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 t3ratech/mcp-session-bridge --skill signed-in-browsergit clone --depth 1 https://github.com/t3ratech/mcp-session-bridgeWrote 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/t3ratech/mcp-session-bridge/signed-in-browser)<a href="https://agentmods.dev/skills/t3ratech/mcp-session-bridge/signed-in-browser"><img src="https://agentmods.dev/badge/skills/t3ratech/mcp-session-bridge/signed-in-browser/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/t3ratech/mcp-session-bridge/signed-in-browser"><img src="https://agentmods.dev/badge/skills/t3ratech/mcp-session-bridge/signed-in-browser.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00109 | $0.02397 |
| Opus 5 | $0.00055 | $0.01198 |
| Sonnet 5 | $0.00022 | $0.00479 |
| Haiku 4.5 | $0.00011 | $0.00240 |
Grade A, and why
signed-in-browser 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 today.
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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in a browser the user is already signed into
Most browser automation starts from an empty profile: no cookies, no session, no access to anything behind a login. For public pages that is fine and you should keep using it.
This skill is for the other case — where the authentication is the hard part. A scripted login against SSO, MFA, a CAPTCHA or bot detection is slow to build, brittle to keep, and often against the site's terms. Attaching to a session the user already has skips all of it.
The tools come from the T3rnel Session Bridge MCP server (session_*). It is a local
stdio server; nothing is hosted and no page content leaves the machine.
Decide first: does this task actually need a real session?
| Situation | What to use |
|---|---|
| Public page, no login | An ordinary headless browser or fetch. Don't reach for this. |
| Anything behind a login | This skill. |
| A scripted login that keeps breaking | This skill — stop maintaining the login. |
| Reading a page's rendered CSS, or its React tree | This skill; static HTML won't have it. |
| Bulk scraping of a site you have no account on | Neither. That's a different problem. |
If the page is public, say so and use the simpler tool. Reaching into someone's live browser for a page you could have fetched is a cost with no benefit.
The rule that matters most
This is the user's real browser, logged into their real accounts. A wrong click here is not a failed test — it can send an email, cancel a subscription, post publicly, or move money.
- Read before you write.
session_list_tabs, thensession_snapshotorsession_read_page, before any click or fill. - Confirm anything irreversible, in your own words, before doing it: purchases, payments, sending or publishing, deleting, permission and sharing changes, anything in an account-settings or billing page. Describe the specific action and wait.
- Never enter credentials you generated. If a field is a password, an OTP, a card
number or a security answer, stop and ask.
session_store_loginexists so the user supplies these once, deliberately. - Stay on the tab you were given. Don't wander into other tabs of a signed-in browser looking for context.
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.
- today Changed · +51 lines b7cbc9cb3a47
- 4d ago Changed · +12 lines 0003eb5884e1
- 8d ago First seen · 139 lines · 109 tokens per session scan A 4525eafeef2b
signed-in-browser is a skill published in the GitHub repository t3ratech/mcp-session-bridge (2 stars, last pushed today), licensed Apache-2.0. It adds 109 tokens to every session and 2,397 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
website-explorer
Discover website capabilities from user behaviors. Learn APIs and automate workflows.
website-explorer
A guide for exploring websites through user actions, discovering their APIs, and documenting reusable automation procedures. It stores findings as structured manuals covering pages, navigation, workflows, and API endpoints.
chrome-bridge
Recipes for the user's real, logged-in Chrome through the chrome-bridge MCP tools and the zero-token chrome-bridge CLI. Use whenever the user wants to test, debug, audit, compare or automate something in a browser — a form "until the email arrives", a checkout with a test card, a pixel/GTM check, a cookie-banner…
qa-runner
Use when asked to "run QA", "qa check", "test checklist", or execute QA checklists against a running app via browser automation. Requires the browser-bridge MCP server and Chrome extension.
browse
Use when asked to interact with a web browser — navigate, click, fill forms, take screenshots, run JavaScript, or read page content. Requires the browser-bridge MCP server and Chrome extension.
melaya-setup
Use for anything involving Melaya. Connecting for the first time; setting up phone or browser control; pairing a phone, installing the app, starting the local runner; driving an Android phone or a browser; building, validating, scheduling or debugging agent pipelines; reading connected services; diagnosing a failed…