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.
git 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/plugins/sinch/sinch-plugins/sinch-gemini-extension)<a href="https://agentmods.dev/plugins/sinch/sinch-plugins/sinch-gemini-extension"><img src="https://agentmods.dev/badge/plugins/sinch/sinch-plugins/sinch-gemini-extension/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/plugins/sinch/sinch-plugins/sinch-gemini-extension"><img src="https://agentmods.dev/badge/plugins/sinch/sinch-plugins/sinch-gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sinch-gemini-extension 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 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.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "sinch-gemini-extension",
"version": "0.3.15",
"description": "Gemini CLI extension for Sinch: Conversation API (SMS, RCS, WhatsApp), Voice, Verification, Fax, Numbers, 10DLC, Email (Mailgun, Mailjet), and more",
"author": {
"name": "Sinch",
"email": "[email protected]",
"url": "https://github.com/sinch"
},
"license": "Apache-2.0",
"homepage": "https://sinch.com/",
"repository": "https://github.com/sinch/sinch-plugins",
"mcpServers": {
"sinch": {
"command": "npx",
"args": [
"-y",
"@sinch/mcp"
],
"env": {
"CONVERSATION_PROJECT_ID": "${CONVERSATION_PROJECT_ID}",
"CONVERSATION_KEY_ID": "${CONVERSATION_KEY_ID}",
"CONVERSATION_KEY_SECRET": "${CONVERSATION_KEY_SECRET}",
"CONVERSATION_REGION": "${CONVERSATION_REGION}",
"CONVERSATION_APP_ID": "${CONVERSATION_APP_ID}"
},
"timeout": 15000
},
"sinch-docs": {
"httpUrl": "https://developers.sinch.com/mcp"
}
},
"settings": [
{
"name": "CONVERSATION_PROJECT_ID",
"description": "Your Sinch Conversation API Project ID",
"envVar": "CONVERSATION_PROJECT_ID"
},
{
"name": "CONVERSATION_KEY_ID",
"description": "Your Sinch Conversation API Key ID",
"envVar": "CONVERSATION_KEY_ID"
},
{
"name": "CONVERSATION_KEY_SECRET",
"description": "Your Sinch Conversation API Key Secret",
"envVar": "CONVERSATION_KEY_SECRET"
},
{
"name": "CONVERSATION_REGION",
"description": "Your Sinch region (us, eu, or br)",
"envVar": "CONVERSATION_REGION"
},
{
"name": "CONVERSATION_APP_ID",
"description": "Your Sinch Conversation API App ID",
"envVar": "CONVERSATION_APP_ID"
},
{
"name": "VOICE_APPLICATION_KEY",
"description": "Sinch Voice API Application Key",
"envVar": "VOICE_APPLICATION_KEY"
},
{
"name": "VOICE_APPLICATION_SECRET",
"descWhat ships with it
60 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- commands/sinch/api/10dlc/brands.toml 1.9 KB
- commands/sinch/api/10dlc/campaigns.toml 1.8 KB
- commands/sinch/api/batch/send.toml 2.6 KB
- commands/sinch/api/batch/status.toml 2.2 KB
- commands/sinch/api/contacts/list.toml 1.7 KB
- commands/sinch/api/fax/list.toml 1.1 KB
- commands/sinch/api/fax/send.toml 1.6 KB
- commands/sinch/api/messages/list.toml 2.4 KB
- commands/sinch/api/messages/send-card.toml 2.5 KB
- commands/sinch/api/messages/send-carousel.toml 2.2 KB
- commands/sinch/api/messages/send-choice.toml 2.3 KB
- commands/sinch/api/messages/send-location.toml 2.2 KB
- commands/sinch/api/messages/send-media.toml 2.6 KB
- commands/sinch/api/messages/send.toml 4.3 KB
- commands/sinch/api/numbers/lookup.toml 1.6 KB
- commands/sinch/api/numbers/search.toml 1.8 KB
- commands/sinch/api/provisioning/setup.toml 1.9 KB
