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-cce-metric-analyzergit 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-cce-metric-analyzer)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cce-metric-analyzer"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cce-metric-analyzer/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-cce-metric-analyzer"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cce-metric-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 105 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.
- high Privilege Escalation · line 229 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 99 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 | $0.00293 | $0.07401 |
| Opus 5 | $0.00147 | $0.03700 |
| Sonnet 5 | $0.00059 | $0.01480 |
| Haiku 4.5 | $0.00029 | $0.00740 |
Grade A, and why
huawei-cloud-cce-metric-analyzer scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> **Execution method**: Cloud service queries are executed through the local `hcloud` CLI. AOM Prometheus `query_range` calls are the only exception and use signed HTTPS requests because the required Prometheus range-que How it starts
The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud CCE Metric Analyzer
Overview
Query and analyze metrics for CCE clusters (Pod/Node CPU/memory/disk) and cloud resources (ECS, ELB, EIP, NAT). Supports threshold-based anomaly detection, status classification (critical/warning/normal), and full-cluster monitoring aggregation.
Architecture: python3 scripts/huawei-cloud.py dispatcher → hcloud (KooCLI) cloud service queries + signed AOM Prometheus HTTP queries + limited kubectl reads only when Kubernetes resource relationships are required → Pod/Node metrics, ECS/ELB/EIP/NAT metrics → Threshold classification → Anomaly detection
Execution method: Cloud service queries are executed through the local
hcloudCLI. AOM Prometheusquery_rangecalls are the only exception and use signed HTTPS requests because the required Prometheus range-query path is not compatible with hcloud. Do not call Huawei Cloud SDKs, curl IAM flows, openstack, or hand-written cloud APIs outside the bundled dispatcher.
Related Skills: use pod/node diagnosers, Kubernetes event analyzer, capacity/cost skills, or auto-remediation runner for follow-up diagnosis or explicitly requested remediation.
Capabilities:
- Pod CPU/memory TopN ranking and single Pod time-series metrics
- Node CPU/memory/disk TopN ranking and single Node time-series metrics
- Node GPU and xGPU metrics, including GPU utilization, memory, temperature, power, schedule policy, xGPU allocation, usage, and health
- CoreDNS QPS, error rate excluding NXDOMAIN, NXDOMAIN rate, P95 latency, replica count, and per-Pod CPU/memory metrics
- nginx-ingress QPS, 4xx/5xx rate, success rate, P95 latency, active connections, per-Pod CPU/memory, and Ingress TLS certificate expiration status
- Autoscaler unschedulable Pods, node state count, scale-up/down events, errors, node groups, HPA current/desired replicas, and per-Pod CPU/memory metrics
- Kubernetes control-plane metrics for apiserver, etcd, controller-manager, and scheduler
- ECS instance CPU/memory/disk/network metrics
- ELB connection, bandwidth, QPS metrics
- EIP bandwidth, traffic, packet loss metrics
- NAT Gateway SNAT connection metrics
- Full-cluster monitoring aggregation with anomaly detection (80% threshold)
- Threshold-based status classification (critical/warning/normal/unknown)
What ships with it
21 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.
- references/acceptance-criteria.md 2.9 KB
- references/cli-installation-guide.md 2.0 KB
- references/iam-policies.md 2.3 KB
- references/kubectl-cce.md 1.3 KB
- references/output-schema.md 3.8 KB
- references/risk-rules.md 945 B
- references/verification-method.md 2.8 KB
- references/workflow.md 1.9 KB
- scripts/huawei_cloud/__init__.py 37 B runs code
- scripts/huawei_cloud/aom.py 4.9 KB runs code
- scripts/huawei_cloud/cce_cluster_monitoring.py 32 KB runs code
- scripts/huawei_cloud/cce_metrics.py 100 KB runs code
- scripts/huawei_cloud/cce.py 8.4 KB runs code
- scripts/huawei_cloud/common.py 9.1 KB runs code
- scripts/huawei_cloud/dispatcher.py 13 KB runs code
- scripts/huawei_cloud/ecs.py 3.8 KB runs code
- scripts/huawei_cloud/elb.py 12 KB runs code
- scripts/huawei_cloud/kubectl_client.py 12 KB runs code
- scripts/huawei_cloud/network.py 14 KB runs code
- scripts/huawei-cloud.py 1.7 KB runs code
- skill-profile.yaml 1.2 KB
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.
- 12d ago First seen · 488 lines · 293 tokens per session scan A a4d81274d5e0
huawei-cloud-cce-metric-analyzer is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 293 tokens to every session and 7,401 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gcp-cloud-monitoring
Google Cloud Monitoring — time series metrics, alert policies, active alerts, metric discovery. Use when checking GCP network performance, investigating firing alerts, querying VM CPU or memory metrics, reviewing Cloud VPN tunnel status, or assessing load balancer latency.
awslabs-cloudwatch-mcp
Metrics, alarms, and logs analysis.
Observability with Prometheus & Grafana
Production-grade observability stack with Prometheus metrics, Grafana dashboards, PromQL query language, alerting rules, and AI-powered anomaly detection for modern cloud-native applications.
performance-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.
querying-yandex-cloud
Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the yc CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.
opentelemetry-net-instrumentation
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.