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 cardstack/boxel --skill browser-sign-ingit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/browser-sign-in)<a href="https://agentmods.dev/skills/cardstack/boxel/browser-sign-in"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/browser-sign-in/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/cardstack/boxel/browser-sign-in"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/browser-sign-in.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 | $0.00105 | $0.02245 |
| Opus 5.5 | $0.00042 | $0.00898 |
| Sonnet 5.5 | $0.00021 | $0.00449 |
| Haiku 4.5 | $0.00011 | $0.00225 |
Grade A, and why
browser-sign-in 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 5d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Signing a browser in
Wraps boxel browse, which mints a Matrix login token from a saved profile and builds a host-app URL that redeems it on load. The browser comes up signed in as that profile, optionally deep-linked to a card. It never touches the sign-in page.
When to use it
- Signing in without typing a password. The user wants to see a change, or work in the app, signed in as an account a profile already holds. This works on any host, local or deployed, whether or not its password form does.
- A host on another origin. The email/password fields are a frame from the environment's secure origin (
secure.stack.cards,secure.boxel.ai), which only listed app origins may frame; on an origin it doesn't list, the sign-in page's email/password area is blank.boxel browse --host-urlskips the form entirely. Google SSO goes through Synapse rather than the frame, so it works there too (production's Synapse shows a confirmation page before it redirects to an origin it doesn't list).- Against staging,
secure.stack.cardslists staging's host PR previews (https://*.boxel-host-preview.stack.cards) and loopback origins. Any other origin, such as a Railway deployment or a custom domain, gets a blank password area until it is added to staging's--secureOriginAppOriginby name. - Against production,
secure.boxel.ailists only loopback origins, and nothing else is ever added. A preview, a Railway deployment or a custom domain against production always signs in withboxel browse --host-urlor Google SSO. - A local host (
localhostor127.0.0.1, any port, http or https) against staging or production doesn't needbrowseto sign in: both list loopback origins, so its email/password form works. If its password area is blank anyway, follow thelocal-host-against-remoteskill in acardstack/boxelcheckout (.claude/skills/local-host-against-remote/SKILL.md), which covers the env vars that point the host at the environment and how to diagnose the frame.
- Against staging,
- Opening a card signed in. Pass the card's path on the realm server, for example
example-user/example-realm/Person/1(owner, realm, then the card), not a path inside one realm. With no card path the app opens on the workspace chooser.
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.
- 5d ago First seen · 91 lines · 105 tokens per session scan A d37ac45e22d4
browser-sign-in is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 2,245 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-21.
Other skills, from other repositories
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
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
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.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…