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 sinch/sinch-plugins --skill sinch-api-messages-send-cardgit clone --depth 1 https://github.com/sinch/sinch-pluginsWrote 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/sinch/sinch-plugins/sinch-api-messages-send-card)<a href="https://agentmods.dev/skills/sinch/sinch-plugins/sinch-api-messages-send-card"><img src="https://agentmods.dev/badge/skills/sinch/sinch-plugins/sinch-api-messages-send-card/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/sinch/sinch-plugins/sinch-api-messages-send-card"><img src="https://agentmods.dev/badge/skills/sinch/sinch-plugins/sinch-api-messages-send-card.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 | $0.00020 | $0.00634 |
| Opus 5 | $0.00010 | $0.00317 |
| Sonnet 5 | $0.00004 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
sinch-api-messages-send-card 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send RCS Card Message
Send a rich card message (title, description, image, optional buttons) to a recipient via the Sinch Conversation API. Best supported on RCS; other channels may receive a transcoded version.
IMPORTANT: Execute this command directly. Do NOT generate script files. Perform the API call immediately.
Input
--to/-t: Recipient phone number (E.164) - required--title/-T: Card title - required--description/-d: Card description text - optional--image-url/-i: URL of card image - optional--choices/-C: Comma-separated button labels (e.g., "Learn More,Contact Us") - optional
Arguments: $ARGUMENTS
Instructions
Execute these steps directly - do not write code or scripts:
-
If $ARGUMENTS empty: ask for recipient, title, description, image URL, and optional choices. Otherwise parse arguments.
-
Validate: --to (E.164), --title (non-empty). Optional: description, image-url (HTTPS), choices (comma-separated strings).
-
Try MCP tool for sending card/rich message if available (e.g. send-card or equivalent). On success display result and exit.
-
If MCP not available: get CONVERSATION_* env vars. If missing, report "Sinch API is not configured."
-
Build message.card_message: title, description (if provided), media_message with url (if image-url), choices array from --choices (each: text_message.text, postback_data). Recipient via channel_identities (channel RCS or as specified).
-
POST https://{region}.conversation.api.sinch.com/v1/projects/{projectId}/messages:send with OAuth2, body: app_id, recipient, message.
-
On success: "✅ Card message sent!" with message ID. Handle errors with clear messages.
-
Handle all errors gracefully.
Examples
/sinch-api-messages-send-card --to=+14155551234 --title="Welcome" --description="Thanks for signing up" --image-url=https://example.com/promo.jpg
/sinch-api-messages-send-card -t +14155551234 -T "Sale" -d "50% off" -C "Shop Now,Details"
API Reference
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.
- 9d ago First seen · 59 lines · 20 tokens per session scan A 7aad17686013
sinch-api-messages-send-card is a skill published in the GitHub repository sinch/sinch-plugins (6 stars, last pushed 27d ago), licensed Apache-2.0. It adds 20 tokens to every session and 634 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.
Other skills, from other repositories
effort
Estimates the implementation effort required to address the given issue.
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
critique
Expertise in auditing and fixing repository scripts and GitHub Actions workflows to ensure technical robustness and security.
prs
Expertise in managing the Git and GitHub Pull Request lifecycle, including staging changes, generating PR descriptions, and branch management.
pirate-skill
You are a pirate. Respond to everything in pirate speak. Always mention "Arrr".
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.