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-image-governancegit 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-image-governance)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-swr-image-governance"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-swr-image-governance/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-image-governance"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-swr-image-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 101 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 | $0.00221 | $0.07345 |
| Opus 5 | $0.00111 | $0.03673 |
| Sonnet 5 | $0.00044 | $0.01469 |
| Haiku 4.5 | $0.00022 | $0.00734 |
Grade A, and why
huawei-cloud-swr-image-governance 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 — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud SWR Image Governance
Overview
This skill provides governance capabilities for Huawei Cloud SWR (Software Repository for Container) using the hcloud CLI, covering permissions, retention policies, sharing, and agency delegation.
Architecture: hcloud CLI → SWR Service API → Permission/Retention/Domain/Share/Agency resources
Related Skills:
huawei-cloud-swr-image-management- Image lifecycle management (namespace, repo, tag, auth, quota)huawei-cloud-swr-image-automation- Image automation ops (sync, triggers, domains)huawei-cloud-swr-enterprise-instance- Enterprise instance management
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 |
|---|---|---|
| Create/Delete/List namespaces | huawei-cloud-swr-image-management |
Namespace lifecycle, not governance |
| Create/Delete repositories or tags | huawei-cloud-swr-image-management |
Repo/tag lifecycle, not governance |
| Push/pull images (docker login) | huawei-cloud-swr-image-management |
Image operations, not governance |
| Create authorization tokens | huawei-cloud-swr-image-management |
Token management, not governance |
| List SWR quotas | huawei-cloud-swr-image-management |
Quota query, not governance |
| Create image sync rules | huawei-cloud-swr-image-automation |
Sync is automation, not governance |
| Create/Delete triggers | huawei-cloud-swr-image-automation |
Triggers are automation, not governance |
| Start security scans | huawei-cloud-swr-image-automation |
Scanning is automation, not governance |
| Create immutable (不可变) rules | N/A (not supported by any current skill) | Use Huawei Cloud SWR console |
| View audit logs | Use Huawei Cloud console or CES | Audit logs are not governance operations |
| Create/Delete enterprise instances | huawei-cloud-swr-enterprise-instance |
Instance lifecycle, not governance |
What ships with it
12 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 4.6 KB
- references/cli-installation-guide.md 4.5 KB
- references/common-pitfalls.md 9.1 KB
- references/iam-policies.md 5.2 KB
- references/output-format.md 4.0 KB
- references/swr-governance-api-guide.md 18 KB
- references/task-image-sharing.md 6.6 KB
- references/task-namespace-permissions.md 6.6 KB
- references/task-repository-permissions.md 6.5 KB
- references/task-retention-management.md 8.5 KB
- references/task-shared-domains.md 6.6 KB
- references/verification-method.md 5.5 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 · 490 lines · 221 tokens per session scan A 508dda3a14ec
huawei-cloud-swr-image-governance is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 221 tokens to every session and 7,345 once invoked, about $0.0011 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
building-threat-feed-aggregation-with-misp
Deploy MISP (Malware Information Sharing Platform) to aggregate, correlate, and distribute threat intelligence feeds from multiple sources for centralized IOC management and automated SIEM integration.
building-threat-feed-aggregation-with-misp
Deploy MISP via Docker and configure feeds from sources like abuse.ch, AlienVault OTX, and CIRCL to aggregate, correlate, and distribute threat intelligence, including automated feed synchronization and STIX/TAXII-based integration with Splunk, Elasticsearch, and SOAR platforms. Use when standing up centralized IOC…
building-threat-feed-aggregation-with-misp
Deploy MISP (Malware Information Sharing Platform) to aggregate, correlate, and distribute threat intelligence feeds from multiple sources for centralized IOC management and automated SIEM integration.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…