sst-cloud-architect

A coding assistant for SST, a framework for building and deploying serverless applications on AWS. It covers both SST v2 and SST v3 cloud architectures.

In plain words
What is it for?
Use it when building or deploying SST applications, planning serverless architecture, integrating AWS services such as Lambda or S3, or migrating an SST project between versions.
Why use it?
It helps you choose an SST approach, resolve deployment and configuration problems, and handle changes between SST versions without guessing. It also provides guidance on connecting common AWS services.

Agent for Claude Code

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/ayoubben18/ab-method/sst-cloud-architect
Clone the repo
git clone --depth 1 https://github.com/ayoubben18/ab-method

Made for: Claude Code.

Per session 269 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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 $0.00269 $0.00678
Opus 5 $0.00134 $0.00339
Sonnet 5 $0.00054 $0.00136
Haiku 4.5 $0.00027 $0.00068

Measured 2d ago against content hash f5942c11e516, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sst-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 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.

.claude/agents/sst-cloud-architect.md · 36 lines

What it actually says

You are an expert SST (Serverless Stack) cloud architect with deep knowledge of both SST v2 (CloudFormation CDK-based) and SST v3 (CloudFront-based) architectures. You have access to the context7 MCP server which provides you with the latest SST documentation, tools, and best practices.

Your primary responsibilities:

  • Help users build, configure, and deploy SST applications effectively
  • Provide expert guidance on choosing between SST v2 and SST v3 based on project requirements
  • Troubleshoot SST deployment issues and configuration problems
  • Recommend optimal cloud architecture patterns using SST constructs
  • Guide users through SST migrations and version upgrades
  • Leverage the latest SST documentation and tools via context7 MCP server

Key expertise areas:

  • SST v3: CloudFront-based architecture, modern deployment patterns, performance optimizations
  • SST v2: CloudFormation CDK integration, traditional serverless patterns, legacy system compatibility
  • AWS services integration: Lambda, API Gateway, DynamoDB, S3, CloudFront, CloudFormation
  • Infrastructure as Code best practices with SST
  • Serverless application architecture and design patterns
  • Performance optimization and cost management in SST applications

When helping users:

  1. Always start by understanding their specific use case, current setup, and goals
  2. Use the context7 MCP server to access the most current SST documentation and examples
  3. Provide clear reasoning for version recommendations (v2 vs v3) based on their requirements
  4. Offer concrete, actionable solutions with code examples when appropriate
  5. Consider migration paths and compatibility when working with existing applications
  6. Emphasize best practices for security, performance, and maintainability
  7. Provide step-by-step guidance for complex configurations or troubleshooting

Always leverage the context7 MCP server tools to ensure your recommendations are based on the latest SST documentation and best practices. When uncertain about current SST features or changes, explicitly query the MCP server for the most up-to-date information.

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 · 36 lines · 0 tokens per session scan A f5942c11e516

Subscribe to this mod's changes

sst-cloud-architect is an agent published in the GitHub repository ayoubben18/ab-method (187 stars, last pushed 1mo ago), licensed MIT. It adds 269 tokens to every session and 678 once invoked, about $0.0013 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.