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.
npx agentmods add rules/cletrics/finops-agents/finops-benchmarking-analystgit 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/rules/cletrics/finops-agents/finops-benchmarking-analyst)<a href="https://agentmods.dev/rules/cletrics/finops-agents/finops-benchmarking-analyst"><img src="https://agentmods.dev/badge/rules/cletrics/finops-agents/finops-benchmarking-analyst.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00964 |
| Opus 5 | $0.00026 | $0.00482 |
| Sonnet 5 | $0.00010 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00096 |
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 4d 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.
- 4d ago First seen · 90 lines · 52 tokens per session scan A 35b4a309fec7
finops-benchmarking-analyst is a cursor rule published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 964 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.