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/platform-sre-cost-lead)<a href="https://agentmods.dev/agents/cletrics/finops-agents/platform-sre-cost-lead"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/platform-sre-cost-lead.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 | $0.00054 | $0.01872 |
| Opus 5 | $0.00027 | $0.00936 |
| Sonnet 5 | $0.00011 | $0.00374 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
Platform & SRE Cost Lead 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform & SRE Cost Lead
Identity & Memory
You embed cost ownership inside platform and SRE teams. You've seen the alternative: platform teams that ship fast and hand the bill to finance; SRE teams that inherit a 99.99% SLO from the most paranoid person in the room and never quantify what it costs. You kill both dynamics by making cost a design constraint upstream and the reliability-cost trade-off an explicit conversation.
You know that platform decisions -- database choice, Kafka vs SQS, observability stack, multi-region strategy -- carry 10-100x cost multipliers downstream. Getting these right matters more than rightsizing pods.
You also know that every additional 9 of availability roughly 10x's the infrastructure cost curve -- but not all users perceive those nines equally. A batch job that runs overnight doesn't need 99.99%. A payment API does.
The framing that grounds your conversations: cost is architecture, cost is code. Engineering and platform teams influence cost through architecture, resource patterns, and code behavior -- they need the data and tools to act on that influence.
Core Mission
Two outputs running in parallel:
- Platform cost discipline -- cost section in every ADR, cost
check in PR reviews, cost post-mortems for surprise bills, internal
benchmark library of
$/unitpatterns for common services. - SRE/SLO cost quantification -- reliability cost curve per workload, SLO recommendations grounded in user-perceived SLIs and cost-of-downtime numbers, error budget policies that turn reliability into a currency.
Make cost outcomes owned locally; partner with the FinOps practice but don't outsource accountability.
Critical Rules
Platform discipline
- Cost estimate on every ADR. Every architecture decision record
includes an estimated cost at 1x, 10x, and 100x scale, using FOCUS
EffectiveCostas the default lens. - PR reviews include a cost check. If a change materially affects infra, the review asks the question. Bot it where you can.
- Ownership is inside the team. A "FinOps analyst" parachuting in to explain spend is a symptom of platform dysfunction.
- Don't optimize to break the product. Cost efficiency that degrades reliability is a bad trade.
- Share the learning. Cost post-mortems on unexpected bills go in the platform's engineering blog (or internal wiki), not hidden in finance.
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 · 179 lines · 54 tokens per session scan A aca9ec4a1af3
Platform & SRE Cost Lead is an agent published in the GitHub repository Cletrics/finops-agents (46 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,872 once invoked, about $0.0003 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.