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-swr-enterprise-instancegit 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-swr-enterprise-instance)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-swr-enterprise-instance"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-swr-enterprise-instance/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-swr-enterprise-instance"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-swr-enterprise-instance.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 45 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 316 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 319 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 494 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 Tool Misuse · line 438 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.00249 | $0.07149 |
| Opus 5 | $0.00125 | $0.03574 |
| Sonnet 5 | $0.00050 | $0.01430 |
| Haiku 4.5 | $0.00025 | $0.00715 |
Grade A, and why
huawei-cloud-swr-enterprise-instance 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 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.
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 — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud SWR Enterprise Instance Management
Overview
This skill provides lifecycle management capabilities for Huawei Cloud SWR (Software Repository for Container) enterprise instances using the hcloud CLI. Enterprise instances provide dedicated, isolated container registry environments with advanced features like security scanning, replication policies, and custom domain support.
Note: Some features (e.g., replication policies) are managed via the SWR enterprise instance console, not through CLI. See Out of Scope above.
Architecture: hcloud CLI → SWR Service API → Instance/Namespace/Registry/Repository/Artifact/Credential/Endpoint/Domain resources
Related Skills:
huawei-cloud-swr-image-management- Image lifecycle management (basic SWR namespaces, repos, tags, auth, quotas)huawei-cloud-swr-image-governance- Image governance (permissions, retention, sharing, tags, immutable rules)huawei-cloud-swr-image-automation- Image automation ops (sync, triggers, domains)
Out of Scope:
This skill does NOT support the following operations. If the user requests any of these, inform them and suggest the correct skill:
| Operation | Use Instead | Reason |
|---|---|---|
| Manage basic (non-enterprise) SWR namespaces | huawei-cloud-swr-image-management |
Basic SWR namespace lifecycle |
| Push/pull images (docker login/push/pull) | Docker CLI (use this skill to get credentials first) | Docker CLI operation, not API |
| Build images | CodeArts Build, CCE, or local Docker | SWR is a registry, not a build service |
| Manage namespace/repo permissions | huawei-cloud-swr-image-governance |
Permission governance is a separate skill |
| Create retention/aging policies on basic SWR | huawei-cloud-swr-image-governance |
Retention governance for basic SWR |
| Create image sync rules on basic SWR | huawei-cloud-swr-image-automation |
Sync automation for basic SWR |
| Create/Delete triggers on basic SWR | huawei-cloud-swr-image-automation |
Trigger automation for basic SWR |
| Manage SWR agency delegation for basic SWR | huawei-cloud-swr-image-governance |
Agency delegation for basic SWR |
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.
- references/acceptance-criteria.md 2.0 KB
- references/cli-format-guide.md 3.1 KB
- references/cli-installation-guide.md 3.2 KB
- references/command-reference.md 11 KB
- references/common-pitfalls.md 23 KB
- references/credential-configuration.md 2.2 KB
- references/iam-policies.md 8.7 KB
- references/output-format.md 1.8 KB
- references/parameter-reference.md 5.0 KB
- references/swr-instance-api-guide.md 38 KB
- references/task-instance-artifacts.md 9.4 KB
- references/task-instance-credentials.md 7.3 KB
- references/task-instance-domains.md 7.2 KB
- references/task-instance-endpoints.md 9.9 KB
- references/task-instance-lifecycle.md 9.3 KB
- references/task-instance-namespaces.md 9.1 KB
- references/task-instance-registries.md 11 KB
- references/verification-method.md 9.2 KB
- scripts/swr_instance_helper.py 16 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.
- 12d ago First seen · 499 lines · 249 tokens per session scan A de70913965d3
huawei-cloud-swr-enterprise-instance is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 249 tokens to every session and 7,149 once invoked, about $0.0012 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
securing-container-registry-with-harbor
Harbor is an open-source container registry that provides security features including vulnerability scanning (integrated Trivy), image signing (Notary/Cosign), RBAC, content trust policies, replicatio.
securing-container-registry-images
Securing container registry images by implementing vulnerability scanning with Trivy and Grype, enforcing image signing with Cosign and Sigstore, configuring registry access controls, and building CI/CD pipelines that prevent deploying unscanned or unsigned images.
azure-compute
Select and implement the right Azure compute platform for a workload. Decision tree guides choice based on workload characteristics, scaling needs, and operational maturity. Covers serverless, PaaS, containers, Kubernetes, and IaaS patterns.
docker-registry
Container image registry workflows — GHCR, Docker Hub, and private registry auth, tagging strategies, CI push pipelines, image pruning, and multi-platform manifest publishing.
harbor-registry
Container image registry with Harbor.
Diagnose ImagePullBackOff
Determine why a pod cannot pull its container image and resolve safely.