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 Aidas-dev/k8s-agent-skills --skill rook-ceph-operatorgit clone --depth 1 https://github.com/Aidas-dev/k8s-agent-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/aidas-dev/k8s-agent-skills/rook-ceph-operator)<a href="https://agentmods.dev/skills/aidas-dev/k8s-agent-skills/rook-ceph-operator"><img src="https://agentmods.dev/badge/skills/aidas-dev/k8s-agent-skills/rook-ceph-operator/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/aidas-dev/k8s-agent-skills/rook-ceph-operator"><img src="https://agentmods.dev/badge/skills/aidas-dev/k8s-agent-skills/rook-ceph-operator.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 | $0.00066 | $0.02727 |
| Opus 5 | $0.00033 | $0.01363 |
| Sonnet 5 | $0.00013 | $0.00545 |
| Haiku 4.5 | $0.00007 | $0.00273 |
Grade A, and why
rook-ceph-operator 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rook-Ceph Operator CRDs
Charts: rook-ceph + rook-ceph-cluster (from https://charts.rook.io/release) + ceph-csi-drivers (v1.20+, from https://charts.ceph.io/ceph-csi-operator)
Latest: v1.20.x (charts) | Ceph: v20.2.2 (Tentacle) | API: ceph.rook.io/v1
Install/upgrade order: rook-ceph → ceph-csi-drivers → rook-ceph-cluster
⚠️ v1.20 breaking change: CSI drivers are now managed by the separate
ceph-csi-driversHelm chart. Rook no longer creates CSI ServiceAccounts, RBAC, or Driver CRs. Without this chart, all PVC provisioning breaks. See Upgrade Notes below.
CRD Reference
| CRD | API | Purpose | Key Fields |
|---|---|---|---|
| CephCluster | v1 |
Core cluster CRD — defines monitors, OSDs, manager, network, storage topology. | spec.mon.count, spec.mgr.count, spec.storage (nodes[], useAllNodes, deviceFilter, config.deviceClass), spec.cephVersion.image, spec.dataDirHostPath, spec.dashboard, spec.network, spec.placement |
| CephBlockPool | v1 |
RBD block storage pool — creates Ceph pool + optional StorageClass. | spec.failureDomain, spec.replicated.size, spec.deviceClass, spec.erasureCoded (dataChunks, codingChunks), spec.application |
| CephFilesystem | v1 |
CephFS shared filesystem — metadata + data pools, MDS daemons. | spec.metadataPool, spec.dataPools[], spec.metadataServer.activeCount, spec.metadataServer.activeStandby |
| CephObjectStore | v1 |
S3-compatible object store — RGW gateway, metadata + data pools. | spec.metadataPool, spec.dataPool, spec.gateway.port, spec.gateway.instances, spec.gateway.placement |
| CephObjectStoreUser | v1 |
S3 access key/secret for object store users. | spec.store, spec.displayName |
| CephNFS | v1 |
NFS export of CephFS filesystem. | spec.rados.namespace, spec.server.active |
| CephRBDMirror | v1 |
RBD mirroring daemon for cross-cluster replication. | spec.count |
| CephFilesystemMirror | v1 |
CephFS snapshot mirroring across clusters. | spec.placement (placement only) |
| CephFilesystemSubVolumeGroup | v1 |
Subvolume group for CephFS quota/UID/GID isolation. | spec.filesystemName, spec.pinning, spec.quota |
| CephBucketTopic | v1 |
S3 bucket notification topic (Kafka, AMQP, webhook). | spec.endpoint, spec.persistent, spec.opaqueData |
| CephBucketNotification | v1 |
Binds topic to object store events. | spec.topic, spec.events[], spec.filter (key/metadata/tagFilters) |
| CephClient | v1 |
Ceph auth key management for external clients. | spec.caps |
| CephBlockPoolRadosNamespace | v1 |
Rados namespace within a block pool for tenant isolation. | spec.blockPoolName, spec.mirroring |
| CephCOSIDriver | v1 |
COSI (Container Object Storage Interface) driver. | Standard COSI config |
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 · 187 lines · 66 tokens per session scan A b6039986455f
rook-ceph-operator is a skill published in the GitHub repository Aidas-dev/k8s-agent-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 66 tokens to every session and 2,727 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…