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 skills add Cletrics/finops-agents --skill showback-chargeback-architectgit 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/skills/cletrics/finops-agents/showback-chargeback-architect)<a href="https://agentmods.dev/skills/cletrics/finops-agents/showback-chargeback-architect"><img src="https://agentmods.dev/badge/skills/cletrics/finops-agents/showback-chargeback-architect/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/skills/cletrics/finops-agents/showback-chargeback-architect"><img src="https://agentmods.dev/badge/skills/cletrics/finops-agents/showback-chargeback-architect.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 | $0.00042 | $0.01062 |
| Opus 5.5 | $0.00017 | $0.00425 |
| Sonnet 5.5 | $0.00008 | $0.00212 |
| Haiku 4.5 | $0.00004 | $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 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 — 74 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.
- 1mo ago First seen · 74 lines · 42 tokens per session scan A 32f9252bbfbc
Showback / Chargeback Architect is a skill published in the GitHub repository Cletrics/finops-agents (47 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 1,062 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 skills, from other repositories
azure-ai-projects-dotnet
Azure AI Projects SDK for .NET. High-level client for Azure AI Foundry projects including agents, connections, datasets, deployments, evaluations, and indexes. Use for AI Foundry project management, versioned agents, and orchestration. Triggers: "AI Projects", "AIProjectClient", "Foundry project", "versioned agents"…
azure-ai-projects-java
Azure AI Projects SDK for Java. High-level SDK for Azure AI Foundry project management including connections, datasets, indexes, and evaluations. Triggers: "AIProjectClient java", "azure ai projects java", "Foundry project java", "ConnectionsClient", "DatasetsClient", "IndexesClient".
cis-aws-foundations-2.2
Maintain current AWS account contact details.
cis-aws-compute-2.4
Ensure an Organizational EC2 Tag Policy has been Created.
cis-aws-compute-2.3
Ensure Tag Policies are Enabled.
yylo-ninja
Master orchestrator for the 7 canonical agent skills from the official yylo-dev/yylo-skills repository. Use when working with ANY YYLO workflow: Kanban-style task management on the YYLO Ledger board, planning Product Development Requirements and implementation-sized tasks, wiki Records as durable project knowledge…