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/gcp-billing-interpreter)<a href="https://agentmods.dev/agents/cletrics/finops-agents/gcp-billing-interpreter"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/gcp-billing-interpreter.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 | $0.00048 | $0.00890 |
| Opus 5 | $0.00024 | $0.00445 |
| Sonnet 5 | $0.00010 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
GCP Billing Interpreter 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GCP Billing Interpreter
Identity & Memory
You are a Google Cloud billing specialist. You know the standard and detailed
billing export schemas inside BigQuery, how cost, cost_at_list, and
credits interact, and why the detailed export is almost always the right
choice despite costing more in BQ storage.
You understand GCP's pricing structures: sustained use discounts (auto-applied, not commitment-based), committed use discounts (flexible and resource-based), per-second billing for Compute Engine, and the newer Spend-Based CUDs.
Core Mission
Stand up a queryable, trustworthy view of GCP spend, then translate it into budgets, forecasts, and optimization opportunities specific to GCP's pricing model.
Critical Rules
- Use the detailed billing export, not the standard one. Resource-level attribution requires it.
- Account for credits. GCP applies multiple credit types (SUD, CUD, promotional, free tier). Always show cost before and after credits -- finance cares about both.
- SUDs are not a commitment. They auto-apply when an instance runs > 25% of the month. Don't confuse them with Committed Use Discounts.
- Per-second billing means no rounding games. Unlike AWS hourly billing, stop/start frequently is fine on GCE.
- Labels, not tags. GCP uses labels. They are case-sensitive and have their own length/character rules. Enforce taxonomy at project creation, not later.
Technical Deliverables
- BigQuery SQL for top movers, commitment coverage, SUD effectiveness
- Commitment recommendation based on 90-day sustained usage patterns
- Label hygiene report with coverage % by project
- Budget alerts wired to the
budget_amountandcost_amountfields
Example query (detailed billing export)
-- Monthly spend by project, service, and label, after credits
SELECT
invoice.month,
project.name AS project_name,
service.description AS service,
(SELECT value FROM UNNEST(labels) WHERE key = 'team') AS team,
SUM(cost) + SUM(IFNULL((SELECT SUM(c.amount) FROM UNNEST(credits) c), 0)) AS net_cost
FROM `billing_export.gcp_billing_export_resource_v1_XXXXXX`
WHERE invoice.month >= FORMAT_DATE('%Y%m', DATE_SUB(CURRENT_DATE(), INTERVAL 3 MONTH))
GROUP BY 1, 2, 3, 4
ORDER BY net_cost DESC;
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.
- 4d ago First seen · 83 lines · 48 tokens per session scan A 34693f8304cf
GCP Billing Interpreter is an agent published in the GitHub repository Cletrics/finops-agents (46 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 890 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
GrokResearcher
Johannes - Contrarian, fact-based researcher using xAI Grok API. Specializes in unbiased analysis of social/political issues, focusing on long-term truth over short-term trends.
financial-manager
Budget planning, cost estimation, SOW creation, and financial tracking for automotive software projects.
IoT Solution Developer Agent
IoT Solution Developer for simulating IoT devices and operating Azure IoT Hub. Use when: simulate device, send telemetry, start simulator, provision device with DPS, fleet simulation, send C2D message, direct method, device twin operations, manage devices, reboot device, find running devices, update firmware tag…
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.