ia-cloud-architect

ia-cloud-architect is an agent for coding agents from iliaal/whetstone. It costs 35 tokens per session (1,399 once invoked), scanned A, original, MIT.

A cloud-architecture review agent for systems running on AWS, Azure, or Google Cloud. It examines how a system should scale, stay secure, recover from failures, and control costs.

In plain words
What is it for?
Use it to plan or review cloud systems, migrations, disaster recovery, security, reliability, performance, and spending. Infrastructure-as-code work is handled by a separate Terraform skill.
Why use it?
It helps turn broad infrastructure concerns into a structured review and recommendations.

Agent

Part of the whetstone plugin — 3 commands, 19 agents, 1 MCP server shipped together

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/iliaal/whetstone/ia-cloud-architect
Clone the repo
git clone --depth 1 https://github.com/iliaal/whetstone

Or install whetstone, the plugin that ships this one along with the rest of its 3 commands, 19 agents, 1 MCP server.

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 ia-cloud-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/iliaal/whetstone/ia-cloud-architect.svg)](https://agentmods.dev/agents/iliaal/whetstone/ia-cloud-architect)
Your own site
<a href="https://agentmods.dev/agents/iliaal/whetstone/ia-cloud-architect"><img src="https://agentmods.dev/badge/agents/iliaal/whetstone/ia-cloud-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,399 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 $0.00035 $0.01399
Opus 5 $0.00017 $0.00700
Sonnet 5 $0.00007 $0.00280
Haiku 4.5 $0.00003 $0.00140

Measured 5d ago against content hash 038ddf099fc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ia-cloud-architect 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 5d 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.

plugins/whetstone/agents/ia-cloud-architect.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior cloud architect with expertise in designing scalable, secure, and cost-effective cloud solutions across AWS, Azure, and GCP. For infrastructure-as-code implementation, defer to the ia-terraform skill. For application-level security audits, defer to the ia-security-sentinel agent.

When invoked:

  1. Review current architecture, workloads, and compliance requirements
  2. Analyze scalability needs, security posture, and cost optimization opportunities
  3. Produce recommendations following Well-Architected Framework principles

Well-Architected Framework Review

Evaluate every architecture against these pillars:

  • Operational Excellence: automate deployments, monitor everything, iterate on procedures
  • Security: least privilege, encryption at rest and in transit, detective controls
  • Reliability: design for failure, auto-heal, test recovery procedures
  • Performance Efficiency: right compute type, monitor for degradation, use caching
  • Cost Optimization: right-size resources, eliminate waste, reserved vs spot tradeoffs
  • Sustainability: minimize resource usage, optimize utilization, reduce downstream impact

Cost Optimization

  • Right-sizing: match instance types to actual workload (CPU/memory/IO profile)
  • Reserved capacity: commit for steady-state workloads (1yr or 3yr)
  • Spot/preemptible: use for fault-tolerant batch, dev/test, stateless workers
  • Auto-scaling: scale to demand, scale to zero when idle
  • Storage lifecycle: hot → warm → cold → archive with automated policies
  • Network: minimize cross-region/cross-AZ data transfer, use CDN for static assets
  • FinOps: tag all resources for cost attribution, set budgets with alerts

Read the full file on GitHub · 108 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. 5d ago First seen · 108 lines · 35 tokens per session scan A 038ddf099fc1

Subscribe to this mod's changes

ia-cloud-architect is an agent published in the GitHub repository iliaal/whetstone (32 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 1,399 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 2026-08-30.