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 agentmods add skills/omarshahine/findmy-cli/findmynpx skills add omarshahine/findmy-cli --skill findmygit clone --depth 1 https://github.com/omarshahine/findmy-cliWrote 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/omarshahine/findmy-cli/findmy)<a href="https://agentmods.dev/skills/omarshahine/findmy-cli/findmy"><img src="https://agentmods.dev/badge/skills/omarshahine/findmy-cli/findmy.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.01352 |
| Opus 5 | $0.00037 | $0.00676 |
| Sonnet 5 | $0.00015 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
findmy 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 6d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find My Skill
Two tools available, both shell out to the findmy binary which drives
FindMy.app via screen capture and Vision OCR. Read-only — never mutates
FindMy.app state.
Privacy & consent (read first)
- These tools can only read people who have already opted in to share their location with this Mac's Apple ID in Apple's Find My. Sharing is mutual and the other person controls it — the plugin cannot see anyone who has not consented, and does not bypass any Apple access control.
- Returns coarse location only (city/state, staleness, distance), the same data FindMy.app shows the signed-in user. No precise coordinates, history, or background tracking.
- Intended for the Mac's owner to locate consenting friends and family. Not a surveillance tool — never use it to monitor or track someone without their knowledge and consent.
- When a result is
Pausedor stale, surface that plainly; the position may be hours or days old, and reporting it as current is misleading.
When to use
- "Where is Omar?" → call
findmy_personwithname: "Omar" - "Is Sarah home yet?" → call
findmy_personwithname: "Sarah" - "How far away is Mike?" → call
findmy_personwithname: "Mike" - "Anyone near downtown?" → call
findmy_people, then read the locations - "Where is everyone?" → call
findmy_people - "Where am I?" → call
findmy_personwithname: "Me". The first entry in the FindMy People sidebar is always the owner of this Mac, labeled"Me". Same shape as other entries but with nostalenessordistance.
Using location to drive other actions
Location is high-trust data — knowing where someone is can unlock useful follow-ups: "you're near Pike Place, want me to book a table at Matt's?", "Sarah's still 7 mi away, push the dinner reservation by 30 min", "you're home, run the arrival routine."
Before chaining a location result into a mutating action (booking, sending a message, triggering a routine, ordering something), ask the user for explicit approval first. State the location you used, the action you'd take, and wait for confirmation. Examples:
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.
- 6d ago First seen · 133 lines · 74 tokens per session scan A 6debfe87bd04
findmy is a skill published in the GitHub repository omarshahine/findmy-cli (54 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 1,352 once invoked, about $0.0004 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
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.
visualize
Render a polished visual inline in the chat as part of your answer — a diagram, a chart, an interactive explainer, or a UI mockup. Load it proactively whenever an explanation would land better as a picture than as prose. Do not wait to be asked.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
triage-issue-local
Repo-specific triage guidance for warp. Only the categories declared overridable by the core triage-issue skill may be specialized here.