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 0xDarkMatter/claude-mods --skill windows-opsgit clone --depth 1 https://github.com/0xDarkMatter/claude-modsWrote 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/0xdarkmatter/claude-mods/windows-ops)<a href="https://agentmods.dev/skills/0xdarkmatter/claude-mods/windows-ops"><img src="https://agentmods.dev/badge/skills/0xdarkmatter/claude-mods/windows-ops/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/0xdarkmatter/claude-mods/windows-ops"><img src="https://agentmods.dev/badge/skills/0xdarkmatter/claude-mods/windows-ops.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 Privilege Escalation · line 339 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00233 | $0.04510 |
| Opus 5.5 | $0.00093 | $0.01804 |
| Sonnet 5.5 | $0.00047 | $0.00902 |
| Haiku 4.5 | $0.00023 | $0.00451 |
Grade A, and why
windows-ops 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
windows-ops
Helps with
Slow or worsening boot, silently failing drives, crashes with no obvious cause, an HKLM startup entry you can't disable without admin, BSODs that leave no dump, unexplained UAC prompts, 'is it safe to unplug this drive?', cloning a failing drive, no-boot recovery, remote diagnostics, and a hot or out-of-commit machine with no boot-time explanation. Where each signal lives: references/symptom-guide.md.
The Universal Insight
Windows tells you what's wrong if you ask the right log in the right way. Most users (and most tutorials) reach for Task Manager. The actual diagnostic signal lives in the Event Log, the Registry's StartupApproved key, the storage driver's reset events, and the kernel's bugcheck records. This skill packages the queries that turn noise into a verdict.
The most common diagnostic failure: treating symptoms in isolation. "Slow boot" → disable startup apps. "BSOD" → reinstall drivers. "Random crashes" → memtest. These are reasonable last resorts, but the data to identify the actual cause is sitting in the System log untouched. Always audit before treating.
The Diagnostic Ladder
Walk down the layers in order. Each rung has a binary outcome:
0. Is it even local? — a "drive" that is a network mapping belongs to net-ops
1. Hardware errors — WHEA-Logger events (CPU/RAM/PCIe-level faults)
2. Storage health — disk events 7/52/153/154, storahci 129 (controller reset)
3. Crash record — Event 41 (Kernel-Power) + BugCheck code + dump files
4. Pre-crash timeline — events in N minutes before each crash
5. Boot inventory — all 5 startup mechanisms (registry, services, tasks, folders, group policy)
6. Resource pressure — CPU RATE sample, commit hoarders, orphans, stale hosts
7. Verdict — what's failing, what to do
The most interesting failures cluster at rung 2 (storage) and rung 5 (startup bloat). Rung 6 is the most-treated and the most misread: a Task Manager snapshot there really is low-value, which is why it gets waved away — but a CPU rate sample at the same rung finds hung processes no snapshot and no orphan check can see.
What ships with it
24 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.
- references/bugcheck-codes.md 12 KB
- references/manual-queries.md 7.3 KB
- references/process-triage.md 7.8 KB
- references/recovery-patterns.md 17 KB
- references/reference-index.md 5.3 KB
- references/remote-diagnostics.md 14 KB
- references/startup-mechanisms.md 18 KB
- references/storage-events.md 10.0 KB
- references/symptom-guide.md 5.4 KB
- references/uac-attribution.md 4.7 KB
- references/worked-example.md 4.6 KB
- references/wsl.md 10 KB
- scripts/_lib/common.ps1 5.1 KB runs code
- scripts/boot-perf.ps1 11 KB runs code
- scripts/copy-tree.ps1 20 KB runs code
- scripts/crash-triage.ps1 12 KB runs code
- scripts/disk-health.ps1 13 KB runs code
- scripts/drive-dependencies.ps1 17 KB runs code
- scripts/extract-image.ps1 14 KB runs code
- scripts/health-audit.ps1 24 KB runs code
- scripts/process-triage.ps1 12 KB runs code
- scripts/rescue-image.ps1 11 KB runs code
- scripts/safe-disable-startup.ps1 11 KB runs code
- tests/run.sh 12 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.
- 8d ago Changed · +2 lines deb61a9d8b1f
- 17d ago Changed · -225 lines f9f6eafea5bf
- 1mo ago Changed · +53 lines · +57 tokens per session 81ec75d9aa69
- 1mo ago First seen · 415 lines · 176 tokens per session scan A e5f1a8d08afd
windows-ops is a skill published in the GitHub repository 0xDarkMatter/claude-mods (71 stars, last pushed 8d ago), licensed MIT. It adds 233 tokens to every session and 4,510 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
diagnose-hid-keycodes
Find out what an unknown USB/Bluetooth HID button actually emits without assuming the label or documentation. Uses Karabiner's.
monitoring-observability
OpenTelemetry, structured logging, distributed tracing, alerting, and dashboards. Use when instrumenting services, designing logs/traces/metrics, defining SLOs and alerts, or debugging production behavior from telemetry.
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.