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 OpenMinis/MinisSkills --skill apple-remindersgit clone --depth 1 https://github.com/OpenMinis/MinisSkillsWrote 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/openminis/minisskills/apple-reminders)<a href="https://agentmods.dev/skills/openminis/minisskills/apple-reminders"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/apple-reminders/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/openminis/minisskills/apple-reminders"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/apple-reminders.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 133 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00255 | $0.03624 |
| Opus 5 | $0.00128 | $0.01812 |
| Sonnet 5 | $0.00051 | $0.00725 |
| Haiku 4.5 | $0.00026 | $0.00362 |
Grade A, and why
apple-reminders 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Reminders
Overview
apple-reminders is a built-in native command backed by EventKit. It exposes five
verbs — list, create, update, complete, delete — over reminder titles,
due dates, lists, priorities, notes, and completion state. Every call prints one
JSON envelope to stdout.
The command is small, but three of its behaviours fail silently and successfully:
a mistyped list name, an unparseable due date, and a truncated read all return
ok: true. Most of this skill exists to keep those three from turning into wrong
answers or misplaced tasks. Read references/cli.md for the full contract — flags,
JSON shapes, error codes, and the exact date grammar.
apple-reminders list [--incomplete|--completed] [--list <name>] [--limit <N>]
apple-reminders create --title <t> [--due <dt>] [--list <name>] [--priority <0-9>] [--notes <text>]
apple-reminders update --id <id> [--title <t>] [--due <dt>] [--list <name>] [--priority <0-9>] [--notes <text>]
apple-reminders complete --id <id> [--undo]
apple-reminders delete --id <id>
Add --compact to minimize JSON, -q to print only the data field. Prefer
--compact for large reads to save context.
Run apple-reminders --help when you are unsure whether an option still exists —
the help text is authoritative for the build you are running, and this reference may
lag it.
The command is iOS-only. If it is not on PATH, say that reminder access is not
available on this device. Do not reach for a workaround: there is no supported path
to Reminders data outside this command, so do not try to install an adapter, script
around it, or read Reminders storage directly.
Three checks before any write
These are not style preferences. Each one prevents a wrong result that the command itself reports as success.
1. Resolve the exact list title from a read. Never pass a guessed name.
--list matches by case-insensitive substring, so --list Work also matches
Workout, and when several titles match, EventKit's calendar order decides which
one wins — not you. Worse, on create an unmatched --list is not an error: the
reminder is silently saved to the default list and the response still says
ok: true. So read first, pick the exact title, then write, then confirm the
list field in the response is the list you intended.
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.
- 9d ago First seen · 275 lines · 255 tokens per session scan A 6331557e24e3
apple-reminders is a skill published in the GitHub repository OpenMinis/MinisSkills (404 stars, last pushed 5d ago), licensed MIT. It adds 255 tokens to every session and 3,624 once invoked, about $0.0013 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.