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/padamson/playwright-rust/playwright-rs-usagenpx skills add padamson/playwright-rust --skill playwright-rs-usagegit clone --depth 1 https://github.com/padamson/playwright-rustWrote 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/padamson/playwright-rust/playwright-rs-usage)<a href="https://agentmods.dev/skills/padamson/playwright-rust/playwright-rs-usage"><img src="https://agentmods.dev/badge/skills/padamson/playwright-rust/playwright-rs-usage.svg" alt="Measured on agentmods" 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 | $0.00098 | $0.03910 |
| Opus 5 | $0.00049 | $0.01955 |
| Sonnet 5 | $0.00020 | $0.00782 |
| Haiku 4.5 | $0.00010 | $0.00391 |
Grade A, and why
playwright-rs-usage 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 4d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using playwright-rs
Rust bindings for Microsoft Playwright. This crate is a thin JSON-RPC client to the upstream Playwright server, so the API mirrors playwright-python / java / .NET semantics. When unsure about a method's behavior, the upstream Playwright docs are the authoritative reference.
Drift discipline. The canonical API tour lives in the crate-level rustdoc at https://docs.rs/playwright-rs — that's compile-checked against the actual code. This skill is the "what to reach for, what to avoid" overlay: durable conventions, not a method-by-method reference. Two build gates hold it to the crate: the Rust code block below is compiled against the real API, and every cargo feature and browser engine the crate exposes must be named somewhere in this file, so a capability cannot ship here undocumented.
Neither gate checks that this prose is accurate. That residue is real. The text is written in concepts (auto-wait, builder pattern) rather than specific method names so it ages slowly, but when it and the crate disagree, the crate wins: check https://docs.rs/playwright-rs for the version you actually have.
Before any of this works
Two things, and the second one is the one that surprises people.
The crate. playwright-rs in [dependencies], or [dev-dependencies]
if it is test-only, alongside tokio with the full feature. Defaults are
native-tls, macros and ring: transport, the locator!() macro, and
the crypto backend respectively.
Prefer leaving them on. default-features = false is only needed to swap
ring for aws-lc, and it drops all three, so the replacements have to be
listed back explicitly or locator!() disappears and no TLS transport
remains:
playwright-rs = { version = "0.17", default-features = false, features = [
"aws-lc",
"native-tls",
"macros",
] }
Two capabilities are opt-in and off unless asked for. screenshot-diff
turns on pixel-diff screenshot assertions, so reach for it when the task
calls for comparing a rendering against a baseline rather than asserting on
the DOM. cli builds an installer binary for use outside a Cargo project;
inside one, prefer the example below, because cargo install compiles a
second copy of the crate that then has to be kept in sync with the
project's lockfile.
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.
- 4d ago First seen · 330 lines · 98 tokens per session scan A ed68bb97e1e3
playwright-rs-usage is a skill published in the GitHub repository padamson/playwright-rust (141 stars, last pushed 4d ago), licensed Apache-2.0. It adds 98 tokens to every session and 3,910 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.
Other skills, from other repositories
webcmd-browser
Use when a live browser task requires Playwright interaction, authenticated handoff, visible UI verification, or ad-hoc page inspection.
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
moli-cdp-server
Start Moli's CDP server and connect Playwright, Puppeteer, or raw CDP clients. Use to run a headless-browser CDP endpoint, replace a Chromium process, attach over CDP, enable real layout and screenshot surfaces, or diagnose CDP discovery, connection, and target startup—even when Moli is not named.
opensteer
Direct browser control via CDP. Use when the user wants to automate, inspect, scrape, test, or interact with web pages.
apitap
ApiTap gives AI agents cheap access to web data through three layers.
shadow-web
Browser automation for Cursor via Shadow Web MCP and shadow-web exec: detail levels (minimal/terse/xml/full), page classifier, shadowgrep, navigate/click/fill by data-sid, SchemaSnap, diff snapshots, self-healing, Camoufox. Use when browsing the web, scraping, running shadow-web exec, compressing HTML, or when the…