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 commands/neonwatty/playwright-profiles/setup-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/commands/neonwatty/playwright-profiles/setup-profiles)<a href="https://agentmods.dev/commands/neonwatty/playwright-profiles/setup-profiles"><img src="https://agentmods.dev/badge/commands/neonwatty/playwright-profiles/setup-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 | $0.00011 | $0.01194 |
| Opus 5 | $0.00005 | $0.00597 |
| Sonnet 5 | $0.00002 | $0.00239 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade B, and why
setup-profiles scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Verify that a Playwright MCP server is configured. Check the project's `.mcp.json` and the user's global MCP config (`~/.claude/settings.json`) for a Playwright MCP server entry. How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Playwright Authentication Profiles
Set up persistent Playwright storageState authentication profiles for the current project. This enables authenticated browser automation without logging in every session.
Step 1: Check MCP Configuration
Verify that a Playwright MCP server is configured. Check the project's .mcp.json and the user's global MCP config (~/.claude/settings.json) for a Playwright MCP server entry.
If no Playwright MCP server is configured, guide the user to add one:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@playwright/mcp@latest"]
}
}
}
The Playwright MCP server runs in headed mode by default, which is required for the interactive login flow.
Step 2: Check for Existing Profiles
Check if .playwright/profiles.json already exists in the project root.
If it exists: Read it and present the existing profiles to the user. Ask whether they want to:
- Refresh specific existing profiles (ask which ones)
- Add new profiles
- Refresh all profiles
Then skip to the appropriate step below.
If it does not exist: Proceed to Step 3 for fresh setup.
Step 3: Define Profiles
Ask the user the following questions, one at a time:
- What user roles/profiles do you need? (e.g., "admin, planner, speaker" or just "user")
- What is the login URL? Ask per-profile if they might differ, but often all roles share the same login page.
- Optional: brief description for each role (e.g., "Full admin permissions" or "Can only view assigned decks"). If the user skips this, generate reasonable descriptions based on the role names.
For projects spanning multiple apps, suggest using descriptive prefixed names (e.g., admin-panel-admin, storefront-buyer).
Step 4: Write Configuration
Create the directory structure:
.playwright/
profiles.json
profiles/
Write .playwright/profiles.json with the profile definitions. Format:
{
"profiles": {
"role-name": {
"loginUrl": "https://example.com/login",
"description": "Role description"
}
}
}
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.
- 3d ago First seen · 140 lines · 11 tokens per session scan B 8ece3e2e483a
setup-profiles is a command published in the GitHub repository neonwatty/playwright-profiles (4 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 1,194 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
open
SoDam-Design-Kit open 대시보드 — 검증 이력·판정서·스크린샷을 브라우저로 열람 + 재검증.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
verify-pr
Verify a PR's frontend changes through browser automation.
gh-issue-use-cypress
Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.