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-cci-instance-managementgit 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-cci-instance-management)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cci-instance-management"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cci-instance-management/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-cci-instance-management"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cci-instance-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
- 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 Memory Poisoning · line 111 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- high Memory Poisoning · line 154 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Excessive Agency · line 118 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 | $0.00150 | $0.06153 |
| Opus 5 | $0.00075 | $0.03076 |
| Sonnet 5 | $0.00030 | $0.01231 |
| Haiku 4.5 | $0.00015 | $0.00615 |
Grade A, and why
huawei-cloud-cci-instance-management 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 13d 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 — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud CCI Container Instance Lifecycle Management
Overview
Manage Huawei Cloud CCI (Cloud Container Instance) full lifecycle using hcloud CLI (KooCLI). CCI is a serverless container service — no cluster management needed, just create a Namespace, define a Network, then deploy workloads directly.
Architecture: hcloud CLI → CCI OpenAPI → Namespace / Network / Deployment / StatefulSet / Pod / EIPPool / Service / Ingress
Constraints and Rules
Security Rules
- Two-step confirmation: All destructive operations (delete Namespace/Network/Deployment/StatefulSet/Pod/EIPPool) require explicit user confirmation — preview command, resource details, and risk warning first; execute only after user confirms.
- Credential security: Never expose AK/SK values in conversation, commands, or output. Only use
hcloud configure listto check credential status (presence only). Prefer profile mode or environment variables over explicit AK/SK parameters.
Resource Constraints
- Namespace flavor annotation is mandatory: Every namespace must carry
namespace-kubernetes-io/flavorannotation (value:general-computingorgpu-accelerated). Without it, creation fails. - limits must equal requests: CCI enforces
resources.limits == resources.requests. Mismatch causes "limit and request doesn't equal" error. Set both to the same values (e.g.,500m/1Gi). - Network must precede workloads: Pod/Deployment/StatefulSet creation fails or stays Pending if no Network exists in the namespace. Always create Network before deploying workloads.
- VPC CIDR restriction: VPC subnet CIDR must NOT be
10.247.0.0/16— CCI reserves this range for Service networking. Using it causes IP conflicts and workload creation failures. - Deletion order: Pod → Deployment/StatefulSet → EIPPool → Network → Namespace. Deleting a Namespace cascades all resources under it.
hcloud CLI Constraints
- Network creation must use Python helper script: hcloud CLI cannot pass annotation keys containing dots (
network.alpha.kubernetes.io/default-security-group). Neither dot notation nor--cli-jsonInputworks. Usescripts/cci_network_helper.py. - Namespace annotation uses hyphen replacement: Keys like
namespace.kubernetes.io/flavorcan use hyphens (namespace-kubernetes-io/flavor) and CCI auto-normalizes. This workaround only works for Namespace, NOT for Network. - Always verify parameters with
--help: CCI has hundreds of parameters. Runhcloud CCI <Operation> --helpbefore constructing any command. The help output is the authoritative source.
What ships with it
16 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 3.2 KB
- references/cci-operation-catalog.md 9.9 KB
- references/common-workflows.md 12 KB
- references/credential-configuration.md 3.3 KB
- references/iam-policies.md 3.0 KB
- references/parameter-format.md 9.6 KB
- references/task-deployment-management.md 4.8 KB
- references/task-eippool-management.md 5.7 KB
- references/task-logs-and-status.md 3.7 KB
- references/task-namespace-management.md 2.3 KB
- references/task-network-management.md 6.2 KB
- references/task-pod-management.md 3.3 KB
- references/task-statefulset-management.md 4.6 KB
- references/troubleshooting.md 7.6 KB
- references/verification-method.md 2.5 KB
- scripts/cci_network_helper.py 10 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.
- 13d ago First seen · 501 lines · 150 tokens per session scan A 051b3dc6e91d
huawei-cloud-cci-instance-management is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 6,153 once invoked, about $0.0007 per session on Opus 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 2026-08-30.
Other skills, from other repositories
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
gcp-essentials
Use when running a small product on core Google Cloud via the gcloud CLI: a project, Cloud Run deploys, a locked-down Cloud Storage bucket, managed Cloud SQL, and least-privilege IAM wiring them together. NOT AWS (that is aws-essentials), NOT the CI pipeline that ships the image (that is deployment), NOT Postgres…
modal
Use when running Python or GPU workloads serverlessly on Modal — modal.App, inline container Images, gpu= on @app.function, Volumes for weight caching, Cron schedules, ASGI endpoints, modal run vs serve vs deploy. NOT managed prediction APIs with no container of your own (that is replicate); NOT SSH-able GPU boxes…
modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
coolify
Use when self-hosting apps and databases with Coolify on a VPS you own — install, first-admin lockdown, Git-to-deploy (Nixpacks/Dockerfile/compose), managed Postgres/Redis, scheduled S3 backups, domains + auto-SSL. NOT a PaaS someone else runs (that is railway), NOT sizing/hardening the box (that is hetzner), NOT…
k8s-autoscaling
Configure Kubernetes autoscaling with HPA, VPA, and KEDA. Use for horizontal/vertical pod autoscaling, event-driven scaling, and capacity management.