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.
/plugin marketplace add sinch/sinch-pluginsnpx agentmods add plugins/sinch/sinch-plugins/sinch-claude-plugingit clone --depth 1 https://github.com/sinch/sinch-pluginsGrade A, and why
sinch-claude-plugin 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.
What it actually says
{
"name": "sinch-claude-plugin",
"author": {
"name": "Sinch",
"email": "[email protected]",
"url": "https://github.com/sinch"
},
"version": "0.3.10",
"description": "Claude Code plugin for Sinch Conversation API (SMS, RCS, etc.)",
"homepage": "https://sinch.com/",
"repository": "https://github.com/sinch/sinch-plugins",
"license": "Apache-2.0",
"keywords": [
"Sinch",
"messaging",
"webhooks",
"api",
"sms",
"rcs",
"mcp",
"ai"
],
"commands": [
"./commands/config/sinch-mcp-setup.md",
"./commands/api/messages/send.md",
"./commands/api/senders/list.md",
"./commands/sinch-help.md",
"./commands/api/webhooks/list.md",
"./commands/api/webhooks/create.md",
"./commands/api/webhooks/update.md",
"./commands/api/webhooks/delete.md",
"./commands/api/webhooks/triggers.md"
],
"skills": "./skills",
"mcpServers": "./.mcp.json"
}
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 · 37 lines scan A f28c35246f61
sinch-claude-plugin is a plugin published in the GitHub repository sinch/sinch-plugins (6 stars, last pushed 20d 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 2026-08-31.
Other plugins, from other repositories
e2e
E2E test triage, debugging, and fix implementation toolkit.
snapsynapse-skill-provenance
Plugin marketplace listing 1 plugin: skill-provenance.
cloud-sql-sqlserver-marketplace
Plugin marketplace listing 1 plugin: cloud-sql-sqlserver.
alloydb-omni-marketplace
Plugin marketplace listing 1 plugin: alloydb-omni.
agent-rules-sync-local
Public plugin marketplace for agent-rules-sync utilities.
securedact-enforced
Local privacy enforcement for Claude Code. Checks prompts before model processing and blocks or requires review when SecuRedact detects protected information.