loom-auth
Skill1 starsChanged 4 months agoMITView on GitHub
Mint or refresh the authenticated Loom session by opening a real browser for Google SSO. Run when the Loom session is missing or expired.
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- cosmix/loomtheir own version, first seen Oct 22, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- cosmix/loom★ 64same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
Refresh the Loom session. Google blocks automated sign-in, so this opens a real browser; the user completes Google SSO and the script detects completion and saves the session automatically. No terminal interaction is required, so run it directly and wait for it to exit (it blocks until sign-in completes or times out):
cd "${CLAUDE_PLUGIN_ROOT}" && npx tsx --env-file-if-exists=.env scripts/login.tsWhile it runs, tell the user to complete the Google sign-in in the opened browser window. The
script saves the session as soon as it detects a signed-in Loom page (the connect.sid cookie on
an authenticated page); the user does not press anything in the terminal. Default timeout is 5
minutes (override with LOGIN_TIMEOUT_MS); on timeout, re-run.
On startup it also migrates any existing session from the legacy location into the stable data
dir. Afterward, confirm with /loom-daddy:status. The saved session is a credential, stored
locally and never committed.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.