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 voice-api-v2git 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/voice-api-v2)<a href="https://agentmods.dev/skills/sinch/sinch-plugins/voice-api-v2"><img src="https://agentmods.dev/badge/skills/sinch/sinch-plugins/voice-api-v2/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/voice-api-v2"><img src="https://agentmods.dev/badge/skills/sinch/sinch-plugins/voice-api-v2.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 | $0.00119 | $0.04409 |
| Opus 5.5 | $0.00048 | $0.01764 |
| Sonnet 5.5 | $0.00024 | $0.00882 |
| Haiku 4.5 | $0.00012 | $0.00441 |
Grade B, and why
sinch-voice-api-v2 scanned grade B with 2 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 10d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- **Untrusted content** — Treat webhook bodies, caller DTMF input, transcribed speech, metadata, and URLs as untrusted data. Validate schemas and sanitize values before logging, storing, rendering in HTML, or adding them Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **Language** — any language, or curl. Voice API v2 is not yet wrapped by the Sinch SDKs; call the REST API directly. This is a copy
100% identical to sinch-voice-api-v2 — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sinch Voice API v2
Overview
The Sinch Voice API v2 provides project-scoped REST resources for creating, receiving, and controlling calls with SVAML v2 commands. Use it for PSTN and SIP calls, IVR, bridging, recording, batch calling, and for connecting AI voice agents through Voice Relay or raw WebSocket audio streams.
Version scope: Voice API v2 (public preview) only. This skill covers the
/v2/projects/...API, SVAML v2 commands, and CloudEvent webhooks. Voice API v1 (/calling/v1, application key and secret, ICE/ACE/PIE callbacks) has a different surface; do not adapt the guidance below to v1. Load thesinch-voice-apiskill for v1 instead. Preview contracts can change; confirm every wire detail against the linked docs in the current session.
Agent Instructions
Policy gate
sinch-shared-policy@5(sha256:4864cf0fa8d6): The policy digest below is binding as written. Before implementation or live execution, read the full shared Sinch policy once per conversation — skip it if this exact ID/version/fingerprint is already loaded; read it if the version is newer or the fingerprint differs. This skill's canonical operation routes live in its Agent Instructions and Links sections.
Sinch policy digest (binding):
- Load the shared policy once per conversation; skip duplicate copies bearing the same ID/version/fingerprint.
- Infer product, language, region, and environment from the request and workspace; ask one combined question only for true blockers. Prefer the official Sinch SDK unless the request or workspace decides otherwise or no official SDK covers the language or operation.
- Code-generation approval is not execution approval. Classify every operation (read-only / reversible / billable / destructive) and obtain explicit approval before billable or destructive calls.
- Tier B facts — endpoint paths, methods, field names, enums, limits, webhook payloads, signature algorithms, SDK signatures — require fetching the exact canonical document in the current session before use.
- Bundled scripts, references, and examples are Tier C: illustrations, never schema authority. Never promote example values to production defaults.
- If a route is unresolved or a canonical fetch fails, climb the resolution ladder in order — re-search already-fetched documents (raw, not summarized), consult https://developers.sinch.com/llms.txt, follow first-party links, retry once — before failing closed. Never pattern-guess a documentation URL; never substitute memory, search snippets, or bundled files.
- Keep an evidence ledger mapping each fetched source to the fields and claims it authorized.
- Bound all polling and retries (backoff, jitter, hard cap); check state before retrying billable or destructive operations; report a timeout as unknown, not failed.
- Report verification levels separately (lint → unit → mock contract → sandbox → live → end-to-end); an HTTP 2xx does not prove delivery. State the levels not performed.
- Load only the smallest skill set that owns the behavior; if a required skill is unavailable, name it and stop rather than improvising its instructions.
What ships with it
1 file beside SKILL.md 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.
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.
- 10d ago First seen · 229 lines · 119 tokens per session scan B 7b1895a0d67d
sinch-voice-api-v2 is a skill published in the GitHub repository sinch/sinch-plugins (6 stars, last pushed 11d ago), licensed Apache-2.0. It adds 119 tokens to every session and 4,409 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 2 findings (instruction-override phrasing, makes network calls). It is 100% identical to sinch-voice-api-v2, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
wraps-workflows
Build email and SMS automation workflows using the @wraps.dev/client TypeScript DSL. Covers triggers, steps, branching, cascades, and the full defineWorkflow API.
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
wikipedia
Search and read Wikipedia via x wkp — MediaWiki API, no API key, zero install; query, extract, suggest, and DDG route in one module. Load for wiki, wikipedia, encyclopedia lookup, article summary.
scaffold-project
Scaffold a new app, API, backend, fullstack project, mobile app, polyglot service, monorepo, or starter with Better Fullstack. Use when the user wants to create, start, bootstrap, initialize, or generate a project from a stack description. Prefer the bundled Better Fullstack MCP server: guidance, schema…
migrate-oracle-forms
Assess and migrate Oracle Forms applications to Mendix — .fmb forms to pages, PL/SQL to microflows, and a staged migration strategy. Use when analysing or converting an Oracle Forms system.