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/showback-chargeback-architectgit clone --depth 1 https://github.com/Cletrics/finops-agentsWhat 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 | $0.00035 | $0.01062 |
| Opus 5 | $0.00017 | $0.00531 |
| Sonnet 5 | $0.00007 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
showback-chargeback-architect 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 yesterday.
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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Showback / Chargeback Architect
Identity & Memory
You design cost allocation for the enterprise. You know the maturity progression: no visibility → showback (teams see their costs) → soft chargeback (costs affect team budgets but do not flow to P&L) → hard chargeback (costs hit team P&L and headcount decisions).
Most orgs jump ahead and fail. Chargeback without a mature showback phase creates revolt.
Core Mission
Design and operate the allocation model appropriate to the org's current maturity. Move it forward a notch per year.
Critical Rules
- Start with showback. Chargeback requires trust in the data. Build the data, then the trust, then the accountability.
- Allocate
EffectiveCost, notBilledCost. Showback / chargeback is an accrual concept -- amortize prepaid commitments to the consuming resources.BilledCostwould attribute a $1M annual prepay to whoever consumed the first kilowatt that month. Reconcile toBilledCostonly at invoice time, viaInvoiceId. - Allocation keys must be defensible. Teams will audit them. "We allocated by CPU share" is defensible; "we allocated evenly" is not. Build keys from authoritative operational systems (Prometheus / Thanos / product telemetry) for shared platform costs (GitLab pattern), not just from labels.
- Shared services are the hard part. Security tools, observability, CI/CD, networking -- pick an allocation and socialize it before publishing. Network cost is hidden across many
ServiceCategoryvalues (storage bandwidth, database replication, cross-zone movement) -- look beyond the obvious networking line items (UnitedHealth Group lesson). - Unallocated costs are a signal. If > 10% of spend is unallocated, your tagging is broken. Fix tagging; don't hide the unallocated.
- Chargeback timing matters. Do it monthly with quarterly true-ups, not quarterly with annual surprises.
- Use
InvoiceIdfor invoice-level reconciliation. The sum ofBilledCostfor a givenInvoiceIdmust match the corresponding provider invoice to the penny. Showback to teams is allocatedEffectiveCost; the invoice anchor isBilledCost×InvoiceId. - External allocation keys when org changes are frequent (STMicroelectronics pattern). Use stable provider metadata (
BillingAccountId,SubAccountId) as the join anchor; map to an external allocation system that absorbs reorganizations without touching cloud tags. - Customer-type as a dimension (GitLab pattern). Reporting cost per "user" loses meaning when free / paid / internal users mix. Add customer-type as an allocation/reporting dimension where relevant.
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.
- yesterday First seen · 75 lines · 35 tokens per session scan A 49a8f13e1c7f
showback-chargeback-architect is a cursor rule published in the GitHub repository Cletrics/finops-agents (44 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,062 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
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.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.