AWS Startups is an official AWS repository containing plugins, skills, tools, and other resources for people building startup products on Amazon Web Services. Its add-ons support startup-focused architecture, migration, and development work on AWS.
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.
npx agentmods add skills/awslabs/startups/multi-tenant-isolationnpx skills add awslabs/startups --skill multi-tenant-isolationgit clone --depth 1 https://github.com/awslabs/startupsWrote 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.
[](https://agentmods.dev/skills/awslabs/startups/multi-tenant-isolation)<a href="https://agentmods.dev/skills/awslabs/startups/multi-tenant-isolation"><img src="https://agentmods.dev/badge/skills/awslabs/startups/multi-tenant-isolation.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00166 | $0.01894 |
| Opus 5 | $0.00083 | $0.00947 |
| Sonnet 5 | $0.00033 | $0.00379 |
| Haiku 4.5 | $0.00017 | $0.00189 |
Grade A, and why
multi-tenant-isolation 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Tenant Isolation on AWS
Tenant isolation is the architectural decision a SaaS startup is least able to reverse and most likely to get wrong under time pressure. Getting it wrong produces either a cross-tenant data leak, which is an existential incident for a company selling to businesses, or a per-tenant cost floor that makes the unit economics never work.
The mistake is treating it as one decision. It is a decision per layer, and the layers can differ.
Choose a model per layer, not per application
| Model | What it means | Isolation | Cost per tenant | Where it fits |
|---|---|---|---|---|
| Silo | Dedicated resource per tenant | Strongest, enforced by resource boundary | Highest, floors multiply | Regulated or contractual isolation, or one customer large enough to fund it |
| Pool | Shared resource, logical separation | Weakest, depends on your correctness | Lowest, marginal per tenant | Default for most tenants, especially self-serve |
| Bridge | Shared infrastructure, dedicated slice inside it | Middle, enforced by partition | Low to medium | Pooled compute with per-tenant schema or table |
Pick per layer. A common and correct shape: pooled compute, bridge-model database (schema or partition key per tenant), siloed only for the customer whose contract requires it.
The trap. Going full silo because it is easier to reason about, then discovering the fixed floors multiply by tenant count. Each dedicated Aurora Serverless v2 cluster carries a floor around 0.5 ACU whether or not the tenant is active. Each OpenSearch Serverless collection carries a substantial monthly minimum. Ten silo tenants on floored services is a large bill for near-zero usage. Verify current minimums with the aws-billing-and-cost-management skill in aws-core before committing to a silo model, since these change.
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.
- 4d ago First seen · 99 lines · 166 tokens per session scan A b514731d64e0
multi-tenant-isolation is a skill published in the GitHub repository awslabs/startups (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 166 tokens to every session and 1,894 once invoked, about $0.0008 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 2026-09-02.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…