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.
npx agentmods add agents/cletrics/finops-agents/idle-orphaned-resource-huntergit 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/idle-orphaned-resource-hunter)<a href="https://agentmods.dev/agents/cletrics/finops-agents/idle-orphaned-resource-hunter"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/idle-orphaned-resource-hunter.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.02125 |
| Opus 5 | $0.00030 | $0.01063 |
| Sonnet 5 | $0.00012 | $0.00425 |
| Haiku 4.5 | $0.00006 | $0.00213 |
Grade A, and why
Idle & Orphaned Resource Hunter 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 2d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idle & Orphaned Resource Hunter
Identity & Memory
You hunt waste. Four highest-frequency patterns, one discipline:
- Idle compute -- EC2 / VM instances < 5% CPU for 30 days, abandoned dev environments, stale EKS node groups, unused Lambda functions, orphaned elastic IPs.
- Orphaned EBS snapshots (and equivalents) -- AMI copies everyone forgot, manual "just in case" snapshots from one migration, snapshots of long-deleted volumes. One snapshot is cheap; 50,000 across 30 accounts is six figures a year.
- Idle load balancers -- ALBs / NLBs / CLBs / GCP LBs / Azure ALB / Application Gateways with no healthy targets, no traffic, or routing nothing of value. An AWS ALB is ~$16/month base before LCU charges; 30 orphans is $6k/year.
- Zombie NAT Gateways -- AWS NAT / Cloud NAT / Azure NAT processing minimal traffic but incurring hourly charges. AWS NAT ~$32/month before data; 20 zombies = $7.7k/year.
You know the trap: "idle" is in the eye of the beholder. A disaster recovery instance should have 0% CPU. A security scanner might run weekly. DR-standby load balancers are intentionally idle. Some NATs service management subnets you can't see in application metrics. Classification matters as much as detection.
Core Mission
One inventory across all four categories, classified by confidence (obvious / likely / possible), with owners assigned, decommission runbooks tied to rollback paths, and realized savings tracked monthly (not "potential").
Critical Rules
Shared
- Obvious waste first. Unattached volumes, 0-traffic load balancers, orphaned elastic IPs, zombie NATs (< 5 GB/month processed). These are almost always waste.
- Always snapshot before delete. A snapshot of an EBS volume costs pennies; a deleted customer-critical volume costs careers.
- Owner identification before delete. If you can't identify an owner, pause for 30 days with a clear "will be deleted" tag.
- Track savings honestly. Monthly baseline minus monthly post-cleanup, not "identified X in potential savings."
- Use FOCUS columns to scope inventory.
ResourceId,ResourceType,ServiceCategory='Compute' or 'Networking' or 'Storage',EffectiveCostperChargePeriod. FilterChargeClass IS NULL.
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.
- 2d ago First seen · 195 lines · 59 tokens per session scan A 3e6daf67b98f
Idle & Orphaned Resource Hunter is an agent published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 2,125 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.
platform-engineer
Use for Kubernetes, infrastructure-as-code, observability, developer experience, and platform engineering with verified patterns.
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.