- commands/sinch/api/senders/list.toml 3.1 KB
- commands/sinch/api/sip/trunks.toml 1.9 KB
- commands/sinch/api/templates/create.toml 2.1 KB
- commands/sinch/api/templates/delete.toml 1.4 KB
- commands/sinch/api/templates/list.toml 1.5 KB
- commands/sinch/api/verification/check.toml 1.9 KB
- commands/sinch/api/verification/start.toml 2.0 KB
- commands/sinch/api/voice/callout.toml 2.2 KB
- commands/sinch/api/voice/calls.toml 1.7 KB
- commands/sinch/api/webhooks/create.toml 5.3 KB
- commands/sinch/api/webhooks/delete.toml 3.8 KB
- commands/sinch/api/webhooks/list.toml 3.4 KB
- commands/sinch/api/webhooks/triggers.toml 3.0 KB
- commands/sinch/api/webhooks/update.toml 4.0 KB
- commands/sinch/config/auth.toml 1.8 KB
- commands/sinch/email/mailgun/inspect.toml 1.6 KB
- commands/sinch/email/mailgun/optimize.toml 1.7 KB
- commands/sinch/email/mailgun/send.toml 2.0 KB
- commands/sinch/email/mailgun/validate.toml 1.5 KB
- commands/sinch/email/mailjet/send.toml 1.8 KB
- commands/sinch/help.toml 2.1 KB
- README.md 11 KB
- skills/10dlc/references/campaign-fields.md 8.3 KB
- skills/10dlc/references/shared-policy.md 14 KB
- skills/10dlc/references/workflow.md 11 KB
- skills/10dlc/SKILL.md 17 KB
- skills/authentication/references/shared-policy.md 14 KB
- skills/authentication/SKILL.md 12 KB
- skills/conversation-api/references/batch.md 6.6 KB
- skills/conversation-api/references/scripts.md 2.5 KB
- skills/conversation-api/references/shared-policy.md 14 KB
- skills/conversation-api/references/templates.md 6.2 KB
- skills/conversation-api/references/webhooks/triggers/capability.md 6.5 KB
- skills/conversation-api/references/webhooks/triggers/contact-management.md 11 KB
- skills/conversation-api/references/webhooks/triggers/conversation-lifecycle.md 7.5 KB
- skills/conversation-api/references/webhooks/triggers/event-delivery.md 5.6 KB
- skills/conversation-api/references/webhooks/triggers/event-inbound.md 5.3 KB
- skills/conversation-api/references/webhooks/triggers/message-delivery.md 6.3 KB
- skills/conversation-api/references/webhooks/triggers/message-inbound.md 5.7 KB
- skills/conversation-api/references/webhooks/triggers/message-submit.md 5.8 KB
- skills/conversation-api/references/webhooks/triggers/opt-inout.md 6.2 KB
- skills/conversation-api/references/webhooks/triggers/smart-conversations.md 8.4 KB
- skills/conversation-api/references/webhooks/triggers/system-events.md 7.8 KB
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.
- 2d ago First seen · 110 lines scan A 27da0fc17411
sinch-gemini-extension is a plugin published in the GitHub repository sinch/sinch-plugins (6 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-15.
Other plugins, from other repositories
alloydb
Create, connect, and interact with an AlloyDB for PostgreSQL database and data.
merit-aktiva-workspace
Merit Aktiva accounting + Merit Palk payroll for Claude Code — full API coverage via the elnora-merit CLI, plus how-to skills for the correct Merit procedure: accounting (sales/purchase invoices, payments/bank reconciliation, VAT/KMD, reports, reverse charge) and payroll (employees & contracts, monthly…
kahea
Deterministic HTTP and finite WebSocket planning, testing, and policy-gated execution for AI agents.
xonovex-skill-hono
Xonovex Hono skills.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.