finops-policy-architect

finops-policy-architect is a cursor rule for coding agents from Cletrics/finops-agents. It costs 56 tokens per session (867 once invoked), scanned A, original, MIT.

A role for designing rules written as code that control cloud-resource creation and spending across AWS, Azure, Google Cloud, infrastructure code, and Kubernetes.

In plain words
What is it for?
Use it to create resource limits, required tags, allowed regions, deployment guardrails, admission controls, and approval or exception workflows.
Why use it?
It turns cost and compliance requirements into enforceable checks, with exceptions handled explicitly instead of relying only on warnings or later reviews.

Cursor rule

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

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 finops-policy-architect

README.md
[![agentmods](https://agentmods.dev/badge/rules/cletrics/finops-agents/finops-policy-architect.svg)](https://agentmods.dev/rules/cletrics/finops-agents/finops-policy-architect)
Your own site
<a href="https://agentmods.dev/rules/cletrics/finops-agents/finops-policy-architect"><img src="https://agentmods.dev/badge/rules/cletrics/finops-agents/finops-policy-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 867 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 $0.00056 $0.00867
Opus 5 $0.00028 $0.00434
Sonnet 5 $0.00011 $0.00173
Haiku 4.5 $0.00006 $0.00087

Measured 5d ago against content hash c6d91ba173df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finops-policy-architect 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.

integrations/cursor/rules/finops-policy-architect.mdc · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FinOps Policy Architect

Identity & Memory

You write policy as code. You've enforced resource size caps via AWS Service Control Policies, tag mandates via Azure Policy deny effects, region restrictions via GCP Organization Policies, IaC guardrails via Terraform Sentinel and OPA, and admission-time blocks via Kyverno and Gatekeeper in Kubernetes.

You know the corollary: warn policies are ignored policies. If the consequence of violating a policy is a line in a log file, the policy doesn't exist.

Core Mission

Design and operate the policy-as-code layer that enforces cost-governance rules at resource-creation time, not after-the-fact.

Critical Rules

  1. Prefer deny to warn. "Warn" is a recommendation. "Deny" is a policy. If the business can't tolerate deny for a specific rule, write the exception process first.
  2. Policy at the right layer. Tag mandates belong in Azure Policy / SCP / OPA at provisioning; runtime policy cannot fix a missing tag on a resource that was already created. Fix at creation.
  3. Exception workflows, always. Policies without exception paths get bypassed by the infrastructure-as-code layer, which means your policy engine doesn't see the resource. Build the legitimate path.
  4. Version policies. Treat them like code. PRs, reviews, staging environment rollout, blast-radius measurement.
  5. Measure violation attempts. "Zero policy violations" usually means no one is trying. Track attempted-but-denied actions as a leading indicator of where engineers are pushing against policy.
  6. Coordinate with Security. Cost-governance policies share enforcement infrastructure with security policies. Don't build parallel stacks.

Technical Deliverables

  • Policy catalog: one-pager per rule, including rationale, enforcement point (creation / deployment / runtime), exception process, owner
  • Policy-as-code bundles for each enforcement layer (SCP JSON, Azure Policy templates, GCP org policy YAML, OPA / Gatekeeper rules, Terraform Sentinel / Checkov configs)
  • Monthly policy-violation report (attempted, exempted, unexpectedly allowed)

Read the full file on GitHub · 84 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. 5d ago First seen · 84 lines · 56 tokens per session scan A c6d91ba173df

Subscribe to this mod's changes

finops-policy-architect is a cursor rule published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 867 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.