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 AtlasOmnia/donna-starter --skill macos-storage-managementgit clone --depth 1 https://github.com/AtlasOmnia/donna-starterWrote 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/atlasomnia/donna-starter/macos-storage-management)<a href="https://agentmods.dev/skills/atlasomnia/donna-starter/macos-storage-management"><img src="https://agentmods.dev/badge/skills/atlasomnia/donna-starter/macos-storage-management/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/atlasomnia/donna-starter/macos-storage-management"><img src="https://agentmods.dev/badge/skills/atlasomnia/donna-starter/macos-storage-management.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 | $0.00022 | $0.03351 |
| Opus 5 | $0.00011 | $0.01675 |
| Sonnet 5 | $0.00004 | $0.00670 |
| Haiku 4.5 | $0.00002 | $0.00335 |
Grade A, and why
macos-storage-management scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- macos-storage-management — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS Storage Management
Safely reclaim local Mac storage without mistaking cloud placeholders for resident data, losing File Provider content, or flattening metadata onto an incompatible external filesystem.
Trigger
Load this skill when the user asks to free space on a Mac, move Documents/Desktop/Downloads to an external SSD, archive iCloud/File Provider folders, migrate between APFS and ExFAT, or explain conflicting Finder, du, and df storage figures.
Safety Principles
- Measure the live Data volume, not only
/. On modern macOS, usedf -h "$HOME"because/System/Volumes/Datacarries user data. - Inspect the destination filesystem before choosing a copy method. ExFAT does not preserve native macOS symlinks, ownership, permissions, extended attributes, resource forks, or every filename semantic.
- Treat File Provider folders specially. A logical file can be
datalesswith zero allocated blocks. Its apparent size is not reclaimable local space until downloaded. - Never delete on a partial copy. Copy/archive, independently verify, re-check source identity/state, then remove only verified source objects.
- Do not force cloud hydration onto a critically full disk. If placeholders materially exceed free space, move only resident files or free space elsewhere first.
- Report actual reclaimed capacity. Compare
dfbefore/after; do not equate logical file size with local blocks released.
Diagnosing an oversized “System Data” category
Treat the Storage Settings number as a classification clue, not a filesystem path. Before recommending cleanup:
- Compare the sealed System volume with the writable Data volume using
diskutil apfs listanddf -h "$HOME". - Check both Time Machine and APFS snapshots; do not assume snapshots are responsible.
- Rank
$HOME,~/Library,/private/var,/Library, and hidden application roots with allocated-block measurements. - Drill into app containers, group containers, caches, developer runtimes, cloud storage, and
/private/var/folders. - Inspect large files stored directly at a root such as
~/.hermes; directory-only rankings can hide backup multiplication. - Separate rebuildable caches/temp data from app-managed stores and live databases before proposing deletion.
What ships with it
2 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.
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.
- 10d ago First seen · 192 lines · 22 tokens per session scan A 20aaa47f6f53
macos-storage-management is a skill published in the GitHub repository AtlasOmnia/donna-starter (110 stars, last pushed 10d ago), licensed MIT. It adds 22 tokens to every session and 3,351 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 2026-08-30.
Other skills, from other repositories
kill-the-standup
Reads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done / doing / blockers), and posts it to Slack. Use when asked to write a standup, generate a standup update, post to the standup channel, summarize yesterday's work, or automate the daily standup. Trigger when a…
notion-artifact-capture
Use when a user says “save to Notion” for research, reports, drafts, references, or generated artifacts and wants a reusable default destination. Bootstraps a generic Notion AI Output Library under a user-created shared parent page, saves typed metadata and optional Markdown, verifies every write through the live API…
libretranslate-markdown-i18n
Machine-translate Markdown / Obsidian / Quartz content into other languages using a self-hosted LibreTranslate instance, preserving frontmatter, headings, emojis, bold/italic, wikilinks (![[...]]/[[...]]) and internal links. Use whenever a user wants to auto-translate a Markdown vault, Obsidian notes, or a…
todo-discipline
Use when starting any complex task (3+ steps) or before declaring work complete. Enforces todo/task state to match reality — merge updates + read verification. Prevents false completion.
obscure-tool-install-lookup
Use when a user asks how to install or use an obscure CLI tool, agent, or package and search engines are blocked, CAPTCHA-walled, or unhelpful. Resolves canonical install commands via GitHub repo search, raw README fetches, and official docs — without relying on websearch or bot-walled search engines.
google-workspace
Gmail, Calendar, Drive, Contacts, Sheets, and Docs — through Hermes-managed OAuth and a thin CLI wrapper. When gws is installed, the skill uses it as the execution backend for broader Google Workspace coverage; otherwise it falls back to the bundled Python client implementation.