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 svix/ai --skill svix-sending-webhooksgit clone --depth 1 https://github.com/svix/aiWrote 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/svix/ai/svix-sending-webhooks)<a href="https://agentmods.dev/skills/svix/ai/svix-sending-webhooks"><img src="https://agentmods.dev/badge/skills/svix/ai/svix-sending-webhooks/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/svix/ai/svix-sending-webhooks"><img src="https://agentmods.dev/badge/skills/svix/ai/svix-sending-webhooks.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 | $0.00138 | $0.01052 |
| Opus 5 | $0.00069 | $0.00526 |
| Sonnet 5 | $0.00028 | $0.00210 |
| Haiku 4.5 | $0.00014 | $0.00105 |
Grade A, and why
svix-sending-webhooks 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 11d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mode
Default to building. Use the routing table below and write the code. A request to integrate Svix is a request for working code.
Plan only when the user explicitly asks for one. "Write me a plan", "how should I approach this?", "design this before we code", "what's the architecture?" — that, and nothing weaker, sends you to <references/planning.md>, which is plan-first: no code until the plan is confirmed.
Size is not a trigger. Multi-tenant routing, an event type catalog, App Portal embedding, a migration — build them. Don't answer a request for code with a document, and don't stop to ask whether they'd like a plan first; if they wanted one they'd have said so.
One thing to say out loud while you build, without pausing for permission: replacing an existing webhook sender changes the signature your customers verify against. Their handlers break on cutover unless they re-verify with Svix's scheme. Flag that in your summary, note it in the code where the cutover happens, and keep going — see the migration guidance in <references/dispatch-questions.md> for what a cutover has to cover.
Integration routing (Building)
First, check whether Svix is already wired into the repo. Look for a Svix SDK in the language's manifest (package.json, pyproject.toml, go.mod, Gemfile, …) and for SVIX_AUTH_TOKEN in config or env files. If it isn't there, start with <references/quickstart.md> — the setup steps come before anything below. If it is, skip the quickstart; that work is done.
| Building… | Recommended approach | Details |
|---|---|---|
| Adding Svix to a project for the first time | Quickstart setup path | <references/quickstart.md> |
| Sending webhooks to your customers | Dispatch (message.create) |
<references/dispatch.md> |
| Receiving third-party webhooks | Ingest Sources | <references/ingest.md> |
| Multi-tenant routing within one customer | Channels (not Event Types) | <references/dispatch.md> |
| Embedded webhooks management for endpoints, logs, replay | App Portal session URL | <references/dispatch.md> |
| Monitoring your customers' endpoint health | Operational webhooks | <references/dispatch.md> |
| Local development against the cloud | svix listen |
<references/cli.md> |
| Shell scripting, bulk ops, one-off provisioning | CLI + jq |
<references/cli.md> |
What ships with it
9 files 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.
- 11d ago First seen · 59 lines · 138 tokens per session scan A 96a4fa64eb79
svix-sending-webhooks is a skill published in the GitHub repository svix/ai (18 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 1,052 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
suap-api
Consume the SUAP (Sistema Unificado de Administração Pública) REST API v2 used by Brazilian federal institutes (IFRN, IFF, IFS, etc.) — obtain a JWT via /api/v2/autenticacao/token/, discover real endpoints via /api/openapi.json, and pull student data (boletim, períodos letivos, dados do aluno). Covers the WAF…
financas-app
Corrigir, estender e validar o app de finanças pessoais (Node/Express + EJS + MongoDB + Docker). Cobre a arquitetura de porta única 4460 com demo via /demo, o fluxo de correção de UI (rebuild de AMBOS os containers + ASSETVERSION), validação por browser headless no IP docker, verificação ad-hoc e o padrão…
suap-iff-api
Authenticate to and consume the SUAP IFF (Instituto Federal Fluminense) API v2 from the CLI — obtain the JWT access/refresh token via matricula+senha, then fetch student data (periodos letivos, dados do aluno, boletim). Use when the user has a suap.iff.edu.br matricula+senha and wants to extract academic data…
express-csp-runtime-config
How to pass server-side runtime config (API prefix, feature flags, user id, CSRF token) from an Express/EJS app to client JS when a strict Content-Security-Policy is in force (helmet default scriptSrc self, with no unsafe-inline). Use this whenever you need to inject a value the browser JS must read at runtime, but…
nextjs-app-router-patterns
Architect and implement modern Next.js App Router applications with Server Components (RSC), Server Actions, Parallel/Intercepting Routes, and Streaming SSR.
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.