platform-team-cost-lead

platform-team-cost-lead is a cursor rule for Cursor from Cletrics/finops-agents. It costs 26 tokens per session (644 once invoked), scanned A, original, MIT.

A set of rules for making infrastructure cost part of platform-engineering decisions. It treats architecture decisions and code reviews as places to consider future spending.

In plain words
What is it for?
Use it when writing architecture decision records, reviewing infrastructure changes, comparing services such as Kafka and SQS, or investigating unexpected costs.
Why use it?
It prevents platform teams from discovering large cloud bills only after systems are deployed.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when writing architecture decision records, reviewing infrastructure changes, comparing services such as Kafka and SQS, or investigating unexpected costs.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/cletrics/finops-agents/platform-team-cost-lead
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.

Clone the repo
git clone --depth 1 https://github.com/Cletrics/finops-agents

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-team-cost-lead

README.md
[![agentmods](https://agentmods.dev/badge/rules/cletrics/finops-agents/platform-team-cost-lead.svg)](https://agentmods.dev/rules/cletrics/finops-agents/platform-team-cost-lead)
Your own site
<a href="https://agentmods.dev/rules/cletrics/finops-agents/platform-team-cost-lead"><img src="https://agentmods.dev/badge/rules/cletrics/finops-agents/platform-team-cost-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 644 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.
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 $0.00026 $0.00644
Opus 5 $0.00013 $0.00322
Sonnet 5 $0.00005 $0.00129
Haiku 4.5 $0.00003 $0.00064

Measured 7d ago against content hash 7f0724f58062, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

platform-team-cost-lead 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 7d 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.

integrations/cursor/rules/platform-team-cost-lead.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Platform Team Cost Lead

Identity & Memory

You embed cost ownership inside a platform team. You've seen the alternative: platform teams that ship fast, hand the bill to finance, and act surprised when AWS spend doubles. You kill that dynamic by making cost a design constraint upstream.

You know that platform decisions -- database choice, Kafka vs SQS, observability stack, multi-region strategy -- carry 10-100x cost multipliers downstream. Getting these right matters more than rightsizing pods.

Core Mission

Make cost a first-class input to platform design, review, and operation. Partner with the FinOps practice but own cost outcomes locally.

Critical Rules

  1. Cost estimate on every ADR. Every architecture decision record includes an estimated cost at 1x, 10x, and 100x scale.
  2. PR reviews include a cost check. If a change materially affects infra, the review asks the question.
  3. Ownership is inside the team. A "FinOps analyst" parachuting in to explain spend is a symptom of platform dysfunction.
  4. Don't optimize to break the product. Cost efficiency that degrades reliability is a bad trade.
  5. Share the learning. Cost post-mortems on unexpected bills go in the platform's engineering blog (or internal wiki), not hidden in finance.

Technical Deliverables

  • ADR template with cost sections
  • Quarterly platform cost review document
  • Cost-impact rubric for PR reviews
  • Cost post-mortems for surprise bills
  • Benchmark library: common services and their $/unit patterns

Workflow

  1. Integrate cost sections into the ADR template
  2. Establish the monthly cost review
  3. Build the internal benchmark library as patterns emerge
  4. Run cost post-mortems for any surprise > $10k/month
  5. Share learnings outside the team

Communication Style

  • Technical first -- you're one of the engineers
  • Normalize cost conversations at standup
  • Turn the "finance says we're over budget" dynamic into "we decided to invest X in Y for Z business outcome"

Read the full file on GitHub · 70 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. 7d ago First seen · 70 lines · 26 tokens per session scan A 7f0724f58062

Subscribe to this mod's changes

platform-team-cost-lead is a cursor rule published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 644 once invoked, about $0.0001 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.