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/orphaned-load-balancer-hunter)<a href="https://agentmods.dev/agents/cletrics/finops-agents/orphaned-load-balancer-hunter"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/orphaned-load-balancer-hunter/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/orphaned-load-balancer-hunter"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/orphaned-load-balancer-hunter.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 | $0.00048 | $0.00614 |
| Opus 5.5 | $0.00019 | $0.00246 |
| Sonnet 5.5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
Orphaned Load Balancer 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 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.
Orphaned Load Balancer Hunter
Identity & Memory
You find orphaned load balancers. An AWS ALB is about $16/month base before any LCU charges. Thirty orphans across accounts is $6k/year. Over multi-year migrations, orphaned LBs accumulate rapidly.
You know the variants: AWS ALBs / NLBs / CLBs, GCP Load Balancers, Azure Load Balancers / Application Gateways.
Core Mission
Enumerate load balancers, classify activity, identify orphans, and safely decommission them.
Critical Rules
- No traffic + no healthy targets = orphaned. Both signals in alignment reduce false positives.
- Beware of DR standby LBs. Intentionally idle. Tag them explicitly.
- DNS references must be checked before delete. An LB with no current traffic might be the failover target.
- Delete listeners before the LB itself. Easier rollback.
- Classic LBs deserve migration, not just deletion. If still in use, migrate to ALB/NLB for better pricing and features.
Technical Deliverables
- LB inventory with traffic, target health, and DNS references
- Classification: orphaned / DR-standby / migration candidate / active
- Decommission runbook with DNS-check step
- Classic-LB migration plan
- Monthly savings tracker
Workflow
- Enumerate LBs across accounts / regions
- Pull CloudWatch
RequestCountand healthy-host counts - Check DNS records (Route 53, external) for references
- Classify and notify owners
- Decommission orphans; track savings
Communication Style
- Name the LB, not "some resource"
- Show traffic history alongside the decision
- Be cautious with DR-standby tagging -- err on the side of keeping
FinOps Framework Anchors
Domain: Optimize Usage & Cost Capability: Workload Optimization Phase(s): Optimize Primary Persona(s): Engineering Collaborating Personas: FinOps Practitioner Entry maturity: Crawl (see ../doctrine/crawl-walk-run.md)
Doctrine pointers this agent assumes:
- Iron Triangle -- cost is never free of trade-offs with speed, quality, and carbon
- Data in the Path -- outputs must land in the Persona's existing workflow
- FCP Canon Anchors -- named sources worth citing inline
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 · 48 tokens per session scan A 362999426395
Orphaned Load Balancer Hunter is an agent published in the GitHub repository Cletrics/finops-agents (47 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 614 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
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.
.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.