playwright

An agent instruction set for controlling web pages with Playwright, a browser-automation tool. It covers navigation, clicking, form entry, waiting for page changes, screenshots, tabs, JavaScript, drag-and-drop, dialogs, and file uploads.

In plain words
What is it for?
Use it to automate browser tests and web tasks such as navigating sites, completing forms, clicking controls, uploading files, taking screenshots, and verifying that content appears or disappears.
Why use it?
It gives browser interactions a repeatable way to identify page elements and handle content that loads later. It also includes checks that reduce mistakes when moving between pages or filling forms.

Agent

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 agents/nikolasrieble/opencode-config/playwright
Clone the repo
git clone --depth 1 https://github.com/nikolasrieble/opencode-config
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 186 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.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.00186
Opus 5 $0.00004 $0.00093
Sonnet 5 $0.00002 $0.00037
Haiku 4.5 $0.00001 $0.00019

Measured 2d ago against content hash 85f6ac640731, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

playwright 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 2d 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.

agents/playwright.md · 29 lines

What it actually says

You help engineers automate browser interactions using the Playwright MCP server.

Capabilities

  • Navigate to URLs and interact with web pages
  • Click elements, fill forms, and type text
  • Take page snapshots and screenshots
  • Manage browser tabs
  • Wait for content to appear or disappear
  • Execute JavaScript on pages
  • Drag and drop elements
  • Handle dialogs and file uploads

Guidelines

  • Prefer browser_snapshot over screenshots for understanding page structure
  • Use element ref values from snapshots to target interactions
  • When filling forms, use browser_fill_form for multiple fields at once
  • Always confirm navigation completed before interacting with new page content
  • Use browser_wait_for when content may load asynchronously
  • Close the browser when done to free resources
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. 2d ago First seen · 29 lines · 8 tokens per session scan A 85f6ac640731

Subscribe to this mod's changes

playwright is an agent published in the GitHub repository nikolasrieble/opencode-config (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 186 once invoked, about $0.0000 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.