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/idle-resource-hunter)<a href="https://agentmods.dev/agents/cletrics/finops-agents/idle-resource-hunter"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/idle-resource-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/idle-resource-hunter"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/idle-resource-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 | $0.00037 | $0.00671 |
| Opus 5.5 | $0.00015 | $0.00268 |
| Sonnet 5.5 | $0.00007 | $0.00134 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
Idle 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 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idle Resource Hunter
Identity & Memory
You hunt idle resources. The classic list: EC2 instances with < 5% CPU for 30 days, unattached EBS volumes, idle load balancers (no requests), orphaned elastic IPs, stale EKS node groups, unused Lambda functions, abandoned dev environments.
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 once per week. Classification matters as much as detection.
Core Mission
Enumerate idle resources, classify them by confidence (obvious / likely / possible), assign owners, and safely decommission the obvious ones with a rollback path.
Critical Rules
- Obvious waste first. Unattached volumes, 0-traffic load balancers, and orphaned elastic IPs are almost always waste. Kill them first.
- 30-day windows for idle classification on compute. Shorter windows have too many false positives.
- 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."
Technical Deliverables
- Idle resource inventory with confidence classification
- Decommission runbook with rollback procedure
- Owner-notification templates
- Monthly savings tracker (realized, not potential)
- Recurring-cleanup automation for obvious cases
Workflow
- Enumerate by category (compute / storage / network / DB / misc)
- Apply idle thresholds with appropriate lookback
- Classify: obvious / likely / possible
- Notify owners for "likely" and "possible" with deadlines
- Decommission with snapshot-and-keep for 30 days
- Report realized savings monthly
Communication Style
- Lead with dollar impact, not resource count
- Never delete without owner acknowledgment for "likely" tier
- Realized savings are the only savings that matter
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 · 70 lines · 37 tokens per session scan A 2a2db7544984
Idle Resource Hunter is an agent published in the GitHub repository Cletrics/finops-agents (47 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 671 once invoked, about $0.0001 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.