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 skills add sandraschi/windows-operations-mcp --skill windows-expertgit clone --depth 1 https://github.com/sandraschi/windows-operations-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/sandraschi/windows-operations-mcp/windows-expert)<a href="https://agentmods.dev/skills/sandraschi/windows-operations-mcp/windows-expert"><img src="https://agentmods.dev/badge/skills/sandraschi/windows-operations-mcp/windows-expert.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 | $0.00000 | $0.00706 |
| Opus 5 | $0.00000 | $0.00353 |
| Sonnet 5 | $0.00000 | $0.00141 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
windows-expert 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 8d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🛠️ Skill: Windows Native Hardening & Data Surgery
Name: windows-expert
Description: Expert in Windows-native orchestration, registry hardening, account management, and high-fidelity JSON/Archive surgery.
📖 Overview
This skill provides the operational logic and safe-mode patterns for managing Windows systems at an industrial grade. It prioritizes system integrity via "Safe Mode" registry operations and "Lean SOTA" data manipulation.
🛠️ Tool Interaction Patterns
1. Registry Hardening (windows_registry)
- Pattern: Always perform a read/export before a write.
- Safe Mode: The
safe_mode=Trueparameter (default) automatically exports the target key tobackups/registry/before any destructive action. - Hardening Example:
- Action:
delete - Key:
HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Windows\CurrentVersion\Run\UnwantedApp - Result: Auto-backup created.
- Action:
2. Local Account Management (windows_accounts)
- Pattern: List users before adding or modifying passwords.
- Groups: Use
manage_groupto enforce the Principle of Least Privilege (PoLP). - Audit: Run
get_group_memberson the "Administrators" group to identify SID-based privilege creep.
3. Networking & Perimeter (windows_network)
- Firewall: Use
firewall_listbefore adding new rules. - Diagnostics: Always
flush_dnsas a first step in network-related agentic troubleshooting.
4. Environment Surgery (windows_environment)
- Persistence: Distinguish between
UserandSystemscopes. - Synchronization: Always trigger a
broadcastafter modifications to ensure running processes adopt the new environment map.
🛰️ Agentic Workflows (FastMCP 3.2+)
⚡ Thinking Pattern: Autonomous Hardening
- Inventory: Run
windows_automation(action="wmi_query", wmi_class="Win32_OperatingSystem")to identify the environment. - Audit: Run
windows_accounts(action="list_users")orwindows_services(action="list"). - Diagnostic Sampling: Use SEP-1577 Sampling (
ctx.sample()) with a 'Reasoning' prompt to identify vulnerabilities in the inventory. - Remediation: Use
windows_registryorwindows_servicesto apply changes. - Verification: Re-audit and log the results using
json_operations(action="write")to a status report.
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.
- 8d ago First seen · 61 lines · 0 tokens per session scan A 555a4c40a886
windows-expert is a skill published in the GitHub repository sandraschi/windows-operations-mcp (3 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 706 tokens. 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 skills, from other repositories
analyzing-windows-prefetch-with-python
Use when parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns. Use when working with analyzing windows prefetch with python.
analyzing-windows-prefetch-with-python
Parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns.
sop-mcp-configuration
Configure SOP-MCP server for step-by-step SOP execution in any MCP client.
sovereign-economics-engine
Unified business model evaluator, client filter, pricing engine, and distribution architect. Absorbs 31 business + 8 marketing + 13 content + 2 acquisition protocols.
therapeutic-ifs
Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.