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-auth-browsegit 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-auth-browse)<a href="https://agentmods.dev/commands/neonwatty/playwright-profiles/setup-auth-browse"><img src="https://agentmods.dev/badge/commands/neonwatty/playwright-profiles/setup-auth-browse.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 | $0.00017 | $0.00657 |
| Opus 5 | $0.00009 | $0.00329 |
| Sonnet 5 | $0.00003 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
setup-auth-browse 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 6d 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.
Setup Authenticated Browsing
Set up the auth-browse system for persistent authenticated browsing of external services using playwright-cli with real Chrome.
Step 1: Check Prerequisites
Verify that playwright-cli is available:
which playwright-cli
If not found, inform the user they need playwright-cli installed. It is typically installed as a global npm package or via a Claude Code plugin.
Step 2: Install the Sign-In Script
Check if ~/.playwright-cli/sign-in.mjs already exists.
If it exists: Ask whether to update it with the latest version from this plugin.
If it does not exist: Copy the bundled script. Find the plugin's script path using Glob:
**/skills/auth-browse/scripts/sign-in.mjs
Then:
mkdir -p ~/.playwright-cli
cp <found-path> ~/.playwright-cli/sign-in.mjs
Also copy the cookie analysis module that sign-in.mjs depends on:
cp <found-path-directory>/cookie-analysis.mjs ~/.playwright-cli/cookie-analysis.mjs
Where <found-path-directory> is the same directory as sign-in.mjs. Use Glob to find it:
**/skills/auth-browse/scripts/cookie-analysis.mjs
Step 3: Install Playwright Dependency
Check if ~/.playwright-cli/node_modules/playwright exists.
If it exists: Skip this step.
If not:
cd ~/.playwright-cli && npm init -y 2>/dev/null; npm install playwright
Step 4: Verify
Run the script to confirm it works:
node ~/.playwright-cli/sign-in.mjs list
This should print the list of available site shortcuts.
Step 5: Initial Sign-Ins
Ask the user which services they want to sign into. Present the available sites from the list output.
For each chosen site, instruct the user to run the following command in a separate terminal:
node ~/.playwright-cli/sign-in.mjs login <site>
This is interactive — Claude cannot run it. The user signs in manually in the browser window. The script auto-detects completion and saves auth state.
After each sign-in, verify the saved state:
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.
- 6d ago First seen · 100 lines · 17 tokens per session scan A 374594ec1dc8
setup-auth-browse is a command published in the GitHub repository neonwatty/playwright-profiles (4 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 657 once invoked, about $0.0001 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 commands, from other repositories
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
ccboard-web
Launch ccboard web interface.
can-i-use
Check browser support for web platform features against the project's browser targets.
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.
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.