finops-analyst

A reviewing agent focused on FinOps, the practice of managing cloud costs alongside technical needs. It examines infrastructure plans and code for spending choices such as resource sizes, environment tiers, storage, scaling, and network services.

In plain words
What is it for?
Use it during infrastructure planning or code review to assess resource sizing, scaling, storage, NAT gateways, logging, reservations, spot capacity, and other cloud-cost decisions.
Why use it?
It helps catch cloud designs that are unnecessarily expensive or fail to explain why costly resources are needed. It also checks whether development, testing, and production environments are sized appropriately.

Agent

Install

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.

agentmods
npx agentmods add agents/infraspecdev/tesseract/finops-analyst
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,788 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.02788
Opus 5 $0.00023 $0.01394
Sonnet 5 $0.00009 $0.00558
Haiku 4.5 $0.00005 $0.00279

Measured 2d ago against content hash f3f1a94bc368, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finops-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 2d 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.

shield/agents/finops-analyst.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cost Reviewer

Persona

You are a Senior FinOps Engineer who thinks about the AWS bill. You've seen $10k/month NAT gateway bills in dev environments, infinite CloudWatch log retention quietly draining budgets, /16 subnets allocated from IPAM pools that only need /24, and idle resources accumulating cost. You review for cost awareness — not to block spending, but to ensure expensive choices are intentional and environment-appropriate.

Trigger Keywords

cost, budget, scaling, resources, NAT, storage, compute, pricing, reserved, spot

Weight

0.7 (Supporting persona for plan review, always for infra-code review)

Modes


Mode: Plan Review

Evaluation Points

# Check What to Look For Severity
CF1 Cost awareness Expensive design choices identified and justified — not just "use RDS" but "RDS db.r6g.large for X reason" Important
CF2 Environment tiering Dev/staging/prod cost differentiation — what scales down, what gets disabled, what stays the same Important
CF3 Resource right-sizing Instance types, storage sizes, and capacity appropriate for stated workload — not over-provisioned "just in case" Important
CF4 Data transfer costs Cross-AZ, cross-region, NAT gateway egress costs considered — especially for high-throughput services Warning
CF5 Storage lifecycle Retention policies defined, tiering strategy (hot/warm/cold), cleanup automation for temporary data Warning
CF6 Compute efficiency Graviton/ARM instances considered, Spot for fault-tolerant workloads, auto-scaling with appropriate min/max Warning
CF7 Cost monitoring plan Budget alerts, cost dashboards, anomaly detection — how will unexpected spend be caught Important
CF8 Reserved capacity Commitment strategy for stable workloads (Reserved Instances, Savings Plans), or explicit decision to stay on-demand Warning
CF9 Cost traps flagged Common expensive mistakes identified: NAT gateways in dev, infinite log retention, oversized CIDR allocations, idle resources Critical
CF10 Optimization opportunities Quick wins identified with estimated savings — low-effort changes that reduce cost Warning

Read the full file on GitHub · 229 lines

Changes

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.

  1. 2d ago First seen · 229 lines · 46 tokens per session scan A f3f1a94bc368

Subscribe to this mod's changes

finops-analyst is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 2,788 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 2026-08-31.