How it works
vs-token-safer isn't a search box — it's a **precision ladder**. You ask where something is, what calls it,
or "how does the auth flow work?" when the name escapes you, and it answers at the highest precision it can
reach, then tells you which rung the answer came from:
- **EXACT** — you know the name and the project builds → the official language server (clangd / Roslyn /
tsserver / pyright), the semantic ground truth.
- **SYNTACTIC** — no toolchain set up → a tree-sitter parse (36 grammars bundled, no native build; 19 languages
with tuned declaration extraction, the rest via a generic parse) still returns real *declarations*, not a grep.
- **FUZZY** — you only remember what the code *does* → a concept dictionary mined from the repo's own
identifiers + comments (no AI model, nothing uploaded).
- **SECTION** — it's a doc or config, not code → Markdown / TOML / YAML / CSS / HTML addressed by heading.
The rungs aren't a one-time pick — they connect, and vts **switches between them as it learns more**. Start