Docs › OpenClaw scheduled task monitoring with RunVouch
OpenClaw scheduled task monitoring with RunVouch
OpenClaw tasks on a schedule are agents talking to themselves at 7 in the morning: nobody is watching when the task does not start, or starts and writes nothing. The verified-run skill turns each task into a run with a start, an end and a file that proves the work.
How it runs on OpenClaw (verified-run skill)
Copy integrations/openclaw/verified-run (and optionally runvouch, the check-in skill for long sessions) into ~/.openclaw/skills/, or load the folder as a plugin via its openclaw.plugin.json. The skill ships scripts/verified-run.sh for cron and instructions the agent follows when it does the task itself. Source and README: integrations/openclaw.
Store the key
RUNVOUCH_KEY in the OpenClaw environment, or skills.entries.verified-run.apiKey in openclaw.json; the skill stays hidden until the key is there.
Wrap the job
# crontab on the OpenClaw host 0 7 * * * ~/.openclaw/skills/verified-run/scripts/verified-run.sh inbox-digest --every 24h --grace 30m --evidence-file ~/out/digest.md -- openclaw task run inbox-digest # the same wrapper with the rv CLI, if installed 0 7 * * * rv run inbox-digest --evidence-file ~/out/digest.md -- openclaw task run inbox-digest
rv fails open: if RunVouch is unreachable the job still runs and you get one warning line.
Register the cadence and caps
rv agent nightly-report --cadence 24h --grace 30m --max-runtime 1h --evidence --cap-run-cost 2
Register the agent once, from anywhere with the key. Cadence is what turns a schedule that stopped into an alert; --evidence makes a run without evidence a failure; the caps pause the agent when it overspends.
What goes silent on OpenClaw (verified-run skill)
- The gateway is down at 7:00: no start call, MISSED at 7:30.
- The task exits 0 without writing the digest: the wrapper reports
failwithevidence_file: false; yesterday's file is removed first so it cannot pass as today's. - The agent loops on the same tool call: the companion
runvouchskill reports tool calls, RETRY_STORM stops it.
What OpenClaw (verified-run skill) does not tell you
OpenClaw runs scheduled tasks and keeps a session log, but it has no notion of an expected run: a task that never starts leaves no trace, and a task that starts, calls no tools and writes no file finishes as a normal session. OpenClaw issue #16808 (a polling loop that cost $150 with no alert) is the documented case.
What RunVouch detects
| Alert | What it means here |
|---|---|
| MISSED | cadence plus grace passed and no run started |
| FAILED | non-zero exit or a reported failure, with the stderr excerpt |
| NO_EVIDENCE | the run said ok but the file, URL or assertion you required is missing |
| STALLED | a run started and never ended within max runtime |
| RETRY_STORM | the same tool called with identical input many times in one run |
| BUDGET_RUN / BUDGET_DAY | cost cap crossed; the agent is paused until you resume it |
| DRIFT | duration or output size far off its 7-run baseline |
Set up in two minutes
- Get a free key (3 agents, no card) and store it where this page says.
- wrap the job: copy the snippet above into the scheduled job.
- Register the cadence once:
rv agent nightly-report --cadence 24h --grace 30m --evidence, or let the first run create the agent and set the cadence on the dashboard. - Send one test alert:
curl -X POST https://api.runvouch.com/v1/settings/test-alert -H "X-API-Key: $RUNVOUCH_KEY". The next missed, failed or empty run reaches the same channels.
Need a key? Get a free key · Stuck? contact