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 notforyou23/home23 --skill contactgit clone --depth 1 https://github.com/notforyou23/home23Wrote 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/notforyou23/home23/contact)<a href="https://agentmods.dev/skills/notforyou23/home23/contact"><img src="https://agentmods.dev/badge/skills/notforyou23/home23/contact/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/notforyou23/home23/contact"><img src="https://agentmods.dev/badge/skills/notforyou23/home23/contact.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 | $0.00026 | $0.00727 |
| Opus 5 | $0.00013 | $0.00364 |
| Sonnet 5 | $0.00005 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
Contact 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 yesterday.
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.
What it actually says
Contact
Use this skill when the work is in the actual day, not inside Home23.
When to use
- calendar, reminders, notes, Mail, Finder
- what needs jtr / what changed / what's waiting
- Home Assistant lights, scenes, fans, music, or (with confirm) locks/garage/climate
- "take this thing and make it part of my world"
- completing a web workflow, not just fetching text
- iOS shortcuts
- drafting or sending a message
Workflow
- Sense first.
attention_scanormac_read/house_get_entity. - If acting, dry-run or preview. Physical, shortcut, and send paths need
confirm=truewhen they are policy-lane or outbound. - Act.
house_call_safe_serviceobserves, commands, then observes again. API 200 is not proof the door closed. - Keep provenance.
capture_artifactarchives the original.comms_draftbeforecomms_send.
Tools
mac_read— calendar | reminders | notes | mail | findermac_write— create_reminder (ok) or run_shortcut (confirm)attention_scan— ranked needs-you list; degraded-honest if a Mac surface is downhouse_get_entity/house_get_area/house_historyhouse_call_safe_service/house_scene_activate/house_verify_changecapture_artifact— ingest | retrieve | inboxbrowser_workflow— open snapshot; submit requires confirmphone_run_shortcut— allowlisted iOS shortcuts, confirm requiredcomms_draft/comms_send— telegram send only, confirm required
Gotchas
- Do not expose arbitrary AppleScript. Named surfaces only.
- Thermostat, cameras, garage, locks, security, water:
confirm=true. - Mail and calendar need macOS permission; if a surface fails, report it, do not invent events.
- Do not auto-send. Preview the exact recipient and body.
- Share-sheet drops land in
workspace/intake. Ingest them withcapture_artifact.
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.
- yesterday First seen · 85 lines · 26 tokens per session scan A 603f2a978f5f
Contact is a skill published in the GitHub repository notforyou23/home23 (11 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 727 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 2026-09-10.
Other skills, from other repositories
local-access
A guide for controlling a Mac through local applications such as Calendar, Contacts, Mail, Reminders, Finder, and a web browser. It describes the command format for requesting these actions.
gigamail
An email and calendar connection for an OpenClaw agent. It can read, search and draft messages, while sending, deleting and changing the calendar require approval from a person outside the agent.
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
brain_dump
Capture unstructured thoughts and organize them into structured notes saved to memory.
workflow
A workflow skill for embedded-device projects that plans and runs building, flashing, debugging, observing, and diagnosis tasks.
remindme
⏰ simple Telegram reminders for OpenClaw. cron, zero dependencies.