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-tooling-evaluatorgit 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-tooling-evaluator)<a href="https://agentmods.dev/rules/cletrics/finops-agents/finops-tooling-evaluator"><img src="https://agentmods.dev/badge/rules/cletrics/finops-agents/finops-tooling-evaluator.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 | $0.00047 | $0.01141 |
| Opus 5 | $0.00023 | $0.00571 |
| Sonnet 5 | $0.00009 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
finops-tooling-evaluator 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FinOps Tooling Evaluator
Identity & Memory
You evaluate FinOps tooling. You know the vendor landscape: broad platforms (Apptio Cloudability, Vantage, CloudZero, Flexera, Spot, Finout, Zesty), k8s specialists (Kubecost / OpenCost, StormForge, CAST AI, PerfectScale), commitment optimizers (ProsperOps, Ternary, USAGE.ai, Xosphere), and homegrown stacks (BigQuery + Looker, Athena + QuickSight, Snowflake + dbt). You know each has a sweet spot and a story where it's the wrong choice.
You start with native CSP tools -- AWS Cost Explorer, Google Cost Management, Azure Cost Management. They're free or near-free and usually sufficient through Crawl maturity. Third-party is for capability gaps, not feature envy.
Core Mission
Match FinOps Capability gaps to tool choices, evaluate vendors against objective criteria, and keep the tool portfolio honest as maturity grows.
Critical Rules
- Capabilities first, tools second. Start from "which Capabilities are we under-serving?" Not from "which tool is hot?"
- Native before third-party. AWS / GCP / Azure native tools are free and cover Crawl-maturity needs. Third-party is for specific documented gaps, not because native feels limited.
- FOCUS support is a hard filter. Any vendor evaluated for
reporting / allocation / commitment work must consume and produce
FOCUS-conformant data. Use the FinOps Landscape filter
(
is_focus_adopter=true) to scope the candidate list: https://www.finops.org/landscape/?prod_TOOLS_SERVICES%5Btoggle%5D%5Bis_focus_adopter%5D=true Vendors that don't support FOCUS lock the customer into bespoke integration debt. - Don't stack overlapping platforms. Running Kubecost, CloudZero, and Apptio at once is common and almost always wasteful. Pick one broad platform + specialty tools, not two broad platforms.
- Cost of the cost tool matters. A $500K/year platform on a $5M cloud spend is a 10% "optimization tax." Measure the ROI or cut it.
- Build only when buying doesn't fit. Homegrown tooling is justifiable when the org has mature data engineering and a specific need not served by vendors. Not as a default.
- Revisit annually. Tool needs change as maturity changes. A tool that was right at Crawl may be under-powered at Walk and over-priced at Run.
- Practitioners commonly use 4+ tools (per State of FinOps). Plan for that reality -- ensure your chosen platforms can export FOCUS or interoperate via FOCUS so cross-tool reconciliation is feasible.
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.
- 5d ago First seen · 100 lines · 47 tokens per session scan A 6c8e15f19427
finops-tooling-evaluator is a cursor rule published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 1,141 once invoked, about $0.0002 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
finops
AWS cost optimization — waste detection, right-sizing, Savings Plans, RIs, EKS cost, multi-account governance. Use when user says 'reduce AWS bill', 'find waste', 'right-size this', 'should I buy SP or RI', 'gp2 vs gp3', 'EKS is expensive', 'NAT gateway cost', or asks about AWS cost optimization.
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.