Google AI Usage Monitor

PassAudited by ClawScan on May 10, 2026.

Overview

This instruction-only skill is coherent for monitoring Google AI usage, but users should be aware it can rely on a logged-in Google browser session, send usage details to Discord, and create recurring checks if configured.

Before enabling this skill, confirm the Google project ID, use the intended logged-in Google account, choose a private Discord channel, and review any cron or HEARTBEAT entries so the monitor does not keep posting longer than you expect.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The agent may view Google AI project usage, quota, tier, and model-limit information for the selected project.

Why it was flagged

The skill expects use of an OpenClaw browser profile to access a Google AI Studio usage page, likely relying on the user's logged-in Google session.

Skill content
browser action=open targetUrl="https://aistudio.google.com/usage?project=YOUR_PROJECT_ID&timeRange=last-28-days&tab=rate-limit" profile=openclaw
Recommendation

Use a dedicated or least-privileged browser profile/account where possible, and confirm the project ID before running the workflow.

What this means

Project names, billing tier, usage levels, and quota warnings could be visible to anyone with access to the configured Discord channel.

Why it was flagged

The skill describes sending monitoring reports and alerts to a Discord channel, moving Google AI usage details into a separate communication service.

Skill content
"delivery": { "mode": "announce", "channel": "discord", "to": "CHANNEL_ID" }
Recommendation

Send reports only to a private, intended channel and avoid including sensitive project identifiers if the channel has broad membership.

What this means

Once configured, the monitor may continue running daily and posting reports until the schedule is changed or removed.

Why it was flagged

The provided cron example would create a recurring autonomous check and Discord report if the user installs that schedule.

Skill content
"schedule": { "kind": "cron", "expr": "0 20 * * *", "tz": "Asia/Shanghai" }, "payload": { "kind": "agentTurn", "message": "检查 Google AI Studio 用量并发送报告到指定 Discord 频道" }
Recommendation

Review the schedule, destination channel, and expected report contents before enabling the cron job, and document how to disable it.

What this means

Persistent context may cause future agent sessions to remember and reuse the monitoring configuration.

Why it was flagged

The skill recommends storing project/channel configuration and recurring behavior in persistent OpenClaw context files.

Skill content
Add to `TOOLS.md`: ... "Project ID": gen-lang-client-XXXXXXXXXX ... "Discord Channel": #google-ai (CHANNEL_ID) ... Add to `HEARTBEAT.md`: "Check usage if last check > 24 hours"
Recommendation

Store only non-secret configuration in these files and periodically review persistent notes for outdated project IDs, channels, or monitoring instructions.