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 nimadorostkar/Claude-Skills-collection --skill file-organizationgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/file-organization)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/file-organization"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/file-organization/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/nimadorostkar/claude-skills-collection/file-organization"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/file-organization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.01339 |
| Opus 5 | $0.00020 | $0.00669 |
| Sonnet 5 | $0.00008 | $0.00268 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
file-organization 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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Organization
Purpose
Bring order to a directory without losing anything. Every file-organization task has one hard requirement that overrides all others: nothing is destroyed, and every action is reversible.
When to Use
- Organizing a directory of accumulated files.
- Finding and removing duplicates.
- Reclaiming disk space.
- Applying a consistent naming convention.
- Sorting downloads, documents, or media.
Capabilities
- Classification by type, content, and date.
- True duplicate detection by content hash.
- Consistent renaming.
- Space analysis.
- Safe, reversible operations.
Inputs
- The directory, and how large it actually is.
- The organizing principle: by type, by date, by project.
- What must not be touched.
Outputs
- A plan, shown before anything is executed.
- The reorganization, performed reversibly.
- A report of what changed.
Workflow
- Survey first — Count, size, types, and the largest items. Never act on a directory you have not looked at.
- Propose a plan and show it — What will move where, what will be renamed, what will be deleted. This is shown, and confirmed, before anything happens.
- Detect duplicates by content, not by name — Hash the files. Two files with the same name are frequently different; two files with different names are frequently identical.
- Move, do not delete — Duplicates and junk go to a quarantine directory, not to oblivion. Delete only after the user has confirmed, and preferably never.
- Preserve the metadata — Modification times carry information. Do not destroy them by copying carelessly.
- Report what happened — With a way to undo it.
Best Practices
- Never delete. Move to a quarantine directory and let the user delete it themselves once they are satisfied. A cleanup that destroys one needed file has failed regardless of how much space it reclaimed.
- Hash before declaring a duplicate. Filename matching produces false positives (two different
invoice.pdf) and false negatives (report.pdfandreport (1).pdfthat are identical). - Hash cheaply: compare sizes first, then hash only the files whose sizes match. Hashing a 200 GB directory in full is slow and almost entirely wasted.
- Dry-run everything. Show the plan, and require confirmation for anything destructive.
- Preserve the original name somewhere — in a manifest, if not in the filename. Renaming without a record is irreversible in practice.
- Watch for hard links and symlinks. "Deleting a duplicate" that is a hard link frees nothing and may break something.
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.
- 9d ago First seen · 138 lines · 40 tokens per session scan A ffea1f94b1cd
file-organization is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 25d ago), licensed MIT. It adds 40 tokens to every session and 1,339 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
update-turbo
Update installed Turbo skills from the local repo with a dynamic changelog, conflict resolution for customized skills, and guided user experience. Use when the user asks to "update turbo", "update turbo skills", "reinstall turbo", or "upgrade turbo".
mm-resume
A workflow for restoring project context after starting a new Claude Code session or clearing the conversation. It reads project notes, recent session information, version-control status, and available planning files.
mm-setup
A setup guide that personalizes a shared mm system for one user. It asks for details such as your name, work area, tools, language, and Obsidian vault location, then saves them in private configuration files.
mm
A dispatcher that provides short /mm commands for project setup, session recovery, project overviews, and workflow checks. It maps these aliases to longer system commands.
apple-shortcuts
Generate importable Apple Shortcuts (.shortcut / plist XML) for macOS and iOS. Use this skill whenever the user wants to create, modify, reverse-engineer, or understand Apple Shortcuts, including native actions, third-party app integrations (Actions, Data Jar, Toolbox Pro, Scriptable, a-Shell, Jayson, Pushcut)…
daily-briefing
Daily orientation and chief-of-staff briefing. Pulls from Slack (saved items), Gmail (important/starred), Google Calendar (today's events), Jira CLI (configured projects), and Todoist CLI, validates every action item, synthesizes a prioritized briefing using three consequence-based tiers, then produces a decisive…