openapi-messaging

A set of instructions for sending SMS, one-time passcodes, certified email, bulk certified mail, and physical mail through Openapi services. Some options are specific to Italy or Spain.

In plain words
What is it for?
Use it to add text notifications, login codes, Italian certified email, registered letters, telegrams, or other supported postal communications to an application.
Why use it?
It explains how to send different kinds of communication and track delivery while accounting for services that may cost money.

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

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 664 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00072 $0.00664
Opus 5 $0.00036 $0.00332
Sonnet 5 $0.00014 $0.00133
Haiku 4.5 $0.00007 $0.00066

Measured 2d ago against content hash 897b65d45838, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openapi-messaging scanned grade A 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST https://sms.openapi.com/IT-messages \
skills/openapi-messaging/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Openapi messaging & communications

All services use a Bearer token (see the openapi-auth skill). Every send is an outward-facing, paid action: always confirm recipient, content and cost with the user before sending.

SMS v2 — https://sms.openapi.com

  • POST /IT-messages (Italy), POST /ES-messages (Spain), POST /WW-messages (worldwide)
  • POST /otp — OTP verification messages
  • GET /messages, GET /messages/{id} — sent messages and delivery status

Features: custom sender, E.164 validation, GSM-7/UCS-2 detection with automatic segmentation, dry_run for free testing, webhook delivery callbacks. Messages expire after 48h (status EXPIRED). Worldwide pricing is computed post-sending and requires a minimum credit balance. SMS v1 (ws.messaggisms.com) is deprecated.

curl -s -X POST https://sms.openapi.com/IT-messages \
  -H "Authorization: Bearer $OPENAPI_TOKEN" \
  -H 'Content-Type: application/json' \
  -d '{"sender": "MyBrand", "body": "Hello!", "recipients": ["+39333…"], "options": {"dry_run": true}}'

PEC (certified e-mail) — https://pec.openapi.it

Activate and manage Legalmail certified e-mail boxes (creation, renewal, configuration).

Massive REM — https://ws.pecmassiva.com

Bulk certified e-mail sending; check delivery-verification and receipt-verification status per message.

Postal Service — https://ws.ufficiopostale.com

Physical mail via Poste Italiane. Same pattern per product: POST /<product>/ (create, returns prices) → PATCH /<product>/{id} (confirm, or pass autoconfirm: true) → status callbacks to your callback URL → GET /<product>/{id}/accettazione (acceptance receipt).

Products: raccomandate and raccomandate_smart (registered mail), telegrammi, ordinarie, prioritarie, posta_massiva, posta_massiva_top, atti_giudiziari (judicial acts, with digital return receipt). Helpers: GET /pricing/, GET /nazioni/, GET /covers/, GET /dug/. Error responses include data.wrong_fields[] pinpointing invalid fields.

Read the full file on GitHub · 39 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. 2d ago First seen · 39 lines · 72 tokens per session scan A 897b65d45838

Subscribe to this mod's changes

openapi-messaging is a skill published in the GitHub repository openapi/openapi-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 664 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.