← ClaudeAtlas

verified-runlisted

Wrap a scheduled OpenClaw task in a RunVouch run. Reports start and end, attaches the output file as evidence, and alerts on Telegram, Slack or e-mail when the task is missed, fails, or ends without the file it was supposed to write.
runvouch/runvouch · ★ 0 · AI & Automation · score 78
Install: claude install-skill runvouch/runvouch
# verified-run Use this skill for any task that runs on a schedule (cron jobs, heartbeat tasks, nightly digests) and is supposed to produce something: a file, a reply, a row. It turns "the task ran" into "the task ran and here is the evidence", and turns silence into an alert. ## What it does 1. `POST /v1/runs/start` on RunVouch with the agent name (registers the agent on first use, with the cadence you give). 2. Runs the task: a shell command, or the steps you carry out yourself. 3. `POST /v1/runs/end` with `status` (ok or fail), the size of the evidence file and evidence checks: `{"evidence_file": true|false}`. If the file is missing or empty the run is reported as `fail` with `evidence_file: false`, and RunVouch raises FAILED. If the run does not start at all within cadence plus grace, RunVouch raises MISSED. ## Setup (once) - Get a free key at https://runvouch.com (three agents free). - Put the key in the OpenClaw environment or in `~/.openclaw/openclaw.json` under `skills.entries.verified-run.apiKey`; it is injected as `RUNVOUCH_KEY`. - Optional: `RUNVOUCH_URL` (default https://api.runvouch.com). ## How to run a task through it Shell form, the normal case. The script is in this skill folder: ``` scripts/verified-run.sh NAME --every 24h --evidence-file /path/out.md -- COMMAND ARGS... ``` Options: - `NAME`: agent name in RunVouch, one per scheduled task (for example `inbox-digest`). - `--every 15m|1h|24h`: how often the task is expected. Used at first registratio