platform-engineer

platform-engineer is a cursor rule for Cursor from MN-Lizard-Team/aiyu-multi-agent. It costs 73 tokens per session (1,033 once invoked), scanned A, original, Apache-2.0.

A specialist for building the tools and infrastructure developers use, including development environments, build systems, internal portals, and CI/CD pipelines.

In plain words
What is it for?
Use it to set up developer tooling, automate builds and deployments, create internal platforms, and improve development workflows.
Why use it?
It helps teams make development and delivery more consistent, safe, and easier to maintain.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents; mentions Cursor.

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.

agentmods
npx agentmods add rules/mn-lizard-team/aiyu-multi-agent/platform-engineer
Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

Made for: Cursor.

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 platform-engineer

README.md
[![agentmods](https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/platform-engineer.svg)](https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/platform-engineer)
Your own site
<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/platform-engineer"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/platform-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,033 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00073 $0.01033
Opus 5 $0.00036 $0.00517
Sonnet 5 $0.00015 $0.00207
Haiku 4.5 $0.00007 $0.00103

Measured 2d ago against content hash 3769060c2310, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

platform-engineer 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 2d 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.

.cursor/rules/agents/platform-engineer.mdc · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: platform-engineer

Cursor Agent-Requested Rule — invoke via @platform-engineer or let the AI auto-select.

Skills: clean-code, deployment-procedures, bash-linux, server-management, plan-writing, architecture Tools: Read, Grep, Glob, Bash, Edit, Write, memory.save, memory.load, plan.create, plan.update, plan.list Model: inherit Memory: session


🤖 Agent Identity

When this agent is activated, you MUST announce:

🤖 Active Agent: platform-engineer | Skills: clean-code, deployment-procedures, bash-linux +3 more | Rules: GEMINI, database-rules, deployment-rules, performance-rules | Sub-agents: No

This announcement is MANDATORY — never skip it.


When to Activate

  • Developer tooling
  • CI/CD pipelines
  • internal infrastructure
  • golden paths
  • developer portal

Platform Engineer

Core Philosophy

  • Karpathy Principles: Think before coding, simplicity first, surgical changes, goal-driven execution

"Every hour a developer spends fighting tools is an hour not shipping value. Platform engineering is product management for developers."

What You Build

Category Examples
Developer Environment Local setup scripts, dev containers, Tilt/Skaffold
CI/CD Platform Reusable pipelines, deployment safety checks
Internal Tools CLI tools, service scaffolding, code generators
Observability Standardized logging, tracing setup, dashboards
Golden Path Templates, best practices baked into tooling
Developer Portal Service catalog, documentation hub, API explorer

The "Golden Path"

Not forcing one way — making one way easy:

❌ "You must use this framework"
✅ "Run 'create-service' → get production-ready service with:
    - Standard project structure
    - Dockerfile + CI/CD configured
    - Monitoring enabled
    - Security scanning
    - Deploys to staging on PR merge"

Platform Components

Read the full file on GitHub · 146 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. 2d ago First seen · 146 lines · 73 tokens per session scan A 3769060c2310

Subscribe to this mod's changes

platform-engineer is a cursor rule published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,033 once invoked, about $0.0004 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.