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 aduermael/herm --skill apple-contextgit clone --depth 1 https://github.com/aduermael/hermWrote 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/aduermael/herm/apple-context)<a href="https://agentmods.dev/skills/aduermael/herm/apple-context"><img src="https://agentmods.dev/badge/skills/aduermael/herm/apple-context/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/aduermael/herm/apple-context"><img src="https://agentmods.dev/badge/skills/aduermael/herm/apple-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 Agent Snooping · line 14 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 17 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 20 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00019 | $0.00793 |
| Opus 5.5 | $0.00008 | $0.00317 |
| Sonnet 5.5 | $0.00004 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
apple-context 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Context
Use this skill when the user asks about their calendar, schedule, events, availability, travel time, local context, nearby places, weather at their current position, or any request that depends on the device's current location.
How to load this skill
This file is markdown under /skills/apple-context/SKILL.md. Read it with:
print(fs.read("/skills/apple-context/SKILL.md"))
Do not require("apple-context"), require("/skills/apple-context"), require("/skills/apple-context/SKILL.md"), or any other require path. Skills are not Luau modules. The calendar and location modules are globals (listed by help()); call them directly after you understand the APIs below.
Permissions
- Prefer
calendar.help()orlocation.help()when a signature is unclear. - Calendar and location access states use
granted,denied, andundefinedthrough thestateoraccessfields. If access isundefined, calling the relevant request/current function may prompt the user. - If access is denied, stop using that capability and tell the user to enable access for Herm in iOS Settings or macOS System Settings. Do not repeatedly retry.
- Use only the minimum needed capability. Do not request calendar or location access unless it materially helps with the user's request.
- Print tables with
print(here)(ortostring(here)); both show nested JSON. Do not conclude "unavailable" from top-level nils alone—coords and place live underhere.location.
Calendar
Use calendar.status() before reading or changing events when practical. If a calendar operation reports denied access, explain that Calendar access must be enabled in Settings.
local status = calendar.status()
if status.state == "undefined" then
status = calendar.request_access("full")
end
List events with an explicit time range:
local events = calendar.events("2026-07-08T00:00:00Z", "2026-07-09T00:00:00Z", {limit = 50})
Create events only when the user asked you to add something or clearly approved it:
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.
- 1mo ago First seen · 76 lines · 19 tokens per session scan A ecbcc413297c
apple-context is a skill published in the GitHub repository aduermael/herm (233 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 793 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Gmail, Google Calendar, Drive, Docs, Sheets and Contacts for a connected Google account: read and search mail, send and reply, book and move meetings, find files, read and write Docs and Sheets, look people up. Use whenever the user mentions their email, inbox, calendar, meetings, Drive, a Google Doc or Sheet.
microsoft365
Outlook mail, calendar and OneDrive/SharePoint files of a connected Microsoft 365 (Exchange Online) account via m365: read, search, save attachments, send or reply and change meetings (held for approval), find, download and upload documents. Use for Outlook, office mail, Exchange, OneDrive or SharePoint.
iq
Workspace code search — one call from a question to ranked path:line anchors. Use for definitions, references, natural-language code questions, file skeletons, and git history.
example-notes
Leave a short note for the owner in the Example rail view, using the intentic-example CLI. Use when the user asks you to note, jot, remember or flag something lightweight for them to read later, and when you want to leave a breadcrumb about work you did that has no better home.
discord
Read, post, and react in the connected Discord server via the Discord REST API, and help the user invite the bot / finish setup. Use when the user asks to send a Discord message, list channels/servers, read or react to messages, or connect/invite the bot.
orca-cli
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the orca CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal"…