Anth Architecture Variants

What it does

When your agent uses it

• With phrases like anthropic architecture
• Claude serverless
• Claude microservice design
• Edge claude deployment

Example prompts

• “anthropic architecture”
• “claude serverless”
• “claude microservice design”
• “/anth-architecture-variants”

Requirements

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

Workflow steps

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

1. 1Select the smallest architecture that satisfies measured latency and volume, then record why its timeout, queue, connection, and failure…
2. 2Keep API keys server-side, validate tenant/model/destination scope at ingress, and apply least privilege to workers and queues. Isolate…
3. 3Add bounded retries, circuit breaking, backpressure, idempotent result handling, and health checks appropriate to the selected variant…
4. 4Exercise the design with synthetic load and failure injection, then release to a limited canary. Compare error rate, latency, queue depth…
5. 5Promote only after owner approval; otherwise restore the prior topology/configuration and remove temporary fixtures, queues, and…

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
  • 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 Architecture Variants loads about 1.9k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 464 words of instructions outside code blocks.

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

~73

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

~1.9k

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). 464 words, ~1,925 tokens.

name

anth-architecture-variants

description

Choose and implement Claude API architecture patterns for different scales: serverless, microservice, event-driven, and edge deployment. Trigger with phrases like "anthropic architecture", "claude serverless", "claude microservice design", "edge claude deployment".

allowed-tools

Read, Write, Edit, Grep

compatibility

Designed for Claude Code

version

1.7.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, ai, anthropic

# Best for: < 100 RPM, event-driven, pay-per-invocation
# lambda_function.py
import anthropic
import json

def handler(event, context):
    client = anthropic.Anthropic()  # Key from Lambda env var

    body = json.loads(event["body"])
    msg = client.messages.create(
        model="claude-haiku-4-20250514",  # Haiku for Lambda speed
        max_tokens=512,
        messages=[{"role": "user", "content": body["prompt"]}]
    )

    return {
        "statusCode": 200,
        "body": json.dumps({
            "text": msg.content[0].text,
            "tokens": msg.usage.input_tokens + msg.usage.output_tokens
        })
    }

# Best for: chatbots, interactive UIs, real-time responses
from fastapi import FastAPI, WebSocket
import anthropic

app = FastAPI()
client = anthropic.Anthropic()

@app.websocket("/chat")
async def chat_ws(websocket: WebSocket):
    await websocket.accept()
    while True:
        prompt = await websocket.receive_text()
        with client.messages.stream(
            model="claude-sonnet-4-20250514",
            max_tokens=2048,
            messages=[{"role": "user", "content": prompt}]
        ) as stream:
            for text in stream.text_stream:
                await websocket.send_text(text)
            await websocket.send_text("[DONE]")

# Best for: batch processing, async workflows, high volume
from celery import Celery
import anthropic

app = Celery("tasks", broker="redis://localhost")

@app.task(bind=True, max_retries=3, default_retry_delay=30)
def process_document(self, doc_id: str, content: str):
    try:
        client = anthropic.Anthropic()
        msg = client.messages.create(
            model="claude-sonnet-4-20250514",
            max_tokens=2048,
            messages=[{"role": "user", "content": f"Summarize:\n\n{content}"}]
        )
        save_result(doc_id, msg.content[0].text)
    except anthropic.RateLimitError as e:
        self.retry(exc=e, countdown=int(e.response.headers.get("retry-after", 30)))

# Best for: complex workflows needing different model strengths
class ClaudeOrchestrator:
    def __init__(self):
        self.client = anthropic.Anthropic()

    def classify_then_respond(self, user_input: str) -> str:
        # Step 1: Classify intent with Haiku (fast, cheap)
        classification = self.client.messages.create(
            model="claude-haiku-4-20250514",
            max_tokens=32,
            messages=[{
                "role": "user",
                "content": f"Classify as: question|task|creative|code\nInput: {user_input[:200]}"
            }]
        )
        intent = classification.content[0].text.strip().lower()

        # Step 2: Route to optimal model
        model = {
            "question": "claude-haiku-4-20250514",
            "task": "claude-sonnet-4-20250514",
            "creative": "claude-sonnet-4-20250514",
            "code": "claude-sonnet-4-20250514",
        }.get(intent, "claude-sonnet-4-20250514")

        # Step 3: Generate response
        msg = self.client.messages.create(
            model=model,
            max_tokens=4096,
            messages=[{"role": "user", "content": user_input}]
        )
        return msg.content[0].text

© 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-architecture-variants of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287