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/bowlofarugula/texting/texting-sendnpx skills add bowlofarugula/texting --skill texting-sendgit clone --depth 1 https://github.com/bowlofarugula/textingWrote 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/bowlofarugula/texting/texting-send)<a href="https://agentmods.dev/skills/bowlofarugula/texting/texting-send"><img src="https://agentmods.dev/badge/skills/bowlofarugula/texting/texting-send.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 | $0.00054 | $0.01558 |
| Opus 5 | $0.00027 | $0.00779 |
| Sonnet 5 | $0.00011 | $0.00312 |
| Haiku 4.5 | $0.00005 | $0.00156 |
Grade B, and why
texting-send scanned grade B with 1 finding 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 4d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
never tell the user a dialog will review the send unless you've read How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/texting-send — send an iMessage
Arguments passed: $ARGUMENTS (free-form, e.g. "Sam let's confirm Friday"
or "+15551234567 the cut is ready")
Resolve the recipient
Pass the recipient straight to send_message — to accepts a phone in
+1 format, an Apple ID email, or a macOS contact name. Name resolution is
the engine's job: imsg looks the name up in the user's real macOS Contacts
itself, so don't pre-resolve names with your own Contacts/AddressBook
queries — that duplicates what the tool already does and adds steps the
user has to sit through. If you need to confirm who a name maps to (or
the name is ambiguous), match it against list_chats/read_messages
output — rows carry contact and display names — or simply ask the user for
the number/email. After a successful send to someone brand new (handle the
user supplied, no Contacts card), offer to add them to macOS Contacts
(scripts/add-contact.applescript "<Name>" "<handle>" — the one
genuinely manual step, since the engine has no contact-write; one-time
Contacts Automation prompt on first use).
Confirm, then send
Always show the exact recipient and exact message text and get a yes before sending. If the user dictated rough intent ("tell her I'm running late"), draft the text, show it, let them edit.
If the approval gate is enabled (approval: true in
~/.claude/texting/config.json), the send also pauses on a client dialog
showing the recipient and final text — only the user can answer it. A
"cancelled" tool result means they declined: stop there, don't retry or
rephrase to resend. If the result says the client can't show approval
prompts, relay that message as-is — the send was blocked on purpose
(fail-closed), not broken.
The gate never replaces your in-chat confirmation. It is opt-in
config that may be off, and a dialog you assumed would appear but doesn't
means the message is already gone — that exact failure has happened. Get
the explicit yes in chat before calling send_message, every time, and
never tell the user a dialog will review the send unless you've read
~/.claude/texting/config.json this session and seen approval: true.
When the gate IS on, it's the user's independent backstop on top of your
confirmation, not a substitute for 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.
- 4d ago First seen · 124 lines · 54 tokens per session scan B 95c05428b4fa
texting-send is a skill published in the GitHub repository bowlofarugula/texting (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,558 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
c-messaging
Send and read messages via imsg (iMessage) and wacli (WhatsApp). Supports sending to individuals or groups, reading recent conversations, and checking unread messages across both platforms.
imessage
Skill "imessage" from furkangonel/cowrangler, covering imessage, ön koşullar, ne zaman kullan, ne zaman kullanma and hızlı referans.
imsg
Read and send iMessages and SMS from the terminal via the imsg CLI.
imessage-group-create
Create a new group chat with contacts.
imessage-send
Send a message by name or number.
imessage-read
Read messages by contact or group.