willitsend

A preflight checker for outbound SMS and iMessage drafts. It checks message wording and length before a text is sent.

In plain words
What is it for?
Use it before sending texts to new contacts or customers, especially when messages contain links, emojis, opt-out instructions, or other non-standard characters.
Why use it?
Mobile carriers may silently filter messages, and some characters can make a message use more segments than expected. Checking first helps catch these problems.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/abryfs/willitsend/skill
Any agent
npx skills add abryfs/willitsend --skill skill
Clone the repo
git clone --depth 1 https://github.com/abryfs/willitsend

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.00896
Opus 5 $0.00014 $0.00448
Sonnet 5 $0.00005 $0.00179
Haiku 4.5 $0.00003 $0.00090

Measured yesterday against content hash 5318381bf6ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

willitsend 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.

skill/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

willitsend — send texts that actually arrive

You are an AI agent that sends text messages. Carriers filter messages with rules they don't publish, and the messaging API will not warn you: a filtered message still returns "sent". This skill teaches you the documented rules so you compose compliant messages the first time, and gives you a tool to verify every draft before you send it.

Before you start

Run every outbound draft through the preflight_message tool before calling any send tool. It sends nothing, needs no API key, and answers in microseconds. If preflight_message is unavailable, apply the composition rules below by hand.

Composition rules (apply while writing, not after)

First message to a new contact must contain all three, or carriers may silently drop it:

  1. The brand or sender name ("Acme Dental: ...")
  2. An opt-in acknowledgment ("thanks for signing up for reminders")
  3. Opt-out instructions ("Reply STOP to unsubscribe.")

Later messages in the same conversation don't need to repeat 2 and 3.

Watch your characters. One emoji, smart quote, or non-breaking space re-encodes the entire message from GSM-7 (160 chars/segment) to UCS-2 (70 chars/segment). Segments are billing and quota units. Prefer straight quotes; skip the emoji unless it earns its cost.

iMessage features degrade silently. send_style effects, threaded replies, and image carousels drop without error when the recipient falls back to SMS. Check capabilities first or accept that the plain text is all that's guaranteed to arrive.

Avoid known filtering triggers: public URL shorteners (bit.ly, tinyurl), ALL-CAPS runs, $$$, and sex/alcohol/firearms/tobacco content, which carriers filter regardless of campaign registration.

Quick start

{
  "tool": "preflight_message",
  "arguments": {
    "body": "Acme: thanks for signing up. Your order shipped. Reply STOP to unsubscribe.",
    "is_first_message_to_contact": true,
    "brand_name": "Acme",
    "to_number": "+14155552671"
  }
}

Read the full file on GitHub · 68 lines

Changes

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.

  1. yesterday First seen · 68 lines · 27 tokens per session scan A 5318381bf6ec

Subscribe to this mod's changes

willitsend is a skill published in the GitHub repository abryfs/willitsend (1 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 896 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 2026-08-31.

Related

Other skills, from other repositories