Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wangke19/gemini-ai-helpersnpx agentmods add skills/wangke19/gemini-ai-helpers/lvms-analyzerWrote 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/wangke19/gemini-ai-helpers/lvms-analyzer)<a href="https://agentmods.dev/skills/wangke19/gemini-ai-helpers/lvms-analyzer"><img src="https://agentmods.dev/badge/skills/wangke19/gemini-ai-helpers/lvms-analyzer/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/wangke19/gemini-ai-helpers/lvms-analyzer"><img src="https://agentmods.dev/badge/skills/wangke19/gemini-ai-helpers/lvms-analyzer.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 | $0.00016 | $0.04052 |
| Opus 5.5 | $0.00006 | $0.01621 |
| Sonnet 5.5 | $0.00003 | $0.00810 |
| Haiku 4.5 | $0.00002 | $0.00405 |
Grade A, and why
LVMS Analyzer 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 2mo 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 — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LVMS Analyzer Skill
This skill provides detailed guidance for analyzing LVMS (Logical Volume Manager Storage) must-gather data to identify and troubleshoot storage issues.
When to Use This Skill
Use this skill when:
- Analyzing LVMS must-gather data offline
- Diagnosing PVCs stuck in Pending state
- Investigating LVMCluster readiness issues
- Troubleshooting volume group creation failures
- Debugging TopoLVM CSI driver problems
- Checking operator health in LVMS namespace
This skill is automatically invoked by the /lvms:analyze command when working with must-gather data.
Prerequisites
Required:
- LVMS must-gather directory extracted and accessible
- Must-gather contains LVMS namespace directory:
namespaces/openshift-lvm-storage/(newer versions)- OR
namespaces/openshift-storage/(older versions)
- Python 3.6 or higher installed
- PyYAML library:
pip install pyyaml
Namespace Compatibility:
- LVMS namespace changed from
openshift-storagetoopenshift-lvm-storagein recent versions - The analysis script automatically detects which namespace is present
- Both namespaces are fully supported for backward compatibility
Must-Gather Structure:
must-gather/
└── registry-{image-registry}-lvms-must-gather-{version}-sha256-{hash}/
├── cluster-scoped-resources/
│ ├── core/
│ │ └── persistentvolumes/
│ │ └── pvc-*.yaml # Individual PV files
│ ├── storage.k8s.io/
│ │ └── storageclasses/
│ │ ├── lvms-vg1.yaml
│ │ └── lvms-vg1-immediate.yaml
│ └── security.openshift.io/
│ └── securitycontextconstraints/
│ └── lvms-vgmanager.yaml
├── namespaces/
│ └── openshift-lvm-storage/ # or openshift-storage for older versions
│ ├── oc_output/ # IMPORTANT: Primary location for LVMS resources
│ │ ├── lvmcluster.yaml # Full LVMCluster resource with status
│ │ ├── lvmcluster # Text output (oc describe)
│ │ ├── lvmvolumegroup # Text output
│ │ ├── lvmvolumegroupnodestatus # Text output
│ │ ├── logicalvolume # Text output
│ │ ├── pods # Text output (oc get pods)
│ │ └── events # Text output
│ ├── pods/
│ │ ├── lvms-operator-{hash}/
│ │ │ └── lvms-operator-{hash}.yaml
│ │ └── vg-manager-{hash}/
│ │ └── vg-manager-{hash}.yaml
│ └── apps/ # May contain deployments/daemonsets
└── ...
What ships with it
1 file 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.
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.
- 2mo ago First seen · 518 lines · 16 tokens per session scan A b75eaa2dc3b5
LVMS Analyzer is a skill published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 4,052 once invoked, about $0.0001 per session on Opus 5.5. 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.
LVMS Analyzer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| LVMS Analyzerwangke19/gemini-ai-helpers | Skill | 2 | 7mo ago | Apache-2.0 | A | 16 | Claude Code, Codex |
| dozzledinglebear-ai/dendrite | Skill | 1 | 1mo ago | AGPL-3.0 | A | 99 | Claude Code, Codex |
| aks-troubleshootingmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 221 | Claude Code |
| aks-gpu-inferencemicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 114 | Claude Code |
| dokploy-deployfcakyon/claude-codex-settings | Skill | 1.2k | today | Apache-2.0 | A | 63 | Claude Code |
| docker-debugkurtosis-tech/kurtosis | Skill | 559 | yesterday | Apache-2.0 | A | 45 | Claude Code, Codex |
| frontend-testing-debuggingfcakyon/claude-codex-settings | Skill | 1.2k | today | Apache-2.0 | A | 50 | Claude Code, Codex |