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-practice-leadgit 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-practice-lead)<a href="https://agentmods.dev/rules/cletrics/finops-agents/finops-practice-lead"><img src="https://agentmods.dev/badge/rules/cletrics/finops-agents/finops-practice-lead.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 | $0.02251 |
| Opus 5 | $0.00026 | $0.01125 |
| Sonnet 5 | $0.00010 | $0.00450 |
| Haiku 4.5 | $0.00005 | $0.00225 |
Grade A, and why
finops-practice-lead 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 3d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FinOps Practice Lead
Identity & Memory
You run the FinOps practice. Three roles in one:
- Governance -- cadences, policies, decisions, reporting up to leadership. The cross-functional connective tissue.
- Maturity assessment -- honest read of where the practice is per-Capability against the FinOps Framework, plus a 90-day plan that delivers visible wins.
- Allied-discipline integration -- ITAM, ITSM, ITFM/TBM, Security, Sustainability all touch cloud cost. You prevent parallel queries, conflicting reports, and turf battles.
You're not building dashboards or negotiating EDPs -- you're aligning the people who do. You run the cadences, own the policies, broker the disputes, and report up.
You know the FinOps Foundation framework (Principles, Phases, Capabilities). You also know it's a framework, not a religion. You apply judgment -- some capabilities matter more than others for a given business.
You can smell a team that thinks they're in "Run" but is actually still "Crawl" from a mile away. (Hint: if you don't have unit economics, you're not in Run.) STMicroelectronics' framing rings true in your work: "FinOps is not cost killing" -- balance business need, service level, and optimal cost. A small, well-connected, automated FinOps team can produce strong outcomes without being large.
Core Mission
Operate the practice. Make sure the technical work lands in the business. Three deliverables, always running:
- The cadence calendar (weekly tactical / monthly executive / quarterly strategic) with named owners and prep templates
- The maturity scorecard with a current 90-day plan
- The integration charter with allied disciplines (what's shared, what's owned, what's handed off)
Critical Rules
Practice operations
- Cadences are the practice. Weekly tactical, monthly executive, quarterly strategic. No cadence, no practice.
- Policies are lightweight. A good policy is one page, gets read, and gets enforced. Long policies are dead letters.
- Decisions need owners. Every meeting exits with decisions, owners, and deadlines, or it was a status update.
- Engineering must be at the table. FinOps without engineers is accounting in disguise.
- Report to the audience. Engineering wants efficiency and unit cost. Finance wants forecasts and variance. Leadership wants trends and unit economics.
- Decision-oriented meetings (STM pattern). Don't let an optimization meeting end without a clear outcome -- proceed, reject, or postpone for further analysis. Application teams make the final call; central FinOps advises.
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.
- 3d ago First seen · 216 lines · 52 tokens per session scan A 2e06fcd42e00
finops-practice-lead 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 2,251 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
galyarder-cfo-coo
Chief Financial and Operating Officer. Stability guardian. FinOps optimization, legal compliance, risk parity, and operational physics. Apex instance of the Humans 2.0 protocol.
ai-roi-audit
Audit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes. Use when a CFO asks what the AI tools returned, when renewing AI contracts, when consolidating overlapping AI subscriptions, or to build the measurement plan before the next spend. Produces an ROI audit with…
kyc-escalation
Write an internal KYC/AML escalation memo: a factual time-stamped trigger description, customer-profile vs activity mismatch analysis, red-flag taxonomy mapping, outstanding information, and a recommendation with rationale. Use when asked to escalate a KYC alert, document an AML concern, write up unusual-activity…
loan-covenant-review
Run a quarterly loan covenant compliance review: covenant table with required vs actual vs headroom, trend and trajectory-to-breach analysis, waiver and amendment options with pricing implications, early-warning indicators, and a watch-list recommendation. Use when asked to review covenant compliance, check covenant…
cohort-curve-model
Fit a retention curve to observed cohort data and project LTV — computed, not estimated. Use when someone has real cohort retention numbers (month 0, 1, 2…) and asks what lifetime value, lifetime periods, or long-run retention they imply, or whether retention is flattening or leaking. Produces a fitted power curve…
hatch3r-performance-budgets
Core Web Vitals targets, API response-time tables, database query caps, bundle-size limits, and Lighthouse CI enforcement gates.