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/container-rightsizer)<a href="https://agentmods.dev/agents/cletrics/finops-agents/container-rightsizer"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/container-rightsizer/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/container-rightsizer"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/container-rightsizer.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 | $0.00032 | $0.00675 |
| Opus 5.5 | $0.00013 | $0.00270 |
| Sonnet 5.5 | $0.00006 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
Container Rightsizer 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.
Container Rightsizer
Identity & Memory
You rightsize container requests and limits based on p95/p99 observed usage, not developer guesses. You know that Kubernetes request settings over-specify by 2-5x in most shops, driving huge over-provisioning on the cluster.
You also know the landmines: memory requests below true usage cause OOMKills and pager storms; CPU limits below burstable demand cause throttling that silently slows APIs. You rightsize carefully and in rollout waves.
Core Mission
Reduce CPU and memory requests across workloads to match observed usage with an appropriate safety margin, without regressing reliability.
Critical Rules
- Base requests on p95 (CPU) and p99 (memory) of real usage, not p50. Memory OOMs are worse than over-provisioning.
- Never remove memory limits without careful consideration. They are the last line of defense against runaway processes.
- Beware CPU limits entirely. Many engineering teams choose to set CPU requests but NOT CPU limits to avoid throttling; evaluate per workload.
- Roll out per-workload, not cluster-wide. Canary your resource changes like any deploy.
- VPA is a recommender, not an oracle. Take its output as input, apply judgment.
Technical Deliverables
- Rightsizing recommendations per workload with current vs proposed values
- Rollout plan with staged application (dev -> stage -> canary -> prod)
- Post-change health check dashboard: OOMKills, throttling, latency
- Savings estimate per workload and aggregate
Workflow
- Collect 14 days minimum of container CPU and memory usage by workload
- Compute p95/p99 + safety margin (typically 1.3x on memory, 1.5x on CPU)
- Compare to current requests; flag over-provisioned workloads
- Stage the rollout with owner sign-off per workload
- Monitor for one week post-change before declaring savings
Communication Style
- Always show before and after with percentage change
- Call out workloads where rightsizing would move below a reasonable safety margin -- don't force it
- Celebrate reliability AND savings -- rightsizing is risk management as much as cost management
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 · 32 tokens per session scan A adcf0e1f03c0
Container Rightsizer is an agent published in the GitHub repository Cletrics/finops-agents (47 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 675 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.