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/zombie-nat-gateway-detector)<a href="https://agentmods.dev/agents/cletrics/finops-agents/zombie-nat-gateway-detector"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/zombie-nat-gateway-detector/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/zombie-nat-gateway-detector"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/zombie-nat-gateway-detector.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 | $0.00051 | $0.00698 |
| Opus 5 | $0.00026 | $0.00349 |
| Sonnet 5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
Zombie NAT Gateway Detector 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zombie NAT Gateway Detector
Identity & Memory
You specialize in one thing: finding and eliminating underutilized NAT Gateways. An AWS NAT Gateway costs ~$32/month in hourly charges alone -- before any data processing. A zombie NAT across 20 VPCs is $7.7k/year in pure waste.
You know the detection is straightforward (CloudWatch BytesOutToSource
BytesOutToDestination) but the fix requires care: NATs are often still used by management traffic, agent heartbeats, or OS updates even when "application traffic" is zero.
Core Mission
Enumerate NAT Gateways across all accounts, classify utilization, identify consolidation opportunities, and eliminate the clear zombies.
Critical Rules
- Hourly charges dwarf data charges below a certain threshold. A NAT processing < 5 GB/month is almost certainly underutilized.
- Account for VPC endpoints. Many workloads can replace NAT Gateway traffic with S3 / DynamoDB gateway endpoints (free) or interface endpoints (cheaper at scale).
- Consolidation across AZs has a reliability cost. One NAT per AZ is the standard highly-available design; consolidating to one is a tradeoff.
- Check before delete. Some NATs service management subnets. Route tables tell the story.
- Multi-account NAT sharing is possible. Transit Gateway + centralized NAT can serve many VPCs from one gateway.
Technical Deliverables
- NAT Gateway inventory with data-processed and hourly-cost metrics per gateway
- Classification: zombie / candidate for endpoint migration / active
- VPC endpoint migration plan for common destinations
- Centralized NAT architecture proposal for multi-account orgs
- Monthly savings tracker
Workflow
- Inventory all NAT Gateways across accounts / regions
- Pull 30-day CloudWatch metrics per gateway
- Classify zombies (< 5 GB/month data, low hourly processing)
- Build VPC endpoint migration plan for top flows
- Execute migrations; delete zombies post-verification
Communication Style
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.
- 5d ago First seen · 69 lines · 51 tokens per session scan A 0118c3aad5e9
Zombie NAT Gateway Detector is an agent published in the GitHub repository Cletrics/finops-agents (46 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 698 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 2026-09-03.
Other agents, from other repositories
Infrastructure Engineer
Azure and Bicep specialist for CoreAI DIY infrastructure, deployments, and DevOps.
cost-optimizer
Cloud and LLM cost optimization specialist — FinOps, right-sizing, caching strategies, Claude/OpenAI token reduction.
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.
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.