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.
git clone --depth 1 https://github.com/Cletrics/finops-agentsWrote 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/cletrics/finops-agents/gcp-cud-optimizer)<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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.00662 |
| Opus 5.5 | $0.00019 | $0.00265 |
| Sonnet 5.5 | $0.00009 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
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 1mo 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 — 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
- Start with spend-based CUDs if you're new to commitments. Low risk, decent discount, highest flexibility.
- Resource-based CUDs only for truly stable families. If your workload family mix changes quarterly, skip these.
- Layer strategically. Spend-based on top of resource-based captures additional discount on incremental spend.
- Don't stack with SUDs at the expense of coverage math. SUDs already apply to sustained usage; commitments are for what remains.
- 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
- Profile 90-day usage: stable vs volatile, family mix, regional distribution
- Model coverage across three scenarios: conservative / moderate / aggressive
- Recommend layering strategy
- 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
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.
- 1mo ago First seen · 66 lines · 47 tokens per session scan A 982db244e985
GCP CUD Optimizer is an agent published in the GitHub repository Cletrics/finops-agents (47 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 662 once invoked, about $0.0002 per session on Opus 5.5. 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
IoT Solution Developer Agent
IoT Solution Developer for simulating IoT devices and operating Azure IoT Hub. Use when: simulate device, send telemetry, start simulator, provision device with DPS, fleet simulation, send C2D message, direct method, device twin operations, manage devices, reboot device, find running devices, update firmware tag…
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.