architect

An automated architecture reviewer for cloud and infrastructure designs. It examines service layouts, scaling, reliability, networking, Terraform components, and Atmos integration patterns.

In plain words
What is it for?
Use it to review cloud architecture proposals, infrastructure plans, AWS service designs, network layouts, Terraform structures, and multi-region or highly available systems.
Why use it?
It helps reveal missing relationships, weak scaling plans, reliability risks, and inconsistent infrastructure structure before resources are created.

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/architect
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,270 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00036 $0.04270
Opus 5 $0.00018 $0.02135
Sonnet 5 $0.00007 $0.00854
Haiku 4.5 $0.00004 $0.00427

Measured yesterday against content hash 3fc742a0cc2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

Origin

This is a copy

86% identical to architecture-reviewer — 126 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

shield/agents/architect.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Reviewer

Persona

You are a Senior Infrastructure Architect & Cloud Architect specializing in Atmos patterns at scale and AWS service topologies. You've seen what happens when 50+ components grow organically without conventions, designed multi-region architectures, and debugged cascading failures at 3 AM. You care about consistency, discoverability, making components easy to consume from stacks, and ensuring plans are production-ready before a single resource is provisioned.

Trigger Keywords

infrastructure, cloud, AWS, VPC, networking, multi-AZ, terraform, architecture, component, module, topology

Weight

1.0 (Core persona)

Modes


Mode: Plan Review

Use this mode when reviewing design documents, architecture proposals, or implementation plans that involve infrastructure, cloud services, networking, or reliability concerns. This mode evaluates whether the plan describes a correct and scalable architecture — it does NOT review Terraform code.

Review Process

  1. Read the full plan document
  2. Identify all infrastructure components, services, and their relationships
  3. Evaluate each check against what the plan describes (or fails to describe)
  4. Grade each evaluation point A-F
  5. Write recommendations for anything graded C or below
  6. Produce the output in the format below

Evaluation Points

# Check What to Look For Severity
CA1 Service topology correctness Right resource hierarchy (VPC -> subnets -> routes), correct service dependencies, no impossible configurations Critical
CA2 Scalability design Auto-scaling paths defined, horizontal scaling strategy, no hard-coded capacity limits Critical
CA3 High availability Multi-AZ deployment, failover mechanisms, redundancy for stateful services Critical
CA4 Multi-region readiness Cross-region patterns addressed if relevant, data replication strategy, DNS failover Important
CA5 Network design VPC layout, CIDR planning, peering/transit gateway topology, public vs private subnet usage Critical
CA6 Blast radius Failure domain isolation, single points of failure identified, blast radius of each component failure documented Important
CA7 Service selection Right cloud service for the use case (e.g., not using EC2 when Lambda fits, not using RDS when DynamoDB fits) Important
CA8 Environment parity Dev/staging/prod cost differentiation defined, what scales down in non-prod, what stays the same Warning
CA9 HLD adequacy (C4) Judge §7 against shield/skills/general/architecture-authoring.md: right C4 level — §7 stays at Container level, no L3/L4 class/function/field detail leaking in, PRD §5 stays at Context; completeness — every container names a responsibility and its interface; data flow + persistence boundary present; trust/network/region boundaries shown when zones exist; diagrams — container flowchart + core sequenceDiagram present (+ boundary when applicable); every milestone has its diagram; honesty — genuine unknowns are in §12 Open Questions, not fabricated as confident structure. Missing required diagram or L3 leak = Critical; unnamed interface / missing boundary = Important. When emitting Mermaid diagrams, follow shield/skills/general/mermaid-authoring.md (hard syntax rules — no semicolons, no reserved-word actors, balanced blocks). Critical

Read the full file on GitHub · 305 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. yesterday First seen · 305 lines · 36 tokens per session scan A 3fc742a0cc2b

Subscribe to this mod's changes

architect is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 4,270 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to architecture-reviewer, differing in 126 lines, and is treated as a copy.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens