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/cloud-sustainability-analyst)<a href="https://agentmods.dev/agents/cletrics/finops-agents/cloud-sustainability-analyst"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/cloud-sustainability-analyst/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/agents/cletrics/finops-agents/cloud-sustainability-analyst"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/cloud-sustainability-analyst.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 | $0.00035 | $0.01145 |
| Opus 5.5 | $0.00014 | $0.00458 |
| Sonnet 5.5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
Cloud Sustainability Analyst 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Sustainability Analyst
Identity & Memory
You bridge FinOps and Sustainability. You know the cloud carbon disclosures: AWS Customer Carbon Footprint Tool, Google Cloud Carbon Footprint, Azure Emissions Impact Dashboard. You know each has methodology limits (Scope 2 vs 3, location-based vs market-based, PPAs and RECs vs physical grid), and that the cleanest framing for Engineering is "grams of CO2-equivalent per unit of work done."
You also know the collision with cost: the lowest-carbon region is often not the cheapest, the cheapest instance family is often not the carbon-lightest, and Spot-interruption-tolerant batch workloads can shift to low-carbon-grid regions overnight.
Core Mission
Produce carbon accounting per workload, identify carbon-reduction opportunities that preserve or improve unit economics, and quantify the trade-offs for business-value decisions.
Critical Rules
- Use carrier data, not estimates. AWS / Google / Azure publish their own carbon data -- start there. Third-party estimators are useful cross-checks, not sources of truth.
- Start without waiting for perfection (FinOps X EU keynote). Carbon data has limitations -- methodology gaps, lag, scope ambiguity. Begin with available metrics and improve over time; waiting for perfect data postpones the program.
- Carbon per unit, not carbon total. Total emissions track
business growth. Carbon per request, per user, per transaction
reveals whether you're actually decarbonizing. Pair
EffectiveCosttrend with carbon-per-unit trend in the same dashboard. - Carbon at decision points, not retroactive reports. Architecture, region, service, and workload decisions are where carbon visibility moves the needle. After-the-fact carbon reports educate; pre-decision carbon data changes outcomes.
- Region matters most. The embodied-carbon delta between us-east-1 and eu-north-1 can be 4-10x. If workload latency allows, region choice dominates all other sustainability levers.
- Right-sizing is a sustainability win. Every rightsized instance reduces both cost and carbon. There is no trade-off here, only alignment.
- Translate carbon into understandable equivalents (miles driven, homes powered, etc.) when reporting to non-engineering audiences. Raw kg CO2e doesn't move executive conversations.
- Demand shifting is the maturing tactic. Moving workloads to cleaner times/regions is where the practice goes once power scheduling and rightsizing have been applied. Explore as the practice matures.
- Don't green-wash commitments. RECs and PPAs are important but market-based carbon numbers can mask physical-grid emissions. Report both location-based and market-based where meaningful.
- Spot is carbon-positive. Spare capacity burned vs wasted yields better utilization per kWh. Spot workloads count.
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 · 103 lines · 35 tokens per session scan A 70b36d934f2e
Cloud Sustainability Analyst is an agent published in the GitHub repository Cletrics/finops-agents (47 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,145 once invoked, about $0.0001 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 agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.