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 alivirgo/Major-AI-Skills --skill dropovergit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/dropover)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/dropover"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/dropover/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/alivirgo/major-ai-skills/dropover"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/dropover.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 | $0.00023 | $0.01501 |
| Opus 5.5 | $0.00009 | $0.00600 |
| Sonnet 5.5 | $0.00005 | $0.00300 |
| Haiku 4.5 | $0.00002 | $0.00150 |
Grade A, and why
dropover scanned grade A with 2 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.parse Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(["open", url], check=True) How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dropover macOS Drag Shelf Utility AI Skill Guide (Claude)
Overview & Engine Architecture
Dropover is a modular macOS productivity utility that provides temporary floating drag shelves to aggregate files, images, snippets, and web links across Mission Control Spaces and full-screen apps. Dropover operates via custom NSPanel floating windows styled with .nonactivatingPanel and .canJoinAllSpaces attributes, intercepts cursor movements via a CGEventTap CoreGraphics mouse event monitor to detect cursor shake gestures, and ingests dragged payloads through NSPasteboard / NSItemProvider. Claude operates as a Principal macOS Application Developer and Workflow Automation Specialist, specializing in AppKit floating window lifecycle management, CoreGraphics event tap debugging, TCC Accessibility permission resolution, and Dropover URL Scheme (dropover://) scripting.
Dropover Window & Event Ingestion Architecture
┌─────────────────────────────────────────────────────────────┐
│ Dropover Engine Architecture │
│ │
│ Event Monitoring & Gesture Trigger Layer │
│ ├── `CGEventTap` Mouse Delta Vector Tracker (Shake Sensor) │
│ ├── Global Hotkey Listener (`NSEvent.addGlobalMonitor...`) │
│ └── TCC Accessibility & Input Monitoring Subsystem │
│ │
│ Floating Presentation & Shelf Layer │
│ ├── Floating `NSPanel` (`level = .floating`, Space Joining)│
│ ├── Quick Look Thumbnail Renderer (`QLThumbnailGenerator`) │
│ └── Multi-Shelf Manager (Group Actions, Cloud Uploading) │
│ │
│ Integration & IPC Protocol │
│ ├── Custom URL Scheme Handler (`dropover://action/...`) │
│ └── macOS Shortcuts & AppleScript Dispatch Interface │
└─────────────────────────────────────────────────────────────┘
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.
- 2mo ago Changed · -18 tokens per session 306052c3a9ff
- 2mo ago First seen · 133 lines · 41 tokens per session scan A 49f367364612
dropover is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,501 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
dropover compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dropoveralivirgo/Major-AI-Skills | Skill | 2 | today | MIT | A | 23 | Claude Code |
| anti-sleepsickn33/agentic-awesome-skills | Skill | 49k | today | MIT | A | 22 | Claude Code |
| cctop-setupst0012/cctop | Skill | 161 | 1mo ago | MIT | A | 31 | Claude Code |
| advogado-criminal-v2diegosouzapw/awesome-omni-skills | Skill | 172 | 4mo ago | MIT | A | 98 | Claude Code, Codex |
| ad-creative-v2diegosouzapw/awesome-omni-skills | Skill | 172 | 4mo ago | MIT | A | 85 | Claude Code, Codex |
| airtable-automation-v2diegosouzapw/awesome-omni-skills | Skill | 172 | 4mo ago | MIT | A | 77 | Claude Code, Codex |
| box-automationrootcastleco/rei-skills | Skill | 7 | today | none | A | 42 | Claude Code, Codex |