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.
npx agentmods add instructions/thnak/windows-host-mcp/claude-mdgit clone --depth 1 https://github.com/thnak/windows-host-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/instructions/thnak/windows-host-mcp/claude-md)<a href="https://agentmods.dev/instructions/thnak/windows-host-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thnak/windows-host-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.02650 | $0.02650 |
| Opus 5 | $0.01325 | $0.01325 |
| Sonnet 5 | $0.00530 | $0.00530 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
windows-host-mcp CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
An MCP server (Node/TypeScript, stdio transport) that gives an MCP agent SSH access to one or more Windows machines — running commands, transferring files, and driving long-running/interactive jobs, all over ssh2. It's the windows-host MCP server available in this session (mcp__windows-host__* tools).
Commands
npm run dev # tsx watch src/index.ts — run against live env vars
npm run check # tsc --noEmit — type-check only, fastest correctness check
npm run build # tsc → dist/
npm run inspect # npx @modelcontextprotocol/inspector node dist/index.js — interactive tool testing
No test suite exists in this repo. npm run check is the main correctness gate before committing.
The server needs a host configuration to start (WINDOWS_HOSTS_CONFIG pointing at a JSON file, or the flat WINDOWS_SSH_* env vars — see README.md and hosts.example.json/.env.example). Without one, loadConfig() in src/config.ts throws immediately.
Published only via GitHub (no npm registry publish access from this environment) — releases are git tags (vX.Y.Z) on github.com/thnak/windows-host-mcp. Install/update is git clone + npm link, not npm install -g git+https://...: that was the original design but testing found it genuinely corrupts the install on some npm versions — npm's git-dependency packing step silently dropped top-level files from this package's dist/ and dropped @modelcontextprotocol/sdk's dist/ entirely, even with --ignore-scripts. git clone + npm install + npm link was verified to work reliably and is now the only documented path; cliUpdate.ts's update subcommand mirrors it (git fetch --tags + git checkout <tag> + npm install inside the existing checkout, resolved via import.meta.url back to the package root) rather than re-invoking npm's git-install machinery. dist/ is committed to the repo (unusual for a TS project, but deliberate — it's what makes a bare git checkout <tag> immediately runnable with no build step, and was also motivated by an earlier, now-moot problem: a prepare: npm run build script couldn't reliably find tsc on PATH inside npm's git-dependency install path). Rebuild and commit dist/ before tagging any release (npm run build, then git add dist) — nothing else does this for you.
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 · 83 lines · 2,650 tokens per session scan A ad06d393f5b6
windows-host-mcp CLAUDE.md is an instructions file published in the GitHub repository thnak/windows-host-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,650 tokens to every session, about $0.0132 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.