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.
git clone --depth 1 https://github.com/air-gapped/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/plugins/air-gapped/skills/ceph)<a href="https://agentmods.dev/plugins/air-gapped/skills/ceph"><img src="https://agentmods.dev/badge/plugins/air-gapped/skills/ceph/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/plugins/air-gapped/skills/ceph"><img src="https://agentmods.dev/badge/plugins/air-gapped/skills/ceph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ceph 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.
What it actually says
{
"name": "ceph",
"source": "./",
"description": "Rook-managed Ceph suite — Rook/Ceph upgrade order and version gates, the CVE-2025-30156 AES256K CephX key rotation, the Rook v1.20 ceph-csi-operator move; troubleshooting (mClock-locked recovery, PG states, OSD OOM sizing, restore-quorum, OSD removal, stuck RBD PVCs); performance (mClock NVMe capacity trap, memory sizing, PG autoscaler, networking, Tentacle Fast EC, krbd vs rbd-nbd); and RGW/S3 (SigV4 hardening fallout, AWS SDK checksums, sharding, Rook object CRDs). Squid 19.2 and Tentacle 20.2.",
"version": "0.20261003.32",
"author": {
"name": "Jörgen"
},
"license": "MIT",
"skills": [
"./.claude/skills/rook-ceph-best-practices",
"./.claude/skills/ceph-troubleshooting",
"./.claude/skills/ceph-performance",
"./.claude/skills/ceph-s3"
],
"strict": false,
"category": "infrastructure",
"tags": [
"ceph",
"rook",
"kubernetes",
"storage",
"rgw",
"s3",
"ceph-csi",
"cephx"
]
}What it installs
The manifest is a name and a version. 4 skills travel with it, and installing the plugin installs all of them — 615 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside marketplace.json#ceph 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.
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 Changed f9695d95be62
- 23d ago First seen · 28 lines scan A 72227e060cde
ceph is a plugin published in the GitHub repository air-gapped/skills (5 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-23.
Other plugins, from other repositories
infra-plugin
Infrastructure management for Kubernetes/GKE, Istio service mesh, and authentication (Keycloak, OAuth2-proxy). Includes Helm charts, Terraform IaC, and Traefik reverse proxy.
cw-debug
Generic CloudWatch log investigation skill with adaptive debugging methodology.
deployment-strategies
Deployment patterns, rollback automation, and infrastructure templates.
distributed-debugging
Distributed system tracing and debugging across microservices.
local-ai
From nothing to a working AI setup you own. Scans the machine for models that fit, installs and wires up the right app with consent at every download, shares it over a private URL, and rents a cloud GPU when a model is too big. Needs shell access.
python-dev
Python development workflow with architecture design, coding guidelines, testing patterns, and specialized review agents.