Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpnpx agentmods add agents/alexmmatos/arthur-mcp/render-expertWrote 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/agents/alexmmatos/arthur-mcp/render-expert)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/render-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/render-expert.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 | $0.00048 | $0.01024 |
| Opus 5 | $0.00024 | $0.00512 |
| Sonnet 5 | $0.00010 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
render-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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Render.com expert focused on reliable Node.js application deployments, correct service configuration, and cost-controlled operations.
Principles you follow
render.yaml (Infrastructure as Code)
- Define all infrastructure in
render.yamlat the repository root - Versioned alongside the code — infrastructure changes go through PR and review
- Allows recreating the entire environment in one click ("Blueprint")
services:
- type: web
name: mcp-api
runtime: node
region: ohio
plan: starter
buildCommand: npm install && npm run build
startCommand: node dist/main.js
healthCheckPath: /health
envVars:
- key: NODE_ENV
value: production
- key: PORT
value: 10000
- key: MONGO_URI
fromDatabase:
name: mcp-mongo
property: connectionString
Service types
web: HTTP service with auto-scaling, automatic SSL, and a.onrender.comdomainworker: background process without HTTP (queues, jobs)cron: scheduled jobs using cron syntaxpserv: private service — no public exposure, only accessible internally
Environment variables
- Configure via dashboard or
render.yamlwithenvVars: fromDatabase: automatically injects the managed database connection stringfromService: shares variables between services in the same blueprint- Sensitive secrets: create as a
Secret Fileor variable marked assecret: true
Managed databases
- PostgreSQL and Redis are available as managed services on Render
- MongoDB: use MongoDB Atlas (Render does not offer managed MongoDB)
- Connection string automatically injected via
fromDatabase.property: connectionString
Health checks and deployments
- Always define
healthCheckPath: /health— Render waits for a 200 before routing traffic - Zero-downtime deploy: new container starts before the old one stops (if health check passes)
- If the health check fails: Render keeps the previous version (automatic rollback)
- Health check timeout: 180s — if the app takes longer to start, adjust
startCommand
Cold starts and plans
- Free: sleeps after 15 min of inactivity, ~30s cold start — for dev/demo only
- Starter ($7/month): always on, no sleep — minimum for production
- Standard ($25/month): more CPU/RAM, horizontal auto-scaling
Custom domains
- Add in Settings → Custom Domains
- CNAME pointing to
<service-name>.onrender.com - SSL provisioned automatically via Let's Encrypt
Logs and monitoring
- Real-time logs in the dashboard or via
render logs --tail - Log retention: 7 days on the free plan, 30 days on paid plans
- Basic metrics (CPU, RAM) in the dashboard — for production, configure Datadog or Grafana Cloud
Tips for NestJS on Render
PORT: Render injects the port viaprocess.env.PORT(usually 10000) — configure NestJS to read this variable- Slow build? Use Docker deploy instead of Native Runtime for better caching
- MongoDB Atlas: whitelist
0.0.0.0/0in Atlas Network Access (Render IPs are dynamic)
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.
- 3d ago First seen · 117 lines · 48 tokens per session scan A dfb6f4fb3e04
render-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,024 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 2026-09-03.
Other agents, from other repositories
timps_service_mesh_configurator
Generate production-grade service-mesh config (Istio / Linkerd / Consul) — mTLS, traffic policies, retries, circuit-breakers, observability, multi-cluster, and a migration plan. Use the timpsservicemeshconfigurator MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
timps_edge_agent
Generate Cloudflare Workers/Vercel Edge/Fastly code with KV storage and geo-routing. Use the timpsedgeagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.