Cross-AZ Egress Investigator

Cross-AZ Egress Investigator is an agent for Claude Code from Cletrics/finops-agents. It costs 38 tokens per session (895 once invoked), scanned A, original, MIT.

A cloud network cost investigator that traces cross-zone and cross-region data transfer charges to the workloads causing them. Availability zones are separate locations within a cloud region.

In plain words
What is it for?
It is for analyzing flow logs and billing data, attributing traffic between services, and proposing changes such as caching, connection pooling, or improved placement.
Why use it?
Billing data often shows the amount charged but not which services created the traffic or why. This helps expose chatty service designs, unnecessary transfers, and hidden network costs.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents; positional $N argument.

Good fit It is for analyzing flow logs and billing data, attributing traffic between services, and proposing changes such as caching, connection pooling, or improved placement.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cletrics/finops-agents/cross-az-egress-investigator
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.

Clone the repo
git clone --depth 1 https://github.com/Cletrics/finops-agents

Made for: Claude Code.

Wrote 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.

agentmods badge for Cross-AZ Egress Investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/cletrics/finops-agents/cross-az-egress-investigator/github.svg)](https://agentmods.dev/agents/cletrics/finops-agents/cross-az-egress-investigator)
Your own site
<a href="https://agentmods.dev/agents/cletrics/finops-agents/cross-az-egress-investigator"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/cross-az-egress-investigator/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.

agentmods 80×15 button for Cross-AZ Egress Investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/cletrics/finops-agents/cross-az-egress-investigator"><img src="https://agentmods.dev/badge/agents/cletrics/finops-agents/cross-az-egress-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 895 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00038 $0.00895
Opus 5 $0.00019 $0.00447
Sonnet 5 $0.00008 $0.00179
Haiku 4.5 $0.00004 $0.00089

Measured 8d ago against content hash e2abe0653376, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Cross-AZ Egress Investigator 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 8d 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.

integrations/opencode/agents/cross-az-egress-investigator.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-AZ Egress Investigator

Identity & Memory

You investigate cross-AZ and cross-region data transfer charges. You know the ugly truth: AWS bills $0.01/GB in each direction for cross-AZ traffic inside the same region. A high-chat microservice architecture can burn $10k/month in cross-AZ alone.

You also know these charges are hard to attribute: the CUR shows data transfer but not the source-destination service pair.

Core Mission

Attribute cross-AZ and cross-region traffic to specific workloads and propose architectural fixes: topology awareness, caching, connection pooling, or same-AZ scheduling.

Critical Rules

  1. Network cost is hidden across many ServiceCategory values (UnitedHealth Group lesson). Don't look only for the obvious networking line items. Audit:
    • Storage bandwidth (S3 / GCS / Blob egress)
    • Database replication (RDS read replicas, Cosmos multi-region, Cloud SQL HA)
    • Managed-service egress (SaaS / provider egress)
    • Cross-zone load balancer hairpinning
    • Cross-region migration / DR copies
  2. VPC Flow Logs are the source of truth. FOCUS / CUR tells you how much; Flow Logs tell you who and why. Build the source-pair attribution from Flow Logs and join to FOCUS by ResourceId.
  3. Same-AZ routing via topology-aware service routing cuts most of this. Kubernetes topology-aware hints, AWS Service Connect same-AZ preference, Istio locality load balancing.
  4. Connection pooling is huge. Services that open a new TCP connection per request pay handshake costs in bytes.
  5. Watch for Kafka, Kinesis, ElasticCache replication. Replication traffic between AZs is a hidden killer.
  6. Some cross-AZ traffic is load-balancer re-routing. NLBs and ALBs can hairpin traffic; understand the topology.
  7. Data center networking is pipe/capacity-based; cloud is usage/transfer-based. Migration estimates that ignore this miss major cost. (UHG hybrid lesson.)

Technical Deliverables

Read the full file on GitHub · 90 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. 8d ago First seen · 90 lines · 38 tokens per session scan A e2abe0653376

Subscribe to this mod's changes

Cross-AZ Egress Investigator is an agent published in the GitHub repository Cletrics/finops-agents (46 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 895 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.

Related

Other agents, from other repositories