uninstall
Skill2 starsChanged 14 days agoMITView on GitHub
Shut sg-stay-where down and remove it from the user's machine: background services, scheduled polls, the WhatsApp link and session, remote access, data and the repo. Use when the user wants to stop using it, start over, or clean up.
- Deletes or force-pushes
17 other projects use a version of this.
Adopted by
Most recently taken up by
- FYClamityDestiny/vettedtheir own version, first seen Nov 15, 2026
- Dariusplayer09/adaptive-skillstheir own version, first seen Nov 8, 2026
- sachingulati/claude-statuslinetheir own version, first seen Nov 1, 2026
- talal-ai/handoff-nowtheir own version, first seen Oct 20, 2026
- pushprove-max/Commandecktheir own version, first seen Oct 17, 2026
- zoo3323/usage-statuslinetheir own version, first seen Oct 15, 2026
Used with
Projects with it also use doctor, config and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkilldoctor
Diagnose an Amplifier CLI environment through the CLI doctor agent. USE WHEN a user requests CLI runtime, settings or missing-capability inspection. DO NOT USE for project bugs or other hosts.
Also in 6 projects that use this
MicrosoftSkillconfig
Show or change TokenEconomizer's settings: turn micro-skills, tool pruning or the loop guard on or off, or tune them, for this repository or (with --global) every repository. Use when the user asks to configure, enable or disable TokenEconomizer or one of its mechanisms.
Also in 3 projects that use this
VercelSkillsetup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
Also in 7 projects that use this
- +1 more from microsoft
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- anthropics/claude-for-legal★ 9.5ksame name
- openclaw/openclaw-windows-node★ 2.2ksame name
- shanselman/openclaw-windows-hub★ 2.2ksame name
- tmck-code/yet-another-statusline★ 244same name
- tanerincode/jedi-statusline★ 18same name
- joris887/exosuit★ 9same name
- HAX-Studio/mnemonica★ 3same name
- pushprove-max/Commandeck★ 3same name
- sachingulati/claude-statusline★ 2same name
- yang1997434/claude-code-hud★ 2same name
7 more not listed
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.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- build-searchSkill
- one-chat-many-homesSkill
- repair-readerSkill
- schedule-pollsSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Ask what the user wants removed and confirm each deletion before running it.
- Very specific: line 21
Stop any npm start still running.
- Very specific: line 27
Remote access: If they set up Tailscale for their phone: tailscale serve status, then tailscale serve --https=8431 off (or the port it …
- Distinctive: line 31
Browser and agents: Remove the bookmarklet if they added one, and any browser tool they configured only for polls.
“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Shut down and remove
Ask what the user wants removed and confirm each deletion before running it. Nothing here can be undone without a backup.
- Backup, if they want one.
data/holds projects, listings, chats and photos:cp -R data ~/sg-stay-where-backup-$(date +%Y%m%d). Tell them it contains private chats. - Stop polls and the server.
- macOS:
launchctl bootout gui/$(id -u)/sg-stay-where.poll,launchctl bootout gui/$(id -u)/sg-stay-where.server, thenrm ~/Library/LaunchAgents/sg-stay-where.*.plist. - Linux:
systemctl --user disable --now sg-stay-where-poll.timer sg-stay-where.service, then delete those unit files in~/.config/systemd/user/(or remove a cron line). - Windows:
Unregister-ScheduledTask sg-stay-where-poll, sg-stay-where-server -Confirm:$false. - Stop any
npm startstill running.
- macOS:
- Unlink WhatsApp. The user does this on their phone: WhatsApp → Settings → Linked devices → the sg-stay-where device → Log out.
- Delete the WhatsApp session. The user runs this themselves; agents never
open or touch that folder:
rm -rf ~/.config/sg-stay-where/, plus the folder inSSW_WA_AUTH_DIRif they set one. - Remote access. If they set up Tailscale for their phone:
tailscale serve status, thentailscale serve --https=8431 off(or the port it shows). - Delete the data.
rm -rf data data-demo. - Browser and agents. Remove the bookmarklet if they added one, and any browser tool they configured only for polls. Chrome itself stays.
- Delete the repo last, from outside it:
rm -rf <path>/sg-stay-where. The user runs this if you are working inside the folder. - Report what was removed, what is left, and where the backup is.
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.

