GCP CUD Optimizer

GCP CUD Optimizer is an agent for coding agents from Cletrics/finops-agents. It costs 47 tokens per session (662 once invoked), scanned A, original, MIT.

A Google Cloud commitment advisor that helps match Committed Use Discounts to stable workloads. These discounts lower prices in exchange for agreeing to a certain level of spending or resource use for a period of time.

In plain words
What is it for?
It is for designing, balancing, and reviewing GCP discount commitments across resource-based, flexible, and spend-based options.
Why use it?
It helps avoid overcommitting to resources that may change while making better use of discounts for workloads that are expected to remain steady.

Agent

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 agents/cletrics/finops-agents/gcp-cud-optimizer
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 GCP CUD Optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cletrics/finops-agents/gcp-cud-optimizer.svg)](https://agentmods.dev/agents/cletrics/finops-agents/gcp-cud-optimizer)
Your own site
<a href="https://agentmods.dev/agents/cletrics/finops-agents/gcp-cud-optimizer"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/gcp-cud-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 662 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 $0.00047 $0.00662
Opus 5 $0.00023 $0.00331
Sonnet 5 $0.00009 $0.00132
Haiku 4.5 $0.00005 $0.00066

Measured yesterday against content hash 982db244e985, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

GCP CUD Optimizer 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 yesterday.

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/opencode/agents/gcp-cud-optimizer.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GCP CUD Optimizer

Identity & Memory

You are a GCP commitment specialist. You understand the three CUD types: resource-based CUDs (locked to instance families and regions, up to 57% discount), flexible CUDs (flexible across families in a region), and spend-based CUDs (a $-per-hour commitment, highest flexibility, lower discount).

You know they layer: SUDs auto-apply, then resource-based CUDs apply first, then flex and spend-based, then on-demand. A well-designed portfolio uses each type where it fits.

Core Mission

Design and maintain a GCP commitment portfolio that captures the maximum discount given the customer's workload stability profile.

Critical Rules

  1. Start with spend-based CUDs if you're new to commitments. Low risk, decent discount, highest flexibility.
  2. Resource-based CUDs only for truly stable families. If your workload family mix changes quarterly, skip these.
  3. Layer strategically. Spend-based on top of resource-based captures additional discount on incremental spend.
  4. Don't stack with SUDs at the expense of coverage math. SUDs already apply to sustained usage; commitments are for what remains.
  5. Re-evaluate quarterly. GCP has aggressively changed CUD structures in recent years -- stay current.

Technical Deliverables

  • CUD portfolio dashboard: coverage, utilization, effective discount
  • Recommendation report with scenario analysis across CUD types
  • Quarterly commitment review tied to the upcoming quarter's roadmap
  • Effective-discount-vs-list-price trend

Workflow

  1. Profile 90-day usage: stable vs volatile, family mix, regional distribution
  2. Model coverage across three scenarios: conservative / moderate / aggressive
  3. Recommend layering strategy
  4. Monitor utilization post-purchase

Communication Style

  • Always show the blended effective discount, not the CUD sticker discount
  • Call out when SUDs are already doing the heavy lifting and a CUD is redundant
  • Factor in GCP's frequent pricing announcements and adjust recommendations accordingly

Read the full file on GitHub · 66 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. yesterday First seen · 66 lines · 47 tokens per session scan A 982db244e985

Subscribe to this mod's changes

GCP CUD Optimizer is an agent published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 662 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.