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 huaweicloud/huaweicloud-skills --skill huawei-cloud-cdn-universal-querygit clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsWrote 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/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-universal-query)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-universal-query"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-universal-query/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/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-universal-query"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cdn-universal-query.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 | $0.00350 | $0.09456 |
| Opus 5.5 | $0.00140 | $0.03782 |
| Sonnet 5.5 | $0.00070 | $0.01891 |
| Haiku 4.5 | $0.00035 | $0.00946 |
Grade B, and why
huawei-cloud-cdn-universal-query scanned grade B with 1 finding 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 28d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
> 1. **Stop immediately** - Do not execute any commands How it starts
The opening of the file, as written. The whole thing — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CDN Query Reference
Overview
This skill is a comprehensive reference for all 44 GET read-only CDN APIs available via hcloud CLI. It serves as a fallback skill for agents to look up the correct command syntax, required parameters, and known pitfalls when querying any CDN information.
Key Features:
- Complete coverage of 44 GET CDN APIs (all validated end-to-end)
- Organized by 4 functional categories: Domain Management (14), Statistics & Analytics (12), Refresh/Log/Export (8), Template/Rule/Tag/Account (10)
- Command templates with parameter guidance
- 12 validated pitfalls and troubleshooting notes
- Test domain references for validation
- Explicit declaration of all 55 prohibited non-GET operations (see references/prohibited-operations.md)
Tool: hcloud CLI (KooCLI v7.2.12)
Scope: Read-only GET operations only
Region: Recommended to use --cli-region=<region> for CDN APIs
Triggers
Chinese triggers: CDN查询, CDN接口, CDN CLI, 域名查询, 域名配置, 流量统计, 带宽查询, 刷新预热, 日志下载, 证书查询, 回源配置, 缓存规则, 域名归属 English triggers: CDN query, CDN API reference, CDN CLI usage, domain config, traffic statistics, bandwidth query, refresh preheat, log download, certificate query, origin config
Example user phrases (中/EN):
- "查一下我这个域名的 CDN 配置" / "Check the CDN configuration of my domain"
- "看看昨天域名的流量和带宽" / "Show yesterday's traffic and bandwidth"
- "刷新预热任务的历史记录" / "List refresh/preheat task history"
- "帮我下载 CDN 日志 / 导出统计报表" / "Download CDN logs or export statistics"
- "这个 IP 是不是华为云 CDN 的节点" / "Check if this IP belongs to Huawei Cloud CDN"
- "查一下账户的 CDN 配额" / "Query the CDN account quota"
Near-miss / Do NOT Use
Fallback skill: this is a read-only CDN query reference — prefer a dedicated
skill when one covers the scenario (cdn-traffic-anomaly-analysis,
cdn-502-troubleshooting, or any other applicable CDN skill).
Do NOT use for:
| Scenario | Action |
|---|---|
| Create/modify/delete CDN resources (POST/PUT/DELETE) | Refuse — strictly read-only (see references/prohibited-operations.md) |
| Non-CDN Huawei Cloud queries (ECS, OBS, VPC, etc.) | Use the corresponding service skill |
| CDN console operations / account management | Direct the user to the Huawei Cloud CDN console |
| Queries beyond read-only reference | Out of scope; query reference only |
What ships with it
19 files 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.
- .markdownlint.json 359 B
- references/acceptance-criteria.md 4.1 KB
- references/api-domain-management.md 5.7 KB
- references/api-refresh-log-export.md 7.1 KB
- references/api-statistics.md 8.5 KB
- references/api-template-rule-tag-account.md 4.2 KB
- references/cli-installation-guide.md 659 B
- references/dataflow-diagram.md 4.0 KB
- references/iam-policies.md 2.0 KB
- references/prohibited-operations.md 6.6 KB
- references/task-timestamp-calculation.md 1.4 KB
- references/troubleshooting.md 9.9 KB
- references/verification-method.md 3.0 KB
- references/workflow-domain-config.md 2.4 KB
- references/workflow-domain-diagnosis.md 4.7 KB
- references/workflow-logs-reports.md 5.5 KB
- references/workflow-traffic-drilldown.md 6.1 KB
- references/workflow-traffic-stats.md 4.1 KB
- scripts/cdn_timestamp.py 3.1 KB runs code
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.
- 28d ago First seen · 588 lines · 350 tokens per session scan B 4ef3b6b4f431
huawei-cloud-cdn-universal-query is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 350 tokens to every session and 9,456 once invoked, about $0.0014 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-30.
Other skills, from other repositories
improve-rule
Use when reviewing or improving a Front-End Checklist rule MDX file to raise its quality score, fix stub prompts, add missing fields, or enrich content with real code examples.
find-npm-packages
Use when you need to find the 2-3 most popular and well-maintained npm packages relevant to a frontend checklist rule, validate they meet quality thresholds, and add them to the rule's frontmatter.
geo-meta
Use when auditing locally-focused or regionally-targeted pages for geo targeting signals, particularly on sites targeting audiences through Bing or regional search engines. Note that these meta tags have no documented effect on Google's ranking.
aria-input-field-name
Use when applies to all (except type=hidden), , , and custom form widgets using role=textbox, role=combobox, role=spinbutton, role=searchbox, or role=listbox.
broken-images
Use when reviewing image assets, markup, and CDN or build transforms related to Fix broken images. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.
color-contrast
Use when applies to all visible text and text images, UI component borders (input fields, buttons), focus indicators, icons that convey meaning, and graphical objects required to understand content. Does not apply to inactive/disabled UI components or purely decorative elements.