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/cohen-liel/hivemind/microservicesnpx skills add cohen-liel/hivemind --skill microservicesgit clone --depth 1 https://github.com/cohen-liel/hivemindWrote 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/cohen-liel/hivemind/microservices)<a href="https://agentmods.dev/skills/cohen-liel/hivemind/microservices"><img src="https://agentmods.dev/badge/skills/cohen-liel/hivemind/microservices.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 5.1 | $0.00032 | $0.01831 |
| Opus 5 | $0.00016 | $0.00915 |
| Sonnet 5 | $0.00006 | $0.00366 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
microservices 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 5d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microservices Architecture Patterns
Service Structure
services/
api-gateway/ # Entry point, routing, auth
user-service/ # User management, auth
product-service/ # Products, catalog, inventory
order-service/ # Orders, checkout flow
notification-service/ # Email, push, SMS (event-driven)
payment-service/ # Stripe, billing
shared/
proto/ # gRPC definitions (if used)
events/ # Event schemas (Pydantic/TypeScript)
libs/ # Shared utilities
docker-compose.yml
API Gateway (FastAPI)
# api-gateway/main.py
import httpx
from fastapi import FastAPI, Request, Depends, HTTPException
from fastapi.middleware.cors import CORSMiddleware
app = FastAPI()
app.add_middleware(CORSMiddleware, allow_origins=["*"], allow_methods=["*"])
SERVICE_URLS = {
"users": "http://user-service:8001",
"products": "http://product-service:8002",
"orders": "http://order-service:8003",
}
@app.api_route("/{service}/{path:path}", methods=["GET", "POST", "PUT", "DELETE", "PATCH"])
async def proxy(service: str, path: str, request: Request, user=Depends(verify_token)):
if service not in SERVICE_URLS:
raise HTTPException(404, "Service not found")
url = f"{SERVICE_URLS[service]}/{path}"
async with httpx.AsyncClient() as client:
response = await client.request(
method=request.method,
url=url,
headers={"X-User-Id": str(user.id), "X-User-Role": user.role},
content=await request.body(),
params=dict(request.query_params),
timeout=30,
)
return Response(content=response.content, status_code=response.status_code,
media_type=response.headers.get("content-type"))
Inter-Service Communication
Synchronous (HTTP)
# Shared HTTP client with circuit breaker
import httpx
from tenacity import retry, stop_after_attempt, wait_exponential
class ServiceClient:
def __init__(self, base_url: str):
self.client = httpx.AsyncClient(base_url=base_url, timeout=10)
@retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=1, max=10))
async def get(self, path: str, **kwargs):
response = await self.client.get(path, **kwargs)
response.raise_for_status()
return response.json()
# order-service calling user-service
user_client = ServiceClient("http://user-service:8001")
async def get_order_with_user(order_id: str):
order = await db.orders.find_one(order_id)
user = await user_client.get(f"/users/{order['user_id']}") # Retries on failure
return {**order, "user": user}
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.
- 5d ago First seen · 257 lines · 32 tokens per session scan A 59b617bb3013
microservices is a skill published in the GitHub repository cohen-liel/hivemind (108 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,831 once invoked, about $0.0002 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.
Other skills, from other repositories
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用;包含 AI Coding 事件表语义,以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE,通常与 sls-dashboard-builder 一起使用。.
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.