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-kubectl-cce-installergit 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-kubectl-cce-installer)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-kubectl-cce-installer"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-kubectl-cce-installer/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-kubectl-cce-installer"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-kubectl-cce-installer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 44 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 198 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 218 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 Privilege Escalation · line 89 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Excessive Agency · line 136 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 | $0.00092 | $0.01420 |
| Opus 5.5 | $0.00037 | $0.00568 |
| Sonnet 5.5 | $0.00018 | $0.00284 |
| Haiku 4.5 | $0.00009 | $0.00142 |
Grade B, and why
huawei-cloud-kubectl-cce-installer 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 27d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo bash scripts/install_kubectl_cce.sh --execute --bin-dir <directory> How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud CCE Kubectl Resource Query
Use this skill to retrieve specific CCE Kubernetes resources through kubectl cce. Resource access is the primary task. Local installation is only a
prerequisite recovery step when kubectl or the kubectl-cce plugin is unavailable.
Overview And Safety
- Use
kubectl cce; do not use a direct Kubernetes API client. - Read-only commands only:
get,describe, andlogs. - Never use
-A,--all-namespaces, or another whole-cluster resource query. - For namespaced resources, require
--namespace <namespace>and, where feasible, a specific resource name. - For cluster-scoped resources such as
node,namespace,persistentvolume, andstorageclass, require an exact resource name. Do not list every instance. - Never run
apply,create,delete,edit,patch,replace,scale,rollout,cordon,drain, orexec. - Do not print credentials, tokens, kubeconfig content, or Secret data.
Prerequisites And Required Context
| Input | Requirement |
|---|---|
cluster_id |
Required standard UUID. An exact name may be resolved with hcloud CCE ListClusters, but never run kubectl cce until it resolves to one UUID. |
region |
Required. Obtain it from the request or current context, then HW_REGION_NAME; otherwise ask the user. |
| Resource kind | Required, for example pod, deployment, service, configmap, or node. |
| Namespace or exact name | At least one is required. Namespaced resources require a namespace; cluster-scoped resources require an exact name. |
Credentials follow the plugin rules in plugin-usage.md. Use explicit --cli-access-key, --cli-secret-key, and optional
--cli-security-token only when the caller supplies them. Do not fall back to other credentials in that case.
Workflow
- Before any resource query, validate the target region and cluster ID. If either is missing, or the cluster ID cannot be resolved to one existing UUID in that
region, do not run
kubectl cce; ask the user to provide the correct region and cluster ID. - Confirm the resource kind, namespace, and exact resource name when required.
- Check local prerequisites:
What ships with it
4 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.
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.
- 27d ago Changed · -105 lines · +17 tokens per session 74861749d870
- 1mo ago First seen · 228 lines · 75 tokens per session scan B 5096be72c5f7
huawei-cloud-kubectl-cce-installer is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,420 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
kubectl-basics
A guide to kubectl, the command-line tool used to manage Kubernetes clusters, which run containerized applications.
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.
network-rca
Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
mirrord-kafka
Helps DevOps engineers configure mirrord Operator's Kafka queue splitting feature end-to-end. Generates the MirrordSplitConfig and MirrordPropertyList Kubernetes CRD YAMLs (the current resources; MirrordKafkaTopicsConsumer + MirrordKafkaClientConfig are deprecated but still supported), the matching mirrord.json…
mirrord-operator
Help users install and configure the mirrord Operator for team/enterprise environments. Use when users ask about operator setup, Helm installation, cloud API key or license configuration, air-gapped/offline licensing, enabling features (queue splitting, DB branching, preview environments, multi-cluster), internal…