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 commands/wangke19/gemini-ai-helpers/windowsWrote 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/commands/wangke19/gemini-ai-helpers/windows)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/windows"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/windows/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/commands/wangke19/gemini-ai-helpers/windows"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/windows.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 | $0.00011 | $0.01987 |
| Opus 5 | $0.00005 | $0.00993 |
| Sonnet 5 | $0.00002 | $0.00397 |
| Haiku 4.5 | $0.00001 | $0.00199 |
Grade A, and why
windows 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 5d 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.
This is a copy
100% identical to windows — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
must-gather:windows
Synopsis
/must-gather:windows [must-gather-path] [--component COMPONENT] [--errors-only]
Description
The must-gather:windows command analyzes Windows-specific logs collected during must-gather from Windows nodes in OpenShift clusters. It parses logs from Windows-specific components and identifies common Windows node issues.
This command analyzes logs from:
- kube-proxy - Windows networking service
- hybrid-overlay - OVN-Kubernetes hybrid networking (Linux-Windows pod communication)
- kubelet - Windows node agent
- containerd - Container runtime for Windows
- WICD - Windows Instance Config Daemon (node configuration)
- csi-proxy - Storage plugin for Windows
Use this command when:
- Troubleshooting Windows node issues
- Investigating Windows pod failures
- Analyzing Windows container runtime problems
- Debugging hybrid-overlay networking issues
- Reviewing HNS (Host Network Service) failures
Prerequisites
Windows Node Logs Collection:
Windows node logs must be collected during must-gather. This requires:
- The cluster has Windows nodes (labeled with
kubernetes.io/os=windows) - Must-gather was run with Windows log collection enabled
Expected Directory Structure:
must-gather/
└── host_service_logs/
└── windows/
└── log_files/
├── kube-proxy/kube-proxy.log
├── hybrid-overlay/hybrid-overlay.log
├── kubelet/kubelet.log
├── containerd/containerd.log
├── wicd/
│ ├── windows-instance-config-daemon.exe.INFO
│ ├── windows-instance-config-daemon.exe.ERROR
│ └── windows-instance-config-daemon.exe.WARNING
└── csi-proxy/csi-proxy.log
Implementation
-
Locate Windows logs:
- Check for
host_service_logs/windows/log_files/directory - If not found, inform user that cluster may not have Windows nodes or logs weren't collected
- Check for
-
Run Windows log analyzer:
python3 extensions/must-gather/skills/must-gather-analyzer/scripts/analyze_windows_logs.py \ <must-gather-path>
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.
- 5d ago First seen · 253 lines · 11 tokens per session scan A c3779f0d7d63
windows is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,987 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to windows, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
wtfp:report-bug
Collect a reproducible bug report and publish it only after explicit user approval.
fix
Diagnose and fix bugs, errors, and issues in code.
issue:discover-by-prompt
Discover issues from user prompt with Gemini-planned iterative multi-agent exploration. Uses ACE semantic search for context gathering and supports cross-module comparison (e.g., frontend vs backend API contracts).
issue:discover
Discover potential issues from multiple perspectives (bug, UX, test, quality, security, performance, maintainability, best-practices) using CLI explore. Supports Exa external research for security and best-practices perspectives.
create-docker-mcp-tunnel
Stand up an Google MCP tunnel locally with Docker Compose so Gemini can call a private MCP server (manual-credentials quickstart).
dograh-doctor
Diagnose a Dograh deployment via the dograh-setup skill — run doctor.sh, read the report, and fix the top issue (failing health check, unhealthy/exited container, port conflict, etc.).