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 niels-emmer/myace --skill scaleway-architecturegit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/scaleway-architecture)<a href="https://agentmods.dev/skills/niels-emmer/myace/scaleway-architecture"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/scaleway-architecture/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/niels-emmer/myace/scaleway-architecture"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/scaleway-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.00932 |
| Opus 5 | $0.00019 | $0.00466 |
| Sonnet 5 | $0.00008 | $0.00186 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
Scaleway Architecture 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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Scaleway has no WAF/CAF-style pillar or adoption framework to map to, so this
single skill is the governance-essentials layer for designing a Scaleway
environment that is secure, auditable, and cost-attributable — the
Organization/Project structure, IAM scoping, VPC/private-network topology,
security groups, and guardrails. It is the Scaleway-specific companion to
iac-expert's generic well-architected-review and resource-naming skills,
naming the concrete Scaleway constructs that the generic skills can't.
When to use it
When designing or reviewing a Scaleway environment's structure — a new project, an IAM/scope change, a network-topology decision, or a security-group change. Also before scaffolding a new workload into an existing environment, to confirm it fits the established pattern.
Organization and Project structure
- Use the hierarchy Organization → Projects → Resources, with IAM, billing, and support at the Organization level and IAM inherited down to Projects.
- Separate platform (bootstrap, networking, security, logging) from workload projects, so governance applied at the platform level inherits down without entangling workload-specific policy.
- Keep the project set shallow and meaningful — a handful of projects, each with a clear purpose, not a deep tree that mirrors the org chart.
- Apply IAM at the highest level where it's uniformly correct and let it
inherit; override only where a genuine exception exists (and document it per
iac-expert'sexception-documentationskill).
IAM scoping
- Assign IAM at the narrowest effective scope — a specific Project, or the Organization only where the permission genuinely applies everywhere.
- Use permission sets (reusable bundles of permissions) bound to a scope (Project or Organization), and grant them to principals — users, groups, or applications.
- Prefer applications + API keys for service-to-service and CI/CD access (see the identity guidance in the collection's AGENTS.md), never a long-lived secret where a scoped application key works.
- Never grant broad
*/admin permission sets as a shortcut — least privilege is the baseline.
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.
- 9d ago First seen · 81 lines · 39 tokens per session scan A 4854efcec752
Scaleway Architecture is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 932 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
loom-kubernetes
Kubernetes deployment, cluster architecture, security, and operations.
loom-prometheus
Prometheus monitoring and alerting for cloud-native observability.
terraform-infrastructure
Structures, writes, and reviews Terraform infrastructure code. Covers module layout, remote state, workspace strategy, variable and secrets handling, CI plan/apply pipeline, naming conventions, and multi-region deployment patterns (provider aliases, per-region state, failover strategies), while delegating shared risk…
design-aws-terraform-iac
Designs AWS-targeted Terraform infrastructure plans before implementation. Focuses on service selection, module boundaries, state/backends, environment separation, security/compliance guardrails, acceptance criteria, and explicit risk/validation assumptions.
loom-terraform
Infrastructure as Code with Terraform/OpenTofu.
loom-karpenter
Kubernetes node autoscaling and cost optimization with Karpenter.