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.
npx agentmods add skills/microsoft/vscode/integrated-browsernpx skills add microsoft/vscode --skill integrated-browsergit clone --depth 1 https://github.com/microsoft/vscodeWhat 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 | $0.00068 | $0.02616 |
| Opus 5 | $0.00034 | $0.01308 |
| Sonnet 5 | $0.00014 | $0.00523 |
| Haiku 4.5 | $0.00007 | $0.00262 |
Grade A, and why
integrated-browser 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrated Browser Architecture
The integrated browser ("browserView") embeds a real Chromium browser in VS Code, backed by an Electron WebContentsView. It renders live pages, presents each as an editor tab, and lets agents drive those pages through tools. It powers the in-product browser tab and the agent "browser" tools. It is not the old extensions/simple-browser (an iframe-in-a-webview), which now delegates to this on desktop.
It's a heavyweight, security-sensitive, multi-process primitive, and almost every design decision follows from that. This file describes the load-bearing ideas that rarely change. It deliberately does not enumerate current features/tools/commands/settings — those churn; the live features/ and tools/ folders are the source of truth. Build the mental model here, then go read the specific code you're changing.
The one idea everything follows from
A page is a native WebContentsView that only the main process may create, own, and position. Nothing else can touch it directly. It's owned by the main process and painted by the OS compositor on top of the workbench DOM — not inside it. Everything else works around this:
- The renderer (editor UI + agent tools) can't hold the page; it holds a model/proxy and talks to main over IPC.
- Playwright is heavy and long-lived, so it runs in the shared process, reaching the page over IPC too.
- The page paints over the DOM, so the workbench choreographs alignment, z-order, focus, and screenshots by hand.
Three processes, and why
| Process | Location | What lives here |
|---|---|---|
| Main | platform/browserView/electron-main |
The WebContentsView, sessions, trust, permissions, history, CDP, screenshots — authoritative page state. Only main can create native views. |
| Shared | platform/browserView/node |
Playwright + remote/group automation services. Keeps a heavy dependency out of main (stability) and renderer (lifecycle). |
| Renderer | workbench/contrib/browserView + platform/browserView/electron-browser |
Editor pane, UI feature contributions, agent tools, page preload script. Holds only lightweight proxies. |
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.
- yesterday First seen · 100 lines · 68 tokens per session scan A c25527302196
integrated-browser is a skill published in the GitHub repository microsoft/vscode (190,061 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 2,616 once invoked, about $0.0003 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.
Other skills, from other repositories
supersplat
Use when editing 3D Gaussian Splatting (3DGS) .ply models in browser — cleanup noise/floaters, crop, transform, color-adjust, animate camera, publish online. SuperSplat: open-source browser-based 3DGS editor by PlayCanvas with PLY/compressed PLY/Splat/KSplat/SOG export.
create-remotion-video
Create or edit video with Remotion. First-party clodex + Remotion skill. Contains full video-making process.
github
Complete guide for the GitHub plugin — REST API access for repositories, issues, pull requests, actions, releases, and search using a GitHub Personal Access Token.
posthog
Complete guide for the PostHog plugin — REST API access for querying analytics with HogQL, managing feature flags, inspecting events and persons, reading insights, experiments, cohorts, surveys, and more.
supabase
Complete guide for the Supabase plugin — Management API access for running SQL queries, listing projects, managing edge functions, secrets, migrations, and inspecting project health.
figma
Complete guide for the Figma plugin — REST API access, real-time selection monitoring via CDP, and the figma-app interactive UI. Read this IMMEDIATELY when the user asks to work with Figma.