Anth Webhooks Events

What it does

When your agent uses it

• Building real-time Claude integrations
• Processing batch results
• With phrases like anthropic events
• Claude streaming events

Example prompts

• “anthropic events”
• “claude streaming events”
• “anthropic async processing”
• “/anth-webhooks-events”

Requirements

• Python 3
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(npm:*), Grep

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Validate the stream or batch request against an allowlist of model, source, destination, and maximum size before sending it. Use synthetic…
2. 2For SSE, process known event types, preserve ordering by message/block index, and mark a response incomplete until message_stop. Never…
3. 3For batches and queues, use stable custom IDs, authenticate internal callbacks, and make result handling idempotent. A duplicate event…
4. 4Enforce bounded polling, retries, and queue visibility timeouts. Quarantine errored or expired items for review instead of repeatedly…
5. 5Release from sandbox to a small canary, verify counts, suppression/data-scope checks, and retention cleanup, then roll back the consumer…

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash(npm:*)
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • platform.claude.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Anth Webhooks Events loads about 1.8k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 409 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~90

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 409 words, ~1,803 tokens.

name

anth-webhooks-events

description

Implement event-driven patterns with Claude API: streaming SSE events, Message Batches callbacks, and async processing architectures. Use when building real-time Claude integrations or processing batch results. Trigger with phrases like "anthropic events", "claude streaming events", "anthropic async processing", "claude batch callbacks".

allowed-tools

Read, Write, Edit, Bash(npm:*), Grep

compatibility

Designed for Claude Code

version

1.7.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, ai, anthropic

import anthropic

client = anthropic.Anthropic()

# Process each SSE event type
with client.messages.stream(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain microservices."}]
) as stream:
    for event in stream:
        match event.type:
            case "message_start":
                print(f"Started: {event.message.id}")
            case "content_block_start":
                if event.content_block.type == "tool_use":
                    print(f"Tool call: {event.content_block.name}")
            case "content_block_delta":
                if event.delta.type == "text_delta":
                    print(event.delta.text, end="", flush=True)
                elif event.delta.type == "input_json_delta":
                    print(event.delta.partial_json, end="")
            case "message_delta":
                print(f"\nStop: {event.delta.stop_reason}")
                print(f"Output tokens: {event.usage.output_tokens}")
            case "message_stop":
                print("[Complete]")

# Submit batch (up to 100K requests, 50% cheaper)
batch = client.messages.batches.create(
    requests=[
        {
            "custom_id": f"doc-{i}",
            "params": {
                "model": "claude-sonnet-4-20250514",
                "max_tokens": 1024,
                "messages": [{"role": "user", "content": f"Summarize: {doc}"}]
            }
        }
        for i, doc in enumerate(documents)
    ]
)

# Poll for completion
import time
while True:
    status = client.messages.batches.retrieve(batch.id)
    if status.processing_status == "ended":
        break
    counts = status.request_counts
    print(f"Processing: {counts.processing} | Done: {counts.succeeded} | Errors: {counts.errored}")
    time.sleep(30)

# Stream results
for result in client.messages.batches.results(batch.id):
    if result.result.type == "succeeded":
        print(f"[{result.custom_id}]: {result.result.message.content[0].text[:100]}")
    else:
        print(f"[{result.custom_id}] ERROR: {result.result.error}")

# Use queues to decouple Claude requests from user-facing endpoints
from redis import Redis
from rq import Queue

redis = Redis()
queue = Queue(connection=redis)

def process_with_claude(prompt: str, callback_url: str):
    """Background job for async Claude processing."""
    client = anthropic.Anthropic()
    msg = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=1024,
        messages=[{"role": "user", "content": prompt}]
    )
    # Notify your system via internal callback
    import requests
    requests.post(callback_url, json={
        "text": msg.content[0].text,
        "usage": {"input": msg.usage.input_tokens, "output": msg.usage.output_tokens}
    })

# Enqueue from your API handler
job = queue.enqueue(process_with_claude, prompt="...", callback_url="https://internal/callback")

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/anth-webhooks-events of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287