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 skills add neonwatty/playwright-profiles --skill use-profilesgit clone --depth 1 https://github.com/neonwatty/playwright-profilesWrote 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/neonwatty/playwright-profiles/use-profiles)<a href="https://agentmods.dev/skills/neonwatty/playwright-profiles/use-profiles"><img src="https://agentmods.dev/badge/skills/neonwatty/playwright-profiles/use-profiles.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 5.1 | $0.00104 | $0.01245 |
| Opus 5 | $0.00052 | $0.00622 |
| Sonnet 5 | $0.00021 | $0.00249 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
use-profiles 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Playwright Authentication Profiles
Purpose
Load saved Playwright storageState authentication profiles before browser automation work. This eliminates the need to log in manually at the start of every browser session.
When This Applies
This skill applies when ALL of the following are true:
- The current project has a
.playwright/profiles.jsonfile - Browser automation work is about to begin (using Playwright MCP tools)
- The target page requires authentication
Profile Discovery
Check for .playwright/profiles.json at the project root. Read it to discover available profiles. The file contains entries like:
{
"profiles": {
"admin": {
"loginUrl": "https://example.com/login",
"description": "Full permissions"
}
}
}
Each profile has a corresponding storageState file at .playwright/profiles/<role-name>.json.
Profile Selection
Determine which profile to use based on conversation context:
- If the user mentions a specific role (e.g., "test the admin dashboard", "check the speaker view"), match it to a profile name from the config.
- If the user does not specify a role and only one profile exists, use it automatically.
- If the user does not specify a role and multiple profiles exist, ask which one to use. Present the available profiles with their descriptions.
Loading a Profile
Before navigating to any authenticated page, load and validate the profile:
-
Verify the storageState file exists at
.playwright/profiles/<role-name>.json. If it does not exist, inform the user and suggest running/setup-profilesto create it. -
Read the storageState JSON file. It contains
cookiesandorigins(localStorage) arrays. -
Pre-load health check (RT-08): Before injecting cookies, inspect the cookie health:
- For any cookie whose value starts with
base64-(Supabase auth): decode the base64 payload (Buffer.from(value.slice(7), 'base64').toString()), parse the JSON, and checkexpires_at. Ifexpires_at < Date.now()/1000, the session is expired. - For any cookie whose value looks like a JWT (three dot-separated base64url segments): decode the middle segment, parse the JSON, and check
exp. Ifexp < Date.now()/1000, the JWT is expired. - For standard cookies: check the
expiresfield. Ifexpires > 0andexpires < Date.now()/1000, the cookie is expired. - Count session-only cookies (
expires <= 0). If >30% of cookies are session-only, note this.
- For any cookie whose value starts with
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.
- 8d ago First seen · 100 lines · 104 tokens per session scan A b351018c6e58
use-profiles is a skill published in the GitHub repository neonwatty/playwright-profiles (4 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 1,245 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…