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/hookdeck/webhook-skills/vapi-webhooksnpx skills add hookdeck/webhook-skills --skill vapi-webhooksgit clone --depth 1 https://github.com/hookdeck/webhook-skillsWrote 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/hookdeck/webhook-skills/vapi-webhooks)<a href="https://agentmods.dev/skills/hookdeck/webhook-skills/vapi-webhooks"><img src="https://agentmods.dev/badge/skills/hookdeck/webhook-skills/vapi-webhooks.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.02489 |
| Opus 5 | $0.00050 | $0.01244 |
| Sonnet 5 | $0.00020 | $0.00498 |
| Haiku 4.5 | $0.00010 | $0.00249 |
Grade A, and why
vapi-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 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vapi Webhooks
Vapi is a voice-AI agent platform (assistants place and receive phone calls,
plus chat/session APIs). Its webhook endpoint is called the Server URL. It is
bidirectional: most messages are fire-and-forget notifications, but four
message types require your endpoint to return a meaningful JSON response body —
not just 200 OK — because Vapi uses your answer to drive the live call.
When to Use This Skill
- How do I receive Vapi webhooks / configure the Server URL?
- How do I authenticate a Vapi webhook? Which header carries the secret?
- Why is there no fixed HMAC signature to verify?
- How do I respond to
assistant-request,tool-calls,transfer-destination-request, orknowledge-base-request? - How do I read the event type — why is it at
message.type, not the top level?
Verification (core)
Vapi has no single, fixed signature scheme. Authentication is opt-in and
per-endpoint — a Server URL has no authentication until you attach a
credential. Auth is configured in the dashboard as a Custom Credential
(referenced by credentialId on the server object) and comes in four flavours:
- Bearer Token (recommended, fully specified): Vapi sends
Authorization: Bearer <your-token>— a literal shared secret, nothing is hashed. - Legacy
X-Vapi-Secret: the same shared-secret idea with the header name set toX-Vapi-Secretand theBearerprefix disabled. This reproduces the older inlineserver.secretfield (kept for backward compatibility). - OAuth 2.0 (client credentials): Vapi fetches a token from your token
endpoint and presents it as
Authorization: Bearer <token>. - HMAC: configurable algorithm/header/encoding/payload-format. Verified
construction (2026-08-12): HMAC-SHA256 (hex) in
x-signature, secret verbatim. The Payload Format decides what's signed:{body}signs the raw body (recommended, self-contained, Hookdeck-compatible);{timestamp}.{body}signsx-timestamp+.+ raw body and requires the timestamp header on (see references/verification.md).
What ships with it
20 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.
- examples/express/.env.example 616 B
- examples/express/package.json 375 B
- examples/express/README.md 1.6 KB
- examples/express/src/index.js 6.1 KB runs code
- examples/express/test/webhook.test.js 6.0 KB runs code
- examples/fastapi/.env.example 542 B
- examples/fastapi/main.py 4.5 KB runs code
- examples/fastapi/README.md 1.4 KB
- examples/fastapi/requirements.txt 82 B
- examples/fastapi/test_webhook.py 4.6 KB runs code
- examples/nextjs/.env.example 542 B
- examples/nextjs/app/webhooks/vapi/route.ts 4.3 KB runs code
- examples/nextjs/package.json 487 B
- examples/nextjs/README.md 1.3 KB
- examples/nextjs/test/webhook.test.ts 4.2 KB runs code
- examples/nextjs/vitest.config.ts 140 B runs code
- references/overview.md 4.8 KB
- references/setup.md 3.7 KB
- references/verification.md 9.0 KB
- TODO.md 2.4 KB
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 · 200 lines · 100 tokens per session scan A 292f15ba9815
vapi-webhooks is a skill published in the GitHub repository hookdeck/webhook-skills (84 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 2,489 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…