schedule-polls
Skill2 starsChanged 14 days agoMITView on GitHub
Set up, check, change or remove the scheduled job that polls sg-stay-where every 2 hours without a chat session open. Use after the first poll when the user wants automatic polls, when polls look stalled, or to switch the agent that polls.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- build-searchSkill
- one-chat-many-homesSkill
- repair-readerSkill
- uninstallSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Ask before creating, changing or removing a job, and tell the user what it does: it starts their coding agent by itself, two runs per poll …
- Very specific: line 37
Stop any npm start first, then systemctl --user enable --now sg-stay-where.service.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Schedule polls
A poll started in a chat stops when the chat ends. The scheduled job runs
npm run poll (node src/cli.js poll), which starts a fresh agent each time. It survives closed
laptops, reboots and forgotten sessions, and runs a missed poll once on wake.
Ask before creating, changing or removing a job, and tell the user what it
does: it starts their coding agent by itself, two runs per poll (listing sites
and Google Maps), up to 12 polls a day, and those runs use their agent plan's
usage (README "What scheduled polls cost"). Run one poll by hand first
(npm run poll) and check its log in data/poll-logs/.
- Pick the agent:
SSW_AGENT=claude(default) orcodex. Only Claude Code's poll has its shell limited to the tracker's own CLI (docs/polling.md, "What stops a poll from sending"). - macOS:
SSW_AGENT=<agent> scripts/install-macos.sh poll(bothalso runs the server). Check it withlaunchctl print gui/$(id -u)/sg-stay-where.poll | grep -E 'state|last exit'. - Linux: first run the server as a service too; one started in a chat
stops with the chat, and every poll after that finds no tracker.
~/.config/systemd/user/sg-stay-where.service:
Stop any[Unit] Description=sg-stay-where server [Service] WorkingDirectory=<repo> ExecStart=/usr/bin/env node --no-warnings=ExperimentalWarning <repo>/src/cli.js serve Restart=on-failure [Install] WantedBy=default.targetnpm startfirst, thensystemctl --user enable --now sg-stay-where.service. Then write~/.config/systemd/user/sg-stay-where-poll.service:
and[Unit] Description=sg-stay-where poll [Service] Type=oneshot WorkingDirectory=<repo> Environment=SSW_AGENT=claude ExecStart=/usr/bin/env node --no-warnings=ExperimentalWarning <repo>/src/cli.js poll~/.config/systemd/user/sg-stay-where-poll.timer:
Then[Unit] Description=sg-stay-where poll every 2 hours [Timer] OnCalendar=0/2:00 Persistent=true [Install] WantedBy=timers.targetsystemctl --user daemon-reload && systemctl --user enable --now sg-stay-where-poll.timer, and checksystemctl --user list-timers. It runs in the user's desktop session, where Chrome is. - Windows (PowerShell):
$env:SSW_AGENT = "<agent>", thenpowershell -ExecutionPolicy Bypass -File scripts\install-windows.ps1 poll(bothalso runs the server, at sign-in, restarted if it stops). Check it withGet-ScheduledTaskInfo sg-stay-where-poll(LastRunTime,LastTaskResult). The tasks keep the agent and the Node and agent folders found at install time; re-run the installer after changing either. Tasks run only while the user is signed in, where Chrome is. - Check it in the app. The header shows "Polled 2h ago". An amber "Polls
stalled" means a job exists but nothing ran for 4 hours: look at the newest
log in
data/poll-logs/, and check the computer was on and Chrome open. - Change the agent: re-run step 2 or 4, or edit the Linux service and restart the timer.
- Remove: macOS
launchctl bootout gui/$(id -u)/sg-stay-where.pollandrm ~/Library/LaunchAgents/sg-stay-where.poll.plist; Linuxsystemctl --user disable --now sg-stay-where-poll.timerand delete the poll unit files (sg-stay-where.serviceis the server; remove it only when uninstalling); WindowsUnregister-ScheduledTask sg-stay-where-poll -Confirm:$false.
Polls on demand only: no job. The header's Poll now button starts one poll in the background; the user doesn't need a chat open.
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.

