A command reference for Sinch, a communications service that provides messaging, voice calls, and phone verification through software. It lists the available commands without creating files.

Use it to review commands for sending SMS or rich messages, managing webhooks, sending batches, using templates, and handling voice or phone verification.

It gives developers a quick way to see what Sinch operations are available without searching through separate documentation.

sinch-help — Skill by sinch

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/sinch/sinch-plugins/sinch-help

Any agent

npx skills add sinch/sinch-plugins --skill sinch-help

Clone the repo

git clone --depth 1 https://github.com/sinch/sinch-plugins

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 754 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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.

Model	Per session	Once invoked
Fable 5	$0.00015	$0.00754
Opus 5	$0.00008	$0.00377
Sonnet 5	$0.00003	$0.00151
Haiku 4.5	$0.00002	$0.00075

Measured 3d ago against content hash 410e4e9c9f1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

sinch-help scanned grade B 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 3d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

**Tip**: Run any command with no arguments for interactive mode. Export credentials in your shell (see `/sinch-config-auth`) before starting `agy`.

plugins/sinch-antigravity-plugin/skills/sinch-help/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sinch Antigravity Plugin — Command Overview

Display a concise overview of all Sinch commands available in this plugin. Do NOT generate script files. Output the overview directly.

Instructions

Display the following structure directly - do not write code or scripts:

Messaging (Conversation API)
- /sinch-api-messages-send — Send text (SMS/RCS)
- /sinch-api-messages-send-media — Send media (image, video, document)
- /sinch-api-messages-send-card — Send RCS rich card
- /sinch-api-messages-send-carousel — Send RCS carousel
- /sinch-api-messages-send-choice — Send choice/buttons
- /sinch-api-messages-send-location — Send location
- /sinch-api-messages-list — List messages
- /sinch-api-senders-list — List active numbers (Numbers API)
Webhooks
- /sinch-api-webhooks-create, list, update, delete, triggers
Batch & Templates
- /sinch-api-batch-send — Send batch (up to 1000 recipients)
- /sinch-api-batch-status — Batch job status
- /sinch-api-templates-list, create, delete
Voice & Verification
- /sinch-api-voice-callout — TTS outbound call
- /sinch-api-voice-calls — Call info
- /sinch-api-verification-start — Start phone verification (SMS/Flashcall/Call)
- /sinch-api-verification-check — Report verification code
Fax & Numbers
- /sinch-api-fax-send, list
- /sinch-api-numbers-lookup — Number lookup (carrier, etc.)
- /sinch-api-numbers-search — Search available numbers to rent
Email
- /sinch-email-mailgun-send, validate, inspect, optimize
- /sinch-email-mailjet-send
Infrastructure & Admin
- /sinch-api-10dlc-brands, campaigns
- /sinch-api-sip-trunks
- /sinch-api-provisioning-setup — WhatsApp/RCS senders
- /sinch-api-contacts-list
Config & Help
- /sinch-config-auth — Authentication setup guide
- /sinch-help — This overview
Product guides
- /10dlc — 10DLC brands and campaigns
- /authentication — Sinch authentication overview
- /conversation-api — Conversation API guide
- /elastic-sip-trunking — Elastic SIP Trunking
- /fax — Fax API
- /in-app-calling — In-app calling
- /mailgun — Mailgun overview
- /mailgun-inspect — Mailgun HTML inspection
- /mailgun-optimize — Mailgun deliverability optimization
- /mailgun-validate — Mailgun email validation
- /number-lookup — Number Lookup API
- /numbers — Numbers API
- /provisioning-api — Provisioning (WhatsApp/RCS senders)
- /verification-api — Verification API
- /voice-api — Voice API

Read the full file on GitHub · 75 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.

3d ago First seen · 75 lines · 15 tokens per session scan B 410e4e9c9f1e

Subscribe to this mod's changes

sinch-help is a skill published in the GitHub repository sinch/sinch-plugins (6 stars, last pushed 21d ago), licensed Apache-2.0. It adds 15 tokens to every session and 754 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ai claude-code cli gemini gemini-extension sms

triage-issue

Investigate a reported bug to root cause, then emit a TDD-shaped fix plan as an issue artifact. Trigger when the user reports a bug, says "triage", asks for issue investigation, or wants a fix plan before code changes.

OutlineDriven/odin-gemini-cli-extension · 54 tokens

git-guardrails-claude-code

Install a Claude-Code PreToolUse hook that blocks destructive git commands (push variants including force-push, hard reset, force clean, branch -D, checkout/restore overwrites) before Bash runs them. Use when the user wants git safety rails, force-push prevention, or repository-wipe protection.

OutlineDriven/odin-gemini-cli-extension · 71 tokens

agentrq

Learn creating, scheduling tasks, workspaces, and collaborating with human operators on the AgentRQ platform. Lead colony of AI agents using AgentRQ MCP tools.

agentrq/agentrq-gemini-extension · 35 tokens

duet

Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.

OutlineDriven/odin-gemini-cli-extension · 73 tokens

explore

Read-only codebase exploration: discovery, structural reading, and emission of architecture/pattern/tooling/dependency summaries. Use to understand existing code, map files, trace function flow, locate symbols, or build pre-implementation context. Uses a staged 1/3/5 Explore-agent escalation protocol scaled to scope.…

OutlineDriven/odin-gemini-cli-extension · 122 tokens

deps-upgrade

Dependency-upgrade campaign — outdated scan, batch-by-severity, breaking-change remediation, lockfile audit. Use when CVEs require remediation, when a major upstream version lands, when stack compatibility forces a sweep, or on a scheduled (quarterly) hygiene cadence. CVE-driven bumps consume security audit findings…

OutlineDriven/odin-gemini-cli-extension · 68 tokens

sinch-help