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 agentmods add skills/sinch/sinch-plugins/sinch-api-batch-sendnpx skills add sinch/sinch-plugins --skill sinch-api-batch-sendgit clone --depth 1 https://github.com/sinch/sinch-pluginsWhat 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 | $0.00024 | $0.00677 |
| Opus 5 | $0.00012 | $0.00338 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
sinch-api-batch-send 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Send Batch Messages
Send a single message definition to up to 1000 recipients in one API call using the Sinch Conversation Batch API. Supports per-recipient parameter substitution (e.g. ${name}).
IMPORTANT: Execute this command directly. Do NOT generate script files. Perform the API call immediately.
Input
--message/-m: Message text; use ${param} for per-recipient substitution - required--recipients/-r: Comma-separated E.164 numbers, or path to file with one number per line - required--channel/-c: Channel (SMS, RCS, etc.) - optional, default SMS--params/-p: Optional JSON object or file mapping recipient index to parameters for substitution
Arguments: $ARGUMENTS
Instructions
Execute these steps directly - do not write code or scripts:
-
If $ARGUMENTS empty: ask for message text (with ${variable} placeholders if needed), recipient list (comma-separated or file), and channel. Otherwise parse.
-
Validate: --message (non-empty, may contain ${var}), --recipients (1-1000 identities). Parse recipients into array. Build recipient_and_params: each recipient has recipient.identified_by.channel_identities and optional parameters object for ${} substitution.
-
Get CONVERSATION_* env vars (project, region, app, key id/secret). Batch API base: https://{region}.conversationbatch.api.sinch.com. If missing, report "Sinch API is not configured."
-
Request body: app_id, message (e.g. text_message with text), recipient_and_params array. Do NOT use a "messages" array - Batch API expects one message + recipient_and_params.
-
POST https://{region}.conversationbatch.api.sinch.com/v1/projects/{projectId}/messages with OAuth2 Bearer token and JSON body.
-
On success: display "✅ Batch submitted" with batch_id and recipient count. Handle errors (400, 401, 429) with clear messages.
-
Handle all errors gracefully.
Examples
/sinch-api-batch-send --message="Hello ${name}, your code is ${code}" --recipients=+15551234567,+15559876543 --params='{"0":{"name":"Alice","code":"111"},"1":{"name":"Bob","code":"222"}}'
/sinch-api-batch-send -m "Hi!" -r +15551111111,+15552222222 --channel=SMS
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 · 56 lines · 24 tokens per session scan A 46a106705bb8
sinch-api-batch-send is a skill published in the GitHub repository sinch/sinch-plugins (6 stars, last pushed 20d ago), licensed Apache-2.0. It adds 24 tokens to every session and 677 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
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.
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.
agentrq
Learn creating, scheduling tasks, workspaces, and collaborating with human operators on the AgentRQ platform. Lead colony of AI agents using AgentRQ MCP tools.
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.
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.…
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…