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 benelser/imessage-tools --skill imessage-sendgit clone --depth 1 https://github.com/benelser/imessage-toolsWrote 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/benelser/imessage-tools/imessage-send)<a href="https://agentmods.dev/skills/benelser/imessage-tools/imessage-send"><img src="https://agentmods.dev/badge/skills/benelser/imessage-tools/imessage-send/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/benelser/imessage-tools/imessage-send"><img src="https://agentmods.dev/badge/skills/benelser/imessage-tools/imessage-send.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 | $0.00011 | $0.00357 |
| Opus 5.5 | $0.00004 | $0.00143 |
| Sonnet 5.5 | $0.00002 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
imessage-send 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.
What it actually says
Send a message using imessage-tools.
imessage-tools send $ARGUMENTS
The CLI handles:
- Contact name resolution (e.g. "John" -> phone number via macOS Contacts)
- Auto-detecting the correct service (iMessage, RCS, SMS) from chat history
- Service override with --sms, --rcs, or --imessage flags
- Sending to multiple contacts at once (1:many, comma-separated names)
- Sending to existing group chats by name (--group flag)
- Rich link previews via --preview (routes through Messages.app compose so URLs unfurl into og:title/og:image cards; briefly steals focus for ~6s per send)
Examples of how the user might invoke this:
/imessage-send "Jane Doe" "Hey what's up?"(1:1 send)/imessage-send "John Smith" "Let's grab lunch"(1:1 send)/imessage-send +15551234567 "Hello!"(1:1 by number)/imessage-send "Jane Doe" "Hello!" --rcs(1:1 with service override)/imessage-send "Jane Doe" "https://example.com/post" --preview(URL with rich preview)/imessage-send "Jane, John, Bob" "Meeting at 3"(1:many individual sends)/imessage-send --group "Work Chat" "Hello team!"(existing group chat)
Parse $ARGUMENTS to extract the recipient and message, then run the command.
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 · 32 lines · 11 tokens per session scan A c68d685dfe17
imessage-send is a skill published in the GitHub repository benelser/imessage-tools (3 stars, last pushed 6d ago), licensed MIT. It adds 11 tokens to every session and 357 once invoked, about $0.0000 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 2026-08-31.
Other skills, from other repositories
confirmation-protocol
Foresay-derived confirmation workflow for email operations. Use this skill BEFORE executing archive-mail with vague filters, composeemail (sending mail), deleteemail/moveemail in bulk, or any operation that touches 5+ emails. Show user a structured preview of "what I understood" before taking action, achieving…
email-search-disambiguation
A clarification step for email searches when a person, time period, direction, or scope is unclear. It presents specific possible meanings so the user can choose one.
munkel
Send ephemeral end-to-end-encrypted messages that appear in friends' MacBook notches, via the munkel CLI (macOS). Use when the user wants to message, ping, or notify someone in a Munkel channel, broadcast to a channel, or list Munkel channels and members.
stats
Show Captain Memo's corpus statistics (chunks per channel, observation counts, indexing progress, embedder info). Use when the user types /captain-memo:stats.
douyin-creator-scraping
Scrape video stats from the Douyin creator center (creator.douyin.com) using AppleScript to automate the user's logged-in Chrome. Covers the data-center/content page. Use when setting up periodic data collection, building a Douyin stats tracker, or automating export of video performance data.
observations
List recent captured session observations (the summarized voyage logs). Use when the user wants to see what Captain Memo has logged from past sessions.