microservices-expert

microservices-expert is a skill for Claude Code from personamanagmentlayer/pcl. It costs 52 tokens per session (2,970 once invoked), scanned A, original, Apache-2.0.

An architecture guide for microservices: applications split into small, independently deployable services. It covers how services communicate, share responsibilities, handle failures, and coordinate data.

In plain words
What is it for?
Use it to plan service boundaries, HTTP or gRPC communication, message-based workflows, API gateways, circuit breakers, event sourcing, or CQRS.
Why use it?
Distributed systems can become difficult to design and keep reliable as services multiply. The guide provides patterns for common problems such as service discovery, retries, gateways, and multi-step operations.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to plan service boundaries, HTTP or gRPC communication, message-based workflows, API gateways, circuit breakers, event sourcing, or CQRS.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/personamanagmentlayer/pcl/microservices-expert
Install

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.

Any agent
npx skills add personamanagmentlayer/pcl --skill microservices-expert
Clone the repo
git clone --depth 1 https://github.com/personamanagmentlayer/pcl

Made for: Claude Code.

Wrote 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.

agentmods badge for microservices-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/microservices-expert.svg)](https://agentmods.dev/skills/personamanagmentlayer/pcl/microservices-expert)
Your own site
<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/microservices-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/microservices-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.02970
Opus 5 $0.00026 $0.01485
Sonnet 5 $0.00010 $0.00594
Haiku 4.5 $0.00005 $0.00297

Measured 3d ago against content hash d91ceef265ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

microservices-expert 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 3d 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.

stdlib/api/microservices-expert/SKILL.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microservices Expert

Expert guidance for microservices architecture, design patterns, service communication, and distributed system challenges.

Core Concepts

Microservices Principles

  • Single responsibility per service
  • Independently deployable
  • Decentralized data management
  • Infrastructure automation
  • Design for failure
  • Evolutionary design

Architecture Patterns

  • API Gateway
  • Service Discovery
  • Circuit Breaker
  • Saga Pattern
  • Event Sourcing
  • CQRS

Communication

  • Synchronous (HTTP/REST, gRPC)
  • Asynchronous (Message queues, Events)
  • Service mesh
  • API composition
  • Backend for Frontend (BFF)

Service Design

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
import httpx
from typing import List, Optional
from circuitbreaker import circuit
import asyncio

# Individual Microservice
app = FastAPI(title="Order Service", version="1.0.0")

class Order(BaseModel):
    id: str
    user_id: str
    items: List[dict]
    total: float
    status: str

class OrderService:
    def __init__(self, inventory_url: str, payment_url: str):
        self.inventory_url = inventory_url
        self.payment_url = payment_url
        self.client = httpx.AsyncClient()

    @circuit(failure_threshold=5, recovery_timeout=60)
    async def check_inventory(self, items: List[dict]) -> bool:
        """Check inventory availability with circuit breaker"""
        try:
            response = await self.client.post(
                f"{self.inventory_url}/check",
                json={"items": items},
                timeout=5.0
            )
            return response.json()["available"]
        except Exception as e:
            print(f"Inventory service error: {e}")
            raise

    @circuit(failure_threshold=5, recovery_timeout=60)
    async def process_payment(self, user_id: str, amount: float) -> dict:
        """Process payment with circuit breaker"""
        try:
            response = await self.client.post(
                f"{self.payment_url}/charge",
                json={"user_id": user_id, "amount": amount},
                timeout=10.0
            )
            return response.json()
        except Exception as e:
            print(f"Payment service error: {e}")
            raise

    async def create_order(self, order: Order) -> Order:
        """Create order with coordination"""
        # 1. Check inventory
        inventory_available = await self.check_inventory(order.items)
        if not inventory_available:
            raise HTTPException(400, "Items not available")

        # 2. Process payment
        payment = await self.process_payment(order.user_id, order.total)
        if payment["status"] != "success":
            raise HTTPException(400, "Payment failed")

        # 3. Reserve inventory
        await self.reserve_inventory(order.items)

        # 4. Create order record
        order.status = "confirmed"
        await self.save_order(order)

        return order

@app.post("/orders", response_model=Order)
async def create_order(order: Order):
    service = OrderService(
        inventory_url="http://inventory-service",
        payment_url="http://payment-service"
    )
    return await service.create_order(order)

Read the full file on GitHub · 498 lines

Changes

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.

  1. 3d ago Changed · +10 lines · +33 tokens per session d91ceef265ad
  2. 8d ago First seen · 488 lines · 19 tokens per session scan A 275c9a4dfcbd

Subscribe to this mod's changes

microservices-expert is a skill published in the GitHub repository personamanagmentlayer/pcl (40 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 2,970 once invoked, about $0.0003 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.