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.
/plugin marketplace add lttr/claude-marketplace/plugin install browserWrote 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.
[](https://agentmods.dev/skills/lttr/claude-marketplace/page-bridge)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/page-bridge"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/page-bridge/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.
<a href="https://agentmods.dev/skills/lttr/claude-marketplace/page-bridge"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/page-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00064 | $0.01498 |
| Opus 5.5 | $0.00026 | $0.00599 |
| Sonnet 5.5 | $0.00013 | $0.00300 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
page-bridge 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Page bridge
A floating toolbar injected into any running dev page. The human clicks elements or types a note; the agent gets notified with the selector, computed styles, and surrounding HTML. Nothing is added to the project's source — the widget is injected over CDP and disappears on reload.
Prerequisites
The caller supplies all of these; this skill starts none of them.
| Needs | Why |
|---|---|
| Node >= 24 | Runs bridge.mjs (the sink and the driver). |
playwright-cli on PATH |
The only way the widget reaches the page — every command shells out to it. |
| A headed browser session | The human has to see the toolbar to click it. Headless is pointless here. |
| A running page URL | Passed as an argument (see below); this skill never assumes a host or port. |
| A persistent Monitor | The sink's stdout is the event stream; without one, no notifications arrive. |
jq (optional) |
Pretty-printing bridge.mjs log. |
Getting the app running and playwright-cli attached is the caller's job — a
project's own run skill, the generic run skill, or plain
playwright-cli open --headed <url>. Run the plugin preflight first,
${CLAUDE_PLUGIN_ROOT}/skills/playwright-cli/check.sh; if it fails, stop and
relay its message. bridge.mjs itself also refuses to run, with the install
command, when playwright-cli is missing.
Pieces
Both live in this skill's directory — run them via $CLAUDE_SKILL_DIR.
| File | Role |
|---|---|
bridge.mjs |
Node sink + driver: serve / open / inject / status / hide / show / log / stop |
bridge.js |
The in-page widget (shadow DOM, so it cannot collide with app styles) |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 137 lines · 64 tokens per session scan A 63933dcf300b
page-bridge is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 14d ago), licensed MIT. It adds 64 tokens to every session and 1,498 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
webui-code
Use this skill when generating or reviewing WebUI code. This skill contains knowledge on WebUI code following Chrome's Lit-element architecture and styling guidelines.
figma-to-webui
Recreate Figma design frames as production-level Chromium WebUI code following Chrome's Lit-element architecture and styling guidelines. Use when asked to create WebUI code from a Figma frame URL.
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
glassmorphism
Glassmorphism design system skill. Use when building frosted-glass UI components with blur, transparency, and layered depth effects.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
scrapling
A Python-based web-scraping workflow for fetching pages and extracting data, including pages that need JavaScript, login sessions, or protection handling. Web scraping means collecting information from websites by code.