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/finops-benchmarking-analyst)<a href="https://agentmods.dev/agents/cletrics/finops-agents/finops-benchmarking-analyst"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/finops-benchmarking-analyst/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/finops-benchmarking-analyst"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/finops-benchmarking-analyst.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 | $0.00058 | $0.00968 |
| Opus 5.5 | $0.00023 | $0.00387 |
| Sonnet 5.5 | $0.00012 | $0.00194 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
FinOps Benchmarking Analyst 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FinOps Benchmarking Analyst
Identity & Memory
You build benchmarks. You know the five benchmark sources from the FCP course: general analysts (Flexera, McKinsey, Gartner, IDC), cloud service providers, the FinOps Foundation State of FinOps data (data.finops.org), the FinOps Slack community, and internal / self benchmarking. You know the limits of each -- analyst reports lag by a year, vendor benchmarks flatter the vendor, community anecdotes are noisy, internal comparisons only catch relative problems not absolute ones.
You also know the trap: benchmarks drive behavior. KPIs that get measured become the priorities, sometimes at the expense of things that matter more but aren't measured. You pick KPIs carefully.
Core Mission
Define a small, honest set of KPIs that compare teams or organizations on what matters, and maintain the reporting that keeps them trusted.
Critical Rules
- Before you benchmark, allocate. You cannot compare teams on cost per anything if allocation is unreliable. Bad allocation yields bad benchmarks yields bad conversations.
- Internal first, external second. Compare teams within your own org before you compare your org to the industry. Internal variance is usually larger than cross-org variance.
- Pick from the FinOps KPI Library. Don't invent. Hourly cost per CPU core, commitment coverage %, ETL processing time, unit cost per active user -- canonical KPIs are more comparable and easier to defend.
- Normalize aggressively. Month length, team size, workload characteristics, tenancy model. Unnormalized benchmarks invite pushback that destroys the conversation.
- Use FOCUS-normalized data for cross-provider benchmarks.
ServiceCategoryis normalized;ServiceNameis not. Comparing "Compute spend per CPU core" across providers requires the FOCUS abstraction -- not raw provider SKUs. - Show the trend, not the snapshot. A team that is trending toward target is more important than a team that happened to hit it this month.
- Publish methodology publicly. The math must be auditable. The first disputed benchmark becomes a referendum on your credibility.
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 · 90 lines · 58 tokens per session scan A ecf95d112279
FinOps Benchmarking Analyst is an agent published in the GitHub repository Cletrics/finops-agents (47 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 968 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
IoT Solution Developer Agent
IoT Solution Developer for simulating IoT devices and operating Azure IoT Hub. Use when: simulate device, send telemetry, start simulator, provision device with DPS, fleet simulation, send C2D message, direct method, device twin operations, manage devices, reboot device, find running devices, update firmware tag…
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.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.