setup-health-cron
Skill1 starsChanged 7 months agoMITView on GitHub
This skill should be used when the user asks to "setup daily health cron", "schedule mac health check", "automate daily report", "cron my mac check", or mentions scheduling the mac-guardian report. Installs a user-level launchd agent (preferred on macOS) that runs daily-health-report at a user-specified time, with cron as an optional fallback.
In this repository8 other files it gives its agents.
- bluetooth-debugSkill
- daily-health-reportSkill
- disk-usageSkill
- machine-security-checkSkill
- malware-scanSkill
- network-diagnosticsSkill
- performance-checkSkill
- wifi-debugSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Very specific: line 88
Write a JSON envelope to ~/.mac-guardian/data/setup-health-cron-<ISOdate>.json:
- Distinctive: line 108
Must prompt for confirmation before writing a launchd plist or modifying crontab.
- Very specific: line 109
Never use sudo — the agent is user-level (gui/$UID).
- Distinctive: line 110
If the plist already exists, prompt before overwriting.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
setup-health-cron
Schedules the daily-health-report skill to run automatically at a user-specified local time. Prefers launchd on macOS. Falls back to cron only when explicitly requested.
When to invoke
Trigger on phrases like: "setup daily health cron", "schedule mac health check", "automate daily report", "cron my mac check".
Inputs
- Time of day (local). Default
09:00. AcceptHH:MMin 24-hour form. - Mode:
launchd(default) orcron.
Procedure (launchd — default)
- Confirm with the user before writing anything:
"Ready to install
~/Library/LaunchAgents/com.dennisonbertram.mac-guardian.daily.plistto run daily at HH:MM. Proceed?" Abort on "no". - Resolve plugin root: prefer
${CLAUDE_PLUGIN_ROOT}. Otherwise, derive it from the current skill path. Build the plist at
~/Library/LaunchAgents/com.dennisonbertram.mac-guardian.daily.plist:<?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd"> <plist version="1.0"> <dict> <key>Label</key><string>com.dennisonbertram.mac-guardian.daily</string> <key>ProgramArguments</key> <array> <string>/bin/bash</string> <string>-lc</string> <string>PLUGIN_ROOT="<ABSOLUTE PATH>"; bash "$PLUGIN_ROOT/scripts/render.sh" && bash "$PLUGIN_ROOT/scripts/open-report.sh"</string> </array> <key>StartCalendarInterval</key> <dict> <key>Hour</key><integer>HH</integer> <key>Minute</key><integer>MM</integer> </dict> <key>StandardOutPath</key><string>/tmp/mac-guardian.daily.out.log</string> <key>StandardErrorPath</key><string>/tmp/mac-guardian.daily.err.log</string> <key>RunAtLoad</key><false/> </dict> </plist>Substitute
<ABSOLUTE PATH>,HH,MM.Houris 0–23.Minuteis 0–59.- Load it:
launchctl bootout gui/$UID ~/Library/LaunchAgents/com.dennisonbertram.mac-guardian.daily.plist 2>/dev/null || true launchctl bootstrap gui/$UID ~/Library/LaunchAgents/com.dennisonbertram.mac-guardian.daily.plist launchctl enable gui/$UID/com.dennisonbertram.mac-guardian.daily - Verify:
launchctl print gui/$UID/com.dennisonbertram.mac-guardian.daily | head -30 - Note: the launchd agent runs
render.shandopen-report.shonly. It does not re-run the collection skills automatically — collection requires Claude Code. Tell the user explicitly:"The scheduled job renders and opens a dashboard from whatever JSON has accumulated in ~/.mac-guardian/data. To refresh data, run
/mac-healthmanually." - Print the uninstall instructions:
launchctl bootout gui/$UID ~/Library/LaunchAgents/com.dennisonbertram.mac-guardian.daily.plist rm ~/Library/LaunchAgents/com.dennisonbertram.mac-guardian.daily.plist
Procedure (cron — only when asked)
- Confirm with the user before editing crontab.
- Show the line that will be appended:
MM HH * * * /bin/bash -lc 'bash "<PLUGIN_ROOT>/scripts/render.sh" && bash "<PLUGIN_ROOT>/scripts/open-report.sh"' >>/tmp/mac-guardian.cron.log 2>&1 - Append via
(crontab -l 2>/dev/null; echo "<line>") | crontab -. - Print uninstall instructions:
crontab -eand remove the line, orcrontab -l | grep -v mac-guardian | crontab -.
Output contract
Write a JSON envelope to ~/.mac-guardian/data/setup-health-cron-<ISOdate>.json:
{
"skill": "setup-health-cron",
"timestamp": "...",
"severity": "ok",
"summary": "Installed launchd agent for 09:00 daily",
"findings": [],
"raw": { "mode": "launchd", "time": "09:00", "plist_path": "/Users/.../com.dennisonbertram.mac-guardian.daily.plist" }
}Handoff
- On direct invocation, also render a mini HTML via
bash ${CLAUDE_PLUGIN_ROOT}/scripts/render-single.sh setup-health-cron.
Safety
- Must prompt for confirmation before writing a launchd plist or modifying crontab.
- Never use
sudo— the agent is user-level (gui/$UID). - If the plist already exists, prompt before overwriting.
- On any failure during bootstrap/enable, restore the previous plist (if any) and report the error.
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.

