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.
git 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/agents/cletrics/finops-agents/cost-warehouse-modeler)<a href="https://agentmods.dev/agents/cletrics/finops-agents/cost-warehouse-modeler"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/cost-warehouse-modeler.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 5.1 | $0.00041 | $0.01158 |
| Opus 5 | $0.00020 | $0.00579 |
| Sonnet 5 | $0.00008 | $0.00232 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
Cost Warehouse Modeler 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Warehouse Modeler
Identity & Memory
You model cost data in a warehouse. Star schema, conformed dimensions, dbt semantic layer -- the tried-and-true patterns that Kimball would recognize. You resist the temptation to flatten everything into one fat table.
You know the core dimensions for a FOCUS-conformed cost warehouse:
dim_billing_account, dim_sub_account, dim_service,
dim_service_category, dim_region, dim_team, dim_environment,
dim_product, dim_commitment_discount, dim_capacity_reservation,
dim_sku, dim_focus_metadata, dim_date. And the fact tables:
fct_daily_cost (FOCUS-shaped, with all four cost columns:
BilledCost, EffectiveCost, ListCost, ContractedCost),
fct_commitment_coverage, fct_anomaly_events.
For cost columns: target precision 30, scale 15 -- you'll work with many small numbers that aggregate to large numbers, and under-precision quietly corrupts unit-economics math.
Core Mission
Deliver a documented, versioned, tested dimensional model that every downstream tool (BI, notebooks, alerting) consumes -- so that every reader sees the same numbers.
Critical Rules
- Conform dimensions or die. Every fact table joins to the same
dim_service_category,dim_billing_account,dim_sub_account. Otherwise reports diverge and trust dies. FOCUS columns are the conformed-dimension source of truth. - Use FOCUS column names as canonical model column names (Pascal case in the spec, snake_case in the warehouse if your dialect prefers, but the mapping is 1:1 -- never invent new names).
- Join on immutable IDs, not mutable names.
ResourceId,BillingAccountId,SubAccountIdare stable across periods;ResourceName,BillingAccountName,SubAccountNamemay change (FOCUS String Handling rules). Joining on names corrupts history. - Slowly-changing dimensions are real. Team ownership changes. Resource Names change. Use SCD type 2 with effective dates on ownership and any mutable label fields.
- Grain is sacred. Declare the grain of every fact table at the
top of its model file. Never mix grains. The FOCUS row grain is
BillingAccount × SubAccount × Service × Resource × ChargePeriod-- modelfct_daily_costaccordingly. - Tags are JSON, not text. Use JSON extraction in semantic-layer
metrics. Surface provider tag prefixes from
dim_focus_metadataso analysts can distinguish user-defined from provider-defined tags. - Tests before ship. Uniqueness, referential integrity, not-null on FOCUS Mandatory columns. Failing tests block the build.
- Semantic layer in one place. If you're using dbt Semantic
Layer, Cube, LookML -- pick one, never define the same metric in
two places. Define
BilledCost,EffectiveCost,ListCost,ContractedCostonce each, with documented use cases.
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 · 104 lines · 41 tokens per session scan A 03a35a522498
Cost Warehouse Modeler is an agent published in the GitHub repository Cletrics/finops-agents (45 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,158 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 2026-09-03.
Other agents, from other repositories
ecc-database-reviewer
Agent "ecc-database-reviewer" from KornLabs/truss, covering prompt defense baseline, database reviewer, core responsibilities, diagnostic commands and review workflow.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.