Agentline Webhooks logo

Agentline Webhooks

Organization
hookdeck
agentline-webhooks

Receive and verify AgentLine webhooks. Use when setting up AgentLine (AI phone agent) webhook handlers, debugging X-Webhook-Signature verification, or handling events like call.received, call.utterance, call.completed and sms.received.

Overview

Publisherhookdeck
Repositorywebhook-skills
Skill nameagentline-webhooks
Stars
97
Forks
17
Bundled files
13
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 13 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hookdeck on GitHub. Read the source before you install it.

Installation

Install the Agentline Webhooks AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hookdeck/webhook-skills/tree/main/skills/agentline-webhooks
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hookdeck/webhook-skills.git /tmp/webhook-skills
mkdir -p .claude/skills
cp -r /tmp/webhook-skills/skills/agentline-webhooks .claude/skills/agentline-webhooks
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agentline Webhooks in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agentline Webhooks on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agentline Webhooks is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AgentLine Webhooks

When to Use This Skill

  • How do I receive AgentLine webhooks?
  • How do I verify AgentLine webhook signatures (X-Webhook-Signature)?
  • How do I handle call.completed, call.utterance or sms.received events?
  • Why is my AgentLine webhook signature verification failing?
  • How do I test an AgentLine webhook with webhook.test?

Verification (core)

AgentLine signs the raw request body with HMAC-SHA256, keyed with the webhook signing secret as a UTF-8 string, and sends the bare hex digest (no prefix, no timestamp) in the X-Webhook-Signature header. The secret is returned in full once when the webhook is created and is masked on later reads. Always verify against the raw body, never re-serialized JSON.

AgentLine has no published webhook SDK for Node (the Node package is not on npm), so verify manually:

javascript
const crypto = require('crypto');

function verifyAgentLineSignature(rawBody, signature, secret) {
  // Check shape first: Buffer.from(x, 'hex') silently truncates invalid hex
  if (!/^[0-9a-f]{64}$/i.test(signature || '')) return false;
  const expected = crypto.createHmac('sha256', secret).update(rawBody).digest();
  return crypto.timingSafeEqual(expected, Buffer.from(signature, 'hex'));
}
python
import hashlib, hmac

def verify(raw_body: bytes, signature: str, secret: str) -> bool:
    expected = hmac.new(secret.encode(), raw_body, hashlib.sha256).hexdigest()
    # Compare bytes so a non-ASCII header returns False (401), not a TypeError (500)
    return hmac.compare_digest(expected.encode(), signature.lower().encode())

For complete handlers with tests, see examples/express/, examples/nextjs/, examples/fastapi/.

Common Event Types

EventTriggered WhenCommon Use Cases
call.receivedAn inbound call is answeredLog the caller, start a session
call.utteranceA live caller turn (conversation uses user / assistant roles)Live transcripts, real-time reply logic
call.completedA call finishesPersist the call record, fetch the transcript
call.owner_taskThe agent hands a task to its ownerCreate a follow-up task
call.failedA call failsAlerting, retry
call.busyThe callee line was busySchedule a retry
call.no-answerThe callee did not answerSchedule a retry
call.canceledA call was canceledClean up state
sms.receivedAn inbound SMS arrivesConversation handling
webhook.testYou trigger a test deliveryConfirm the endpoint is wired up

Each agent has one webhook URL that receives all of its events. Event objects in AgentLine's events API have the shape { event_id, agent_id, event_type, payload, created_at }; the docs do not publish the exact HTTP delivery envelope, so the examples read the type from event_type (falling back to type / event). Log a real webhook.test delivery to confirm. See references/overview.md.

Environment Variables

bash
# Signing secret returned once when the webhook was created
AGENTLINE_WEBHOOK_SECRET=your_webhook_signing_secret
PORT=3000

Setup

Create the webhook with POST /v1/webhooks (agent_id, url, optional secret), save the returned secret, and keep the default X-Webhook-Signature header. AgentLine allows a custom signature_header, but Hookdeck's AgentLine source only checks X-Webhook-Signature, so a custom header is not supported. Details: references/setup.md.

Local Development

For local webhook testing, run the Hookdeck CLI via npx — no install required:

bash
npx hookdeck-cli listen 3000 agentline --path /webhooks/agentline

No account required — the CLI creates a guest account on first run and provides a local tunnel + web UI for inspecting requests. Express and Next.js examples use port 3000; the FastAPI example uses 8000.

Resources

Recommended: webhook-handler-patterns

We recommend installing the webhook-handler-patterns skill alongside this one for handler sequence, idempotency, error handling, and retry logic. Key references (open on GitHub):

Related Skills

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Agentline Webhooks AI skill do?

Receive and verify AgentLine webhooks. Use when setting up AgentLine (AI phone agent) webhook handlers, debugging X-Webhook-Signature verification, or handling events like call.received, call.utterance, call.completed and sms.received.

Why use Agentline Webhooks on TypingMind?

Because you install it once and use it with any model. Agentline Webhooks is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agentline Webhooks in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hookdeck/webhook-skills/tree/main/skills/agentline-webhooks. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Agentline Webhooks?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agentline Webhooks?

As many as you like. As long as a model supports skills, you can use Agentline Webhooks with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agentline Webhooks AI skill free?

Yes. It is published on GitHub by hookdeck under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