Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add runvouch/runvouch --skill verified-rungit clone --depth 1 https://github.com/runvouch/runvouchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/runvouch/runvouch/verified-run)<a href="https://agentmods.dev/skills/runvouch/runvouch/verified-run"><img src="https://agentmods.dev/badge/skills/runvouch/runvouch/verified-run/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/runvouch/runvouch/verified-run"><img src="https://agentmods.dev/badge/skills/runvouch/runvouch/verified-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01036 |
| Opus 5.5 | $0.00023 | $0.00414 |
| Sonnet 5.5 | $0.00011 | $0.00207 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade B, and why
verified-run scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
1. Start: `curl -sS -X POST $RUNVOUCH_URL/v1/runs/start -H "X-API-Key: $RUNVOUCH_KEY" -H "Content-Type: application/json" -d '{"agent":"NAME","source":"openclaw"}'` and keep `run_id`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: {"openclaw": {"emoji": "shield", "requires": {"bins": ["curl"], "env": ["RUNVOUCH_KEY"]}, "primaryEnv": "RUNVOUCH_KEY"}} How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
POST /v1/runs/starton RunVouch with the agent name (registers the agent on first use, with the cadence you give).- Runs the task: a shell command, or the steps you carry out yourself.
POST /v1/runs/endwithstatus(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 asfailwithevidence_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.jsonunderskills.entries.verified-run.apiKey; it is injected asRUNVOUCH_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 exampleinbox-digest).--every 15m|1h|24h: how often the task is expected. Used at first registration.--grace 5m: how late a run may be before MISSED (default 15m).--evidence-file PATH: the file the task must write. Missing or zero bytes means failure.--cost USD: what the task cost, if known; enables the daily cap.--source openclaw: shown in the dashboard (default openclaw).
Exit code is the task's exit code, so cron and OpenClaw see the real result.
Example for an OpenClaw cron task that writes a digest:
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
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 67 lines · 57 tokens per session scan B 04514e116608
verified-run is a skill published in the GitHub repository runvouch/runvouch (0 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 1,036 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
flutter-mcp-toolkit-control
Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.
flutter-mcp-e2e-harness
Use this skill when writing or running repeatable E2E scenarios for Flutter apps as checked-in Dart with the fluttermcpharness package (packages/harness) — build/launch the app, attach to its VM service, drive widgets (snapshot/tap/enter text) and assert without MCP; also covers the repo showcase launcher (make…
harness-engineering-lifecycle
Design, implement, and integrate generalized validation harnesses across a producer-consumer boundary after a local harness contract exists. Use when refactoring custom validation CLIs/MCPs for large polyrepos, extending Steward across sibling repos, or deploying a local tool to a consumer project for dogfooding and…
opik-test
Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the compare skill. Works over the SDK; uses the MCP write tool when connected. Returns the suite, the item, and the assertion.…
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.