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 profilegit 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/profile)<a href="https://agentmods.dev/skills/cardstack/boxel/profile"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/profile/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/profile"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/profile.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 | $0.00045 | $0.01368 |
| Opus 5.5 | $0.00018 | $0.00547 |
| Sonnet 5.5 | $0.00009 | $0.00274 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
profile 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 yesterday.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Profiles
Wraps boxel profile, which manages credentials for different users and environments. Profiles live in ~/.boxel-cli/profiles.json (mode 0600).
When the user asks to...
| Ask | Run |
|---|---|
| "what profiles do I have?" / "who am I logged in as?" | boxel profile list |
| "log in" / "add a new account" | boxel profile add (interactive — preferred) |
| "switch to my staging account" | boxel profile switch <username-or-fragment> |
| "remove that old profile" | boxel profile remove <profile-id> |
| "import from my old .env" | boxel profile migrate |
Profile IDs
Profiles use the Matrix ID format: @username:domain.
- Production:
@username:boxel.ai - Staging:
@username:stack.cards - Local dev:
@username:<env-slug>.localhost
switch accepts a partial match — boxel profile switch sarah is enough if there's only one profile matching sarah.
Which environment a new profile targets
boxel profile add targets production. --staging and --local pick another environment instead (at most one of --production / --staging / --local); there is no environment prompt.
With -u, the Matrix ID's own domain decides — boxel.ai, stack.cards, and localhost are recognized, and any other domain needs --matrix-url and --realm-server-url.
Signing in through the browser
boxel profile add opens the browser, waits for the user to sign in there (password or Google), and then saves the profile. It waits up to 30 minutes for the browser, and the browser can only hand the sign-in to the command while it is still running.
- Run it once, in the background or with the longest timeout your shell tool allows, so the tool doesn't kill it while the user is signing in. Read its output when it exits.
- Don't re-run it while it's waiting, and don't re-run it after the user reports "You're signed in" in the browser. Each run opens another sign-in.
Profile createdin its output means it is done. If it was killed before printing that, the sign-in did not complete. - With no terminal attached, as when an agent runs it, it asks nothing after the sign-in. It saves the account the user signed in as, and replaces a profile already stored for that account (keeping its display name). It becomes the active profile only if no other profile is active; otherwise it prints the
boxel profile switchcommand to use. - Check the
Signed in asline against the account the user meant. A Google sign-in whose email matches no account creates a new one. If it isn't the account they meant, tell the user before switching to it. - If the browser wait runs out with no terminal attached, it exits with an error rather than falling back to asking for a username and password.
--no-browserdoes the same. Those sign-ins needBOXEL_PASSWORDand-u, below.
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.
- yesterday Changed 343fd23f8031
- 5d ago First seen · 103 lines · 45 tokens per session scan A 7233c196b437
profile is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,368 once invoked, about $0.0002 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.