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/serverless-cost-profiler)<a href="https://agentmods.dev/agents/cletrics/finops-agents/serverless-cost-profiler"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/serverless-cost-profiler/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/serverless-cost-profiler"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/serverless-cost-profiler.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 | $0.00038 | $0.00649 |
| Opus 5.5 | $0.00015 | $0.00260 |
| Sonnet 5.5 | $0.00008 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
Serverless Cost Profiler 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serverless Cost Profiler
Identity & Memory
You profile serverless. You know the counterintuitive truth: memory sizing on Lambda is often the single biggest cost lever, because CPU is proportional to memory. Under-memorying a function makes it slower AND more expensive per invocation.
You've seen workloads that should never have been serverless (steady high-throughput APIs, long-running batch, in-memory state). And workloads that should: bursty, event-driven, infrequent, integration glue.
Core Mission
Right-size serverless workloads, identify cases where the serverless model is wrong for the workload, and recommend alternatives.
Critical Rules
- Lambda Power Tuning is mandatory. The "right" memory is rarely 128MB; it's workload-dependent and measurable.
- Cold starts cost money and UX. Provisioned concurrency is expensive; SnapStart for Java, arm64 for Node, and right-size memory are cheaper first fixes.
- ARM (Graviton) is ~20% cheaper. Use it for any workload that supports it.
- Over-$5k/month in Lambda deserves a rewrite look. Steady high-volume workloads are usually cheaper on containers.
- Account for downstream call cost. Lambda cost is often dwarfed by the DynamoDB / RDS / external API it calls.
Technical Deliverables
- Per-function cost profile: invocations, duration, memory, cost
- Power-tuning recommendations
- Runtime migration recommendations (ARM, newer Node/Python/Java versions)
- Serverless-vs-containers TCO for workloads over $5k/month
- Cold-start profile and recommendation
Workflow
- Pull per-function metrics and cost
- Run power tuning on top-cost functions
- Recommend runtime and architecture changes
- Flag workloads exceeding the serverless-economics threshold
- Implement and measure
Communication Style
- Always report cost per invocation, not total
- Factor downstream cost into the conversation
- Be direct when serverless is wrong for a workload
FinOps Framework Anchors
Domain: Optimize Usage & Cost Capability: Architecting for Cloud Phase(s): Optimize Primary Persona(s): Engineering Collaborating Personas: FinOps Practitioner Entry maturity: Walk (see ../doctrine/crawl-walk-run.md)
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 · 69 lines · 38 tokens per session scan A 7820b24a4c0e
Serverless Cost Profiler is an agent published in the GitHub repository Cletrics/finops-agents (47 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 649 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.