A local dashboard for viewing what vs-token-safer has indexed and how much search data it has reduced. It runs only when started and displays charts plus a three-dimensional include graph, which shows file-inclusion relationships.

Viewing token savings, language usage, savings by tool, search counts, and relationships between included files.

It makes local indexing and token savings easier to inspect without sending data to an external service. It also provides a clear way to start and stop the dashboard.

vs-viz — Skill for Claude Code by JSungMin

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add JSungMin/vs-token-safer

Claude Code

/plugin install vs-token-safer

Made for: Claude Code.

Or install vs-token-safer, the plugin that ships this one along with the rest of its 3 skills, 6 commands, 1 agent, 1 MCP server, 1 plugin.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jsungmin/vs-token-safer/vs-viz/github.svg)](https://agentmods.dev/skills/jsungmin/vs-token-safer/vs-viz)

Your own site

<a href="https://agentmods.dev/skills/jsungmin/vs-token-safer/vs-viz"><img src="https://agentmods.dev/badge/skills/jsungmin/vs-token-safer/vs-viz/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jsungmin/vs-token-safer/vs-viz"><img src="https://agentmods.dev/badge/skills/jsungmin/vs-token-safer/vs-viz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 656 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00090	$0.00656
Opus 5	$0.00045	$0.00328
Sonnet 5	$0.00018	$0.00131
Haiku 4.5	$0.00009	$0.00066

Measured 10d ago against content hash 09d71eb49f86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vs-viz scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/vs-viz/SKILL.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vs-token-safer dashboard (`vts serve`)

A local, interactive view of what vts knows + how much it saved. Local-only and opt-in: the server binds 127.0.0.1, serves a fully self-contained page (inline CSS/JS + a locally-vendored Three.js — no CDN, no external fetch), and runs ONLY while explicitly started — the always-on MCP server never starts it. Same zero-transmission trust model as the rest of vts (localhost ≠ off-machine).

Open / close (prefer the commands)

Open: /vs-token-safer:viz — starts the server (background) + opens the browser.
Close: /vs-token-safer:viz-stop — stops it via the pidfile.

Under the hood (if running the CLI directly):

vts serve --open --projectPath <root> — start + launch browser. Run it with run_in_background: true (it's a long-running server). --port N if 8731 is busy. Falls back to node "$CLAUDE_PLUGIN_ROOT/server/cli.js" serve … when vts isn't on PATH.
vts serve --stop — shut it down. Ctrl-C also works on the foreground process.

What it shows (all from local stores — no network)

Tokens saved / ratio / $ / searches — from the savings ledger (~/.vs-token-safer/savings.json).
30-day savings trend + per-tool savings bars.
Language mix donut — file counts per backend (clangd/roslyn/tsserver/pyright) for the project.
3D include graph — nodes = files, sized + heat-colored by include fan-in (how many files include them), edges = include relationships. Drag to orbit, wheel to zoom, hover a node for its path + fan-in. Built on Three.js (WebGL); falls back to a message if WebGL is unavailable.

Notes

The graph fills in as searches run (each records into the warm-set + include-graph). Empty graph → suggest vts warmup --projectPath <root> --backend <clangd|typescript|…> or just keep using the search tools.
It's a viewer, not a data source — read actual numbers from vts savings / vts_admin {op:"savings"}.
Bounded: the graph caps at VTS_VIZ_MAX_NODES (200) highest-fan-in nodes so the WebGL sim stays smooth.

Read the full file on GitHub · 35 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 35 lines · 90 tokens per session scan A 09d71eb49f86

Subscribe to this mod's changes

vs-viz is a skill published in the GitHub repository JSungMin/vs-token-safer (11 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 656 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics C and C++C# and .NET Claude Code clangd code-search developer-tools

graph-retrieval

Exposes graph-based retrieval as a tool capability via querygraph. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.

study8677/repobrain · 46 tokens

research

Performs deep research on a topic via deepresearch. Simulates a multi-step research process and returns a comprehensive research result as a string.

study8677/repobrain · 32 tokens

clipper1

Use when maintaining legacy code that depends on Clipper 1.x API for polygon clipping and offsetting. Clipper1: the original widely-deployed polygon boolean library. Prefer Clipper2 for new projects.

znlgis/opengis-skills · 46 tokens

ygrep

IMPORTANT: Try ygrep FIRST for all code and file searches before using Grep, Glob, or Task explore. ygrep uses a pre-built full-text index and returns results in milliseconds. Fall back to built-in tools only if ygrep returns no results.

yetidevworks/ygrep · 55 tokens

aspnet-core

ASP.NET Core 8+ with controllers, services, DI, configuration, and middleware pipeline. Covers Program.cs setup and enterprise patterns. USE WHEN: user mentions "ASP.NET Core", "Web API", ".NET controllers", "Program.cs", "dependency injection", ".NET DI", ".NET configuration", "appsettings" DO NOT USE FOR: Minimal…

claude-dev-suite/claude-dev-suite · 111 tokens

aspnet-middleware

ASP.NET Core custom middleware, pipeline order, exception handling middleware, and request/response manipulation. USE WHEN: user mentions "middleware", "request pipeline", "exception middleware", "ASP.NET middleware", "UseMiddleware", "pipeline order" DO NOT USE FOR: Express middleware - use express, NestJS middleware…

claude-dev-suite/claude-dev-suite · 73 tokens