Borrowing it
Nothing to install: this file belongs to doublej/consult-user-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/doublej/consult-user-mcp/main/.claude/skills/windows-build/SKILL.mdgit clone --depth 1 https://github.com/doublej/consult-user-mcpWrote 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/doublej/consult-user-mcp/windows-build)<a href="https://agentmods.dev/skills/doublej/consult-user-mcp/windows-build"><img src="https://agentmods.dev/badge/skills/doublej/consult-user-mcp/windows-build/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/doublej/consult-user-mcp/windows-build"><img src="https://agentmods.dev/badge/skills/doublej/consult-user-mcp/windows-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 33 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00077 | $0.00635 |
| Opus 5.5 | $0.00031 | $0.00254 |
| Sonnet 5.5 | $0.00015 | $0.00127 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
windows-build scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows builds
Nothing Windows can be built or tested from macOS. .NET/WPF and Velopack need the real environment.
ssh [email protected]
Repo: C:\Users\jurre\PycharmProjects\consult-user-mcp
Commands run through cmd.exe by default. For PowerShell use powershell -Command "..." or powershell -ExecutionPolicy Bypass -File ....
Prerequisites on that machine
dotnet SDK 8.0 · node/npm · gh CLI (authenticated) · vpk (dotnet tool install -g vpk)
Builds
cd dialog-cli-windows && dotnet publish -r win-x64 --self-contained -p:PublishSingleFile=true
cd windows-app && dotnet build # dev
cd windows-app && dotnet publish -c Release -r win-x64 --self-contained
powershell -ExecutionPolicy Bypass -File scripts\build-windows-installer.ps1
Gotchas
- stderr aborts the installer script.
build-windows-installer.ps1sets$ErrorActionPreference = "Stop", so a Node.jsExperimentalWarningon stderr kills the build. The script flips it toContinuearound npm/npx calls — wrap any new npm command the same way. dialog-cli-windows/cannot be renamed todialog-cli/. It would collide with the macOS Swift CLI directory.%APPDATA%\ConsultUserMCPcannot be renamed. Existing users' settings and snooze state live there.- Velopack + WPF setup is unusual.
App.xamlis aPage, not anApplicationDefinition; the entry point is a customMainwithStartupObjectset in the csproj. Do not "fix" this back to the WPF default. <UseWPF>true</UseWPF>and anet8.0-windowstarget are both required.System.Drawingneeds an explicitSystem.Drawing.CommonNuGet reference on .NET 8.
Parity
The Windows dialog CLI must accept the same JSON and print the same response shape as the macOS one — mcp-server calls both through one DialogProvider interface. See .claude/rules/dialog-parity.md.
tweak and propose_layout are macOS-only; WindowsDialogProvider throws for both. That is intentional, not a bug to fix incidentally.
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.
- 1mo ago First seen · 45 lines · 77 tokens per session scan A b3c263ae11cc
windows-build is a skill published in the GitHub repository doublej/consult-user-mcp (39 stars, last pushed 14d ago), licensed MIT. It adds 77 tokens to every session and 635 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
debugging-livekit-agents
Drives a live multi-turn conversation with a LiveKit agent running locally, using lk agent debugger. Use when the user says "test my agent", "try my agent", "does this work", or "why did it call that tool", after editing an agent to check how it behaves, or when an agent on a speech-to-speech model or one that…
gcloud-usage
This skill should be used when user asks about "GCloud logs", "Cloud Logging queries", "Google Cloud metrics", "GCP observability", "trace analysis", or "debugging production issues on GCP".
chisle-audit
One-shot efficiency audit of a file, diff, or whole repo across BOTH axes at once: over-engineered code (reinvented stdlib, needless abstractions, speculative config) AND bloated prose (verbose comments, padded docstrings, redundant doc sections). Neither a pure code-minimizer nor a pure prose compressor does both in…
mongodb-query-optimizer
Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…
frontend-testing-debugging
This skill should be used when user asks to "debug this UI", "verify a rendered frontend change", or "check responsive layouts". Diagnose visual and interaction problems, compare reference screenshots, and reuse project QA journeys when available.
spk-run-blocked-recovery
Recover from Spec Kitty blocked runtime states, missing artifacts, failed guards, stale worktrees, and decision-required loops.