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 MSApps-Mobile/claude-plugins --skill gcloud-cli-health-checkgit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote 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/msapps-mobile/claude-plugins/gcloud-cli-health-check)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/gcloud-cli-health-check"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/gcloud-cli-health-check/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/msapps-mobile/claude-plugins/gcloud-cli-health-check"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/gcloud-cli-health-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 6 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 26 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00175 | $0.02490 |
| Opus 5.5 | $0.00070 | $0.00996 |
| Sonnet 5.5 | $0.00035 | $0.00498 |
| Haiku 4.5 | $0.00017 | $0.00249 |
Grade A, and why
gcloud-cli-health-check scanned grade A with 0 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 2mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill may run in an automated/scheduled context with no user present. Execute all steps autonomously without asking clarifying questions. For write actions (send, post, create, update, delete), only take them if explicitly requested. When in doubt, produce a report of what you found.
Critical: Use Desktop Commander — Not the Bash Tool
All gcloud commands MUST run via mcp__Desktop_Commander__start_process. The Bash tool runs in a sandboxed Linux environment where gcloud is not installed AND the sandbox proxy returns 403 blocked-by-allowlist for every Google endpoint (dl.google.com, sdk.cloud.google.com, oauth2.googleapis.com, www.googleapis.com, accounts.google.com). The user's Mac has Google Cloud SDK installed at /opt/homebrew/bin/gcloud with auth already configured.
✅ mcp__Desktop_Commander__start_process → runs on user's Mac → gcloud found, auth available
❌ Bash tool → runs in Linux sandbox → gcloud not found, Google blocked
If Desktop Commander is unavailable, do NOT try to install gcloud in the sandbox — it is impossible (no network access to Google, no sudo). Write a report documenting the block and stop.
Expected State
| Thing | Expected value |
|---|---|
| gcloud binary | /opt/homebrew/bin/gcloud (macOS, Homebrew) |
| Active account | [email protected] (primary) |
| Active project | opsagent-prod (project# 523955774086, display: "OpsAgent Production") |
| Compute region | me-west1 (Israeli prod) |
| Secondary project | socialjetopsagent — accessed as [email protected], michal has no IAM on it |
Legacy project (informational, not a failure): opsagent-491114 exists on a different Google account ([email protected] / AI Studio auto-created) and returns PERMISSION_DENIED when queried as michal. Do NOT include it in the primary sweep.
Step 1 — Verify gcloud is installed
/opt/homebrew/bin/gcloud --version
Fall back to gcloud --version if the explicit path is missing. If both fail → mark Installation ❌ and stop.
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.
- 2mo ago First seen · 224 lines · 175 tokens per session scan A e02cce9a4296
gcloud-cli-health-check is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (11 stars, last pushed today), licensed MIT. It adds 175 tokens to every session and 2,490 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
gcloud-cli-health-check compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gcloud-cli-health-checkMSApps-Mobile/claude-plugins | Skill | 11 | today | MIT | A | 175 | Claude Code |
| azure-mcp-connectionWYRE-AI/msp-claude-plugins | Skill | 52 | today | Apache-2.0 | A | 68 | Claude Code |
| azure-mcp-observabilityWYRE-AI/msp-claude-plugins | Skill | 52 | today | Apache-2.0 | A | 66 | Claude Code |
| Axcient ClientsWYRE-AI/msp-claude-plugins | Skill | 52 | today | Apache-2.0 | A | 50 | Claude Code |
| Axcient JobsWYRE-AI/msp-claude-plugins | Skill | 52 | today | Apache-2.0 | A | 42 | Claude Code |
| Axcient VaultsWYRE-AI/msp-claude-plugins | Skill | 52 | today | Apache-2.0 | A | 56 | Claude Code |
| rented-server-setupnaveedharri/benai-skills | Skill | 80 | 1mo ago | MIT | A | 258 | Claude Code |