What is windows-build?

Instructions for building and debugging the Windows parts of Consult User MCP, including a WPF command-line tool, tray application, and Velopack installer. The work is performed on a separate Windows machine over SSH.

Use it when changing, testing, or packaging files in the Windows application, Windows CLI, or installer.

It prevents attempts to build Windows-specific components on macOS and documents the required commands and common installer failure.

windows-build — Skill for Claude Code by doublej: Instructions for building and debugging the Windows parts of…

Install

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.

agentmods

npx agentmods add skills/doublej/consult-user-mcp/windows-build

Any agent

npx skills add doublej/consult-user-mcp --skill windows-build

Clone the repo

git clone --depth 1 https://github.com/doublej/consult-user-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/doublej/consult-user-mcp/windows-build.svg)](https://agentmods.dev/skills/doublej/consult-user-mcp/windows-build)

Your own site

<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="Measured on agentmods" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 635 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00039	$0.00318
Sonnet 5	$0.00015	$0.00127
Haiku 4.5	$0.00008	$0.00064

Measured 6d ago against content hash b3c263ae11cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

.claude/skills/windows-build/SKILL.md · 45 lines

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.ps1 sets $ErrorActionPreference = "Stop", so a Node.js ExperimentalWarning on stderr kills the build. The script flips it to Continue around npm/npx calls — wrap any new npm command the same way.
dialog-cli-windows/ cannot be renamed to dialog-cli/. It would collide with the macOS Swift CLI directory.
%APPDATA%\ConsultUserMCP cannot be renamed. Existing users' settings and snooze state live there.
Velopack + WPF setup is unusual. App.xaml is a Page, not an ApplicationDefinition; the entry point is a custom Main with StartupObject set in the csproj. Do not "fix" this back to the WPF default.
<UseWPF>true</UseWPF> and a net8.0-windows target are both required.
System.Drawing needs an explicit System.Drawing.Common NuGet 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.

Read the full file on GitHub · 45 lines

Changes

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.

6d ago First seen · 45 lines · 77 tokens per session scan A b3c263ae11cc

Subscribe to this mod's changes

windows-build is a skill published in the GitHub repository doublej/consult-user-mcp (40 stars, last pushed 17d ago), licensed MIT. It adds 77 tokens to every session and 635 once invoked, about $0.0004 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 2026-08-30.

Debugging DevOps and cloud claude claude-code codex gemini-cli

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".

fcakyon/claude-codex-settings · 49 tokens

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…

fcakyon/claude-codex-settings · 98 tokens

spk-run-blocked-recovery

Recover from Spec Kitty blocked runtime states, missing artifacts, failed guards, stale worktrees, and decision-required loops.

Priivacy-ai/spec-kitty · 31 tokens

spk-admin-setup-doctor

Install, verify, and repair Spec Kitty commands, skills, agent paths, runtime prerequisites, and common setup failures.

Priivacy-ai/spec-kitty · 31 tokens

superlint

This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.

mgechev/skillgrade · 0 tokens

bug-audit

Weekly multi-agent audit for serious bugs (data integrity, silent caps, staleness, timestamp math, trust boundaries). Fans out Sonnet scanners + Opus deep auditors, adversarially verifies every finding, files GitHub issues for confirmed critical/high bugs. Trigger: /bug-audit.

VasiHemanth/tokentelemetry · 0 tokens