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 codepros100-dev/claude-windows-health-check --skill windows-health-checkgit clone --depth 1 https://github.com/codepros100-dev/claude-windows-health-checkWrote 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/codepros100-dev/claude-windows-health-check/windows-health-check)<a href="https://agentmods.dev/skills/codepros100-dev/claude-windows-health-check/windows-health-check"><img src="https://agentmods.dev/badge/skills/codepros100-dev/claude-windows-health-check/windows-health-check/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/codepros100-dev/claude-windows-health-check/windows-health-check"><img src="https://agentmods.dev/badge/skills/codepros100-dev/claude-windows-health-check/windows-health-check.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 | $0.00015 | $0.00911 |
| Opus 5 | $0.00008 | $0.00456 |
| Sonnet 5 | $0.00003 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
windows-health-check 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 11d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows System Health Check & Remediation
You are a Windows system administrator performing a comprehensive health check. Follow the phases below strictly. Do NOT delete files, uninstall software, or modify the registry unless fixing a clearly broken key. Always ask for confirmation before making system changes.
Arguments
Parse $ARGUMENTS for flags:
--report-only: Run diagnostics and generate report only, skip remediation--auto-fix: Automatically apply safe fixes (updates, temp cleanup, outdated software) without asking. Still ask before reboots.--quick: Run only critical checks (system health, security, disk space) -- skip full software inventory, network connections, and event viewer deep dive
If no arguments provided, run full diagnostics and ask before each remediation action.
Phase 1: DIAGNOSTICS
Run the PowerShell diagnostic scripts in parallel using Bash. Use script files to avoid $ escaping issues in bash-to-powershell. The diagnostic scripts are located in ${CLAUDE_SKILL_DIR}/scripts/.
Step 1a: Run all diagnostic scripts in parallel
Execute these script files simultaneously (each via powershell -NoProfile -ExecutionPolicy Bypass -File "path/to/script.ps1"):
- system-info.ps1 -- OS version, CPU, RAM, disk, uptime, battery, activation
- security-check.ps1 -- Defender status, firewall, pending updates, recent installs
- software-inventory.ps1 -- Installed software, startup programs, outdated apps (skip if --quick)
- performance-check.ps1 -- Temp folder sizes, large folders, top processes
- network-check.ps1 -- Adapters, DNS, connectivity, open connections (skip if --quick)
- services-check.ps1 -- Critical services, event viewer errors
- hardware-check.ps1 -- Device manager issues, drivers, disk health
Step 1b: Collect and analyze results
Parse all script outputs. For each of the 7 categories, assign:
- PASS (8-10/10): No issues or only cosmetic ones
- WARN (5-7/10): Issues that should be addressed but aren't urgent
- FAIL (0-4/10): Critical issues requiring immediate attention
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/hardware-check.ps1 2.9 KB runs code
- scripts/network-check.ps1 1.5 KB runs code
- scripts/performance-check.ps1 1.5 KB runs code
- scripts/security-check.ps1 1.7 KB runs code
- scripts/services-check.ps1 2.1 KB runs code
- scripts/software-inventory.ps1 1.3 KB runs code
- scripts/system-info.ps1 2.6 KB runs code
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.
- 11d ago First seen · 91 lines · 0 tokens per session scan A 804737aad35d
windows-health-check is a skill published in the GitHub repository codepros100-dev/claude-windows-health-check (1 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 911 once invoked, about $0.0001 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 skills, from other repositories
lcx-report-bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.
ast-grep
Searches and rewrites code by AST shape across 25 languages. Use when the target is a syntax pattern (every call/class/import shaped like X, a codemod, a YAML rule) rather than literal text; for plain strings, comments, or filenames, use rg.
debugging
Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.
lcx-doctor
Diagnose LazyCodex and Codex CLI installation health against the latest sources. Use whenever the user asks for a doctor or health check, says LazyCodex, lazycodex-ai, omo-codex, or Codex behaves oddly after an install, update, or config change, suspects a stale, drifted, or broken setup, or wants the local install…
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.
lsp
Use when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace.