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 1181652815-hub/clean-windows-c-drive-skill --skill clean-windows-c-drivegit clone --depth 1 https://github.com/1181652815-hub/clean-windows-c-drive-skillWrote 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/1181652815-hub/clean-windows-c-drive-skill/clean-windows-c-drive)<a href="https://agentmods.dev/skills/1181652815-hub/clean-windows-c-drive-skill/clean-windows-c-drive"><img src="https://agentmods.dev/badge/skills/1181652815-hub/clean-windows-c-drive-skill/clean-windows-c-drive/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/1181652815-hub/clean-windows-c-drive-skill/clean-windows-c-drive"><img src="https://agentmods.dev/badge/skills/1181652815-hub/clean-windows-c-drive-skill/clean-windows-c-drive.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 | $0.00124 | $0.02790 |
| Opus 5 | $0.00062 | $0.01395 |
| Sonnet 5 | $0.00025 | $0.00558 |
| Haiku 4.5 | $0.00012 | $0.00279 |
Grade A, and why
clean-windows-c-drive 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 12d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Windows C Drive
Objective
Assess C: health, diagnose usage, separate safe cleanup from review-only data, and preserve normal Windows operation. Prefer Windows-supported cleanup mechanisms and reversible actions. Never claim that a single check guarantees future hardware or filesystem health.
Safety rules
- Start read-only. Do not change anything during the audit.
- Run the health gate on every invocation before measuring cleanup candidates.
- Stop cleanup on a
Criticalresult. OnAttention, explain the failed checks and clean only if the warning is solely low free space and the proposed action is low risk. - Read references/safety-catalog.md before recommending or performing cleanup.
- Never manually delete from Windows, Program Files, ProgramData, System Volume Information, Recovery, Boot, WinSxS, DriverStore, EFI/recovery partitions, registry hives, page files, or restore-point storage.
- Never bulk-clean a user profile, Downloads, Desktop, Documents, cloud folders, browser profiles, mail, projects, VMs, or game libraries.
- Never use registry cleaners, broad wildcards, recursive deletion from a drive root,
DISM /ResetBase, ownership changes, ACL changes, or unresolved environment variables. - Do not disable hibernation, System Restore, Windows Update, antivirus, indexing, reserved storage, or OneDrive Files On-Demand merely to gain space.
- Prefer Windows-supported cleanup and reversible actions. State when recovery is impossible.
- Verify exact resolved targets stay inside each user-approved location before a destructive operation.
- Never move installed-program directories, AppData, ProgramData, game libraries, cloud placeholders, shortcuts, profile configuration, WSL/Docker/VM data, or any folder tree with the generic relocation script.
Workflow
0. Use the Simplified Chinese interface when requested
Prefer the standalone CDriveManager.exe when the user has installed or downloaded it. A known executable may be launched for an interactive request, but launching the app authorizes only its initial read-only health check. The app must still scan first, leave personal-file rows unselected, display an exact confirmation, and enforce the protected locations in code before any cleanup.
What ships with it
17 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.
- agents/openai.yaml 357 B
- references/deep-clean-policy.md 2.0 KB
- references/health-policy.md 2.1 KB
- references/relocation-policy.md 1.8 KB
- references/safety-catalog.md 2.8 KB
- references/user-file-cleanup-policy.md 1.2 KB
- scripts/Find-CDriveDuplicateFiles.ps1 2.4 KB runs code
- scripts/Find-CDriveLargeFiles.ps1 1.1 KB runs code
- scripts/Get-CDriveCleanupReport.ps1 4.0 KB runs code
- scripts/Invoke-DeepCDriveCleanup.ps1 8.8 KB runs code
- scripts/Invoke-SafeCDriveCleanup.ps1 4.9 KB runs code
- scripts/Invoke-SafeFileRelocation.ps1 5.7 KB runs code
- scripts/Invoke-SafeUserFileCleanup.ps1 3.2 KB runs code
- scripts/New-SafeRelocationPlan.ps1 4.3 KB runs code
- scripts/Start-CDriveManager.ps1 23 KB runs code
- scripts/Test-CDriveHealth.ps1 7.5 KB runs code
- scripts/UserFileSafety.ps1 3.7 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.
- 12d ago First seen · 195 lines · 124 tokens per session scan A 354f1dd1deca
clean-windows-c-drive is a skill published in the GitHub repository 1181652815-hub/clean-windows-c-drive-skill (6 stars, last pushed 19d ago), licensed MIT. It adds 124 tokens to every session and 2,790 once invoked, about $0.0006 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
storywriter
Write well-formed work items (Tasks, User Stories, Issues) for Azure DevOps, GitHub, or Jira. Use this skill when asked to write, draft, or create a task, story, issue, or work item.
conventional-commit
Workflow for generating conventional commit messages following the Conventional Commits specification. MUST be invoked every time a commit is created. Guides construction of standardized commit messages with correct type, scope, description, body, and footer.
segment-create
Full scaffolding workflow for creating a new Oh My Posh segment. Invoke when asked to add a new segment: generates the Go source, registers the type, creates documentation, updates the sidebar and JSON schema.
bilibili-page-reader
A tool for reading Bilibili videos, including subtitles, viewer messages, and comments. Bilibili is a Chinese video platform; viewer messages are timed comments that appear over the video.
locus-unity-bridge
Use when an agent needs to inspect or control a real Unity Editor through Locus, especially when Unity MCP is unavailable, named-pipe discovery is needed, C# must be executed, or Unity scripts must be recompiled.
powershell-safe-invocation
Use when writing or running PowerShell on Windows, especially native programs, quoted paths, escaping, pwsh, Start-Process, file operations, or shell troubleshooting.