vscode-ui

vscode-ui is a skill for Claude Code, Codex from microsoft/vscode. It costs 49 tokens per session (1,114 once invoked), scanned A, original, MIT.

Guidance for presenting numbers and comparisons as built-in visuals in an Agents window. It covers metrics, tables, bar charts, and expandable details using a special Markdown format.

In plain words
What is it for?
Use it when an answer contains metrics, before-and-after values, comparisons, tables, or bar charts. It is not intended for diagrams, mockups, or standalone documents.
Why use it?
It helps make comparisons and small sets of measurements easier to scan than plain text. The visuals are rendered by the coding environment rather than by a separate document or image.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit Use it when an answer contains metrics, before-and-after values, comparisons, tables, or bar charts. It is not intended for diagrams, mockups, or standalone documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/vscode/vscode-ui
About the project

Visual Studio Code is a code editor that supports editing, navigating, understanding, debugging, and extending software projects. Developers use it for the edit-build-debug cycle, and the catalogue add-ons provide skills, instructions, and agents for working within the editor.

microsoft/vscode · 195,658 stars · on GitHub · code.visualstudio.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add microsoft/vscode --skill vscode-ui
Clone the repo
git clone --depth 1 https://github.com/microsoft/vscode

Made for: Claude Code, Codex.

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.

agentmods badge for vscode-ui

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/vscode/vscode-ui/github.svg)](https://agentmods.dev/skills/microsoft/vscode/vscode-ui)
Your own site
<a href="https://agentmods.dev/skills/microsoft/vscode/vscode-ui"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/vscode-ui/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.

agentmods 80×15 button for vscode-ui

Your own site · 80×15
<a href="https://agentmods.dev/skills/microsoft/vscode/vscode-ui"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/vscode-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,114 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01114
Opus 5.5 $0.00020 $0.00446
Sonnet 5.5 $0.00010 $0.00223
Haiku 4.5 $0.00005 $0.00111

Measured 6d ago against content hash dec838a1abff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vscode-ui 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 6d 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.

src/vs/sessions/skills/vscode-ui/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Native visuals

Use a native visual when showing data helps the user more than describing it: a few key numbers, a before-and-after comparison, a small table, or a bar chart. VS Code renders the visual itself, so it matches the user's theme and reads as part of the answer. Keep the explanation in ordinary Markdown around it, and honor the format the user asked for; most answers need no visual.

This is on-demand authoring guidance bundled with the Agents window. It is available while native visuals and AI features are enabled. Rendering does not depend on invoking this skill.

Write a visual

Put the components in a closed Markdown code fence with the language vscode-ui. The visual appears once the closing fence arrives. Start the fence at the beginning of a line, not inside a list item or a block quote.

The incremental build is considerably faster.

```vscode-ui
<Columns>
  <Metric label="Full build" value="12.4 s" />
  <Metric label="Incremental build" value="1.8 s" delta="-85%" tone="positive" />
</Columns>
<BarChart title="Build duration" unit="s">
  <Bar label="Full build" value="12.4" />
  <Bar label="Incremental build" value="1.8" />
</BarChart>
<Disclosure summary="How this was measured">
  <Text>Median of five runs on a warm cache.</Text>
</Disclosure>
```

Most of the improvement comes from caching.

The chat.nativeComponents.enabled setting controls rendering in the Agents window and is off by default. While it is off, the block is shown as source code. Do not change the user's setting unless asked.

Components

You supply content, data, and composition. VS Code owns how every component looks, so there is nothing to style.

Component Attributes Content
Stack none Components, laid out top to bottom.
Columns none Components, laid out side by side in equal columns that stack when the chat is narrow.
Text variant: body (default), heading, or caption Plain text.
Metric label and value (required), delta, tone None.
Badge tone Plain text. Adjacent badges share a line.
Table caption Every Column, then every Row.
Column align: start (default) or end The column's header text. Use end for numbers.
Row none One Cell per column.
Cell none Plain text.
BarChart title (required), unit One Bar per value.
Bar label and value (required) None.
Disclosure summary (required) Components, hidden until the user expands them.

Read the full file on GitHub · 74 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.

  1. 6d ago First seen · 74 lines · 49 tokens per session scan A dec838a1abff

Subscribe to this mod's changes

vscode-ui is a skill published in the GitHub repository microsoft/vscode (195,658 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,114 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-14.

Related

vscode-ui compared with skills from other repositories

vscode-ui next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vscode-uimicrosoft/vscodeSkill196ktodayMITA49Claude Code, Codex
cyrene-diagramPlaya-0v0/Cyrene-AgentSkill8027d agoMITA50Claude Code, Codex
figmamereyabdenbekuly-ctrl/clodex-ideSkill87228d agoAGPL-3.0A48Claude Code, Codex
magic-uimagicuidesign/magicuiSkill23k3d agoMITA56Claude Code, Codex
winui-designmicrosoft/winappCliSkill1.4ktodayMITA70Claude Code
openscreen-designgetopenscreen/openscreenSkill7.6kyesterdayMITA62Claude Code
cyrene-obsidian-workspacePlaya-0v0/Cyrene-AgentSkill8027d agoMITA42Claude Code, Codex