webview-ui

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.

agentmods

npx agentmods add skills/generous-corp/pulp/webview-ui

Any agent

npx skills add Generous-Corp/pulp --skill webview-ui

Clone the repo

git clone --depth 1 https://github.com/Generous-Corp/pulp

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/generous-corp/pulp/webview-ui.svg)](https://agentmods.dev/skills/generous-corp/pulp/webview-ui)

Your own site

<a href="https://agentmods.dev/skills/generous-corp/pulp/webview-ui"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/webview-ui.svg" alt="Measured on agentmods" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,462 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00035	$0.03462
Opus 5	$0.00017	$0.01731
Sonnet 5	$0.00007	$0.00692
Haiku 4.5	$0.00003	$0.00346

Measured today against content hash 5e9ced388378, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

webview-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 today.

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.

.agents/skills/webview-ui/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WebView UI

Use this skill when working on Pulp's optional WebView layer: HTML/JS panels, Monaco-style tools, documentation views, or mixed native/WebView windows.

Core Positioning

Pulp WebView is an opt-in compatibility layer, not the primary UI path. Default to native Pulp UI unless the task truly benefits from existing web content.

Core Runtime Pieces

Main APIs:

pulp::view::WebViewPanel
pulp::view::WebViewOptions
pulp::view::WindowHost
pulp::view::AssetManager

Bridge contract:

window.pulp.postMessage(type, payload, id)
window.pulp.on(type, callback)
native set_message_handler(...)
native post_message(...)
async evaluate_js(..., callback)

Platform Truth

PULP_BUILD_WEBVIEW=ON is now the honest opt-in switch for the common Pulp WebView layer on:

macOS via WebKit
Windows via CHOC's WebView2 path
Ubuntu/Linux via CHOC's GTK/WebKitGTK path

Required platform notes:

macOS: no extra package discovery beyond the system WebKit framework
Windows: normal Visual Studio/CMake toolchain plus a WebView2-capable runtime
Linux: gtk+-3.0 and webkit2gtk-4.1 available through pkg-config

Keep claims narrow:

macOS has the deepest runtime proof today, including Monaco in a native host
Windows and Ubuntu now have truthful opt-in configure/build/test proof plus pulp-webview-palette build proof
do not describe that as full runtime parity unless the host-level proof is actually there

File drag-and-drop (from `choc::ui::WebView`)

CHOC's WebView layer carries file drag-and-drop, exposed to page JS — no Pulp C++ wiring needed, it rides the choc/gui/choc_WebView.h we already wrap in core/view/src/web_view.cpp:

Drag a file OUT of the webview: call window.chocStartFileDrag(["/abs/path", ...]) from a pointerdown/mousedown handler.
Drop files INTO the webview: listen for the chocfilesdropped event; e.detail.paths is the array of absolute paths.

Platform reality: macOS (WKWebView) + Linux (WebKitGTK) — both directions. Windows (WebView2) — inbound only (outbound is a documented no-op: windowed WebView2 can't start a drag from web content without moving to composition hosting). The JS call exists on all platforms for parity.

Read the full file on GitHub · 284 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.

today First seen · 284 lines · 35 tokens per session scan A 5e9ced388378

Subscribe to this mod's changes

webview-ui is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 3,462 once invoked, about $0.0002 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 2026-09-04.

Frontend Hardware and IoT

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

hsb-flash

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…

NVIDIA/skills · 94 tokens