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 skills add magnus919/agent-skills --skill multi-tenant-saas-architecturegit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/multi-tenant-saas-architecture)<a href="https://agentmods.dev/skills/magnus919/agent-skills/multi-tenant-saas-architecture"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/multi-tenant-saas-architecture/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.
<a href="https://agentmods.dev/skills/magnus919/agent-skills/multi-tenant-saas-architecture"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/multi-tenant-saas-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00121 | $0.01385 |
| Opus 5 | $0.00060 | $0.00692 |
| Sonnet 5 | $0.00024 | $0.00277 |
| Haiku 4.5 | $0.00012 | $0.00138 |
Grade A, and why
multi-tenant-saas-architecture 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Tenant SaaS Architecture
Use this skill to join product tenancy semantics to system boundaries and operating decisions. It owns the cross-cutting architecture choice, not the implementation or specialist evidence behind each choice.
Workflow
- Frame the service promise. Identify customer/account shape, users and operators, subscription commitments, regions, data classes, lifecycle states, support model, scale assumptions, and unknowns. Separate contractual promises from aspirations.
- Define tenant semantics. Load
references/tenant-domain-model-and-boundaries.md. Establish tenant, account, organization, user, membership, subscription, entitlement, resource, and environment meanings, ownership, cardinality, and lifecycle authority. - Separate planes. Load
references/control-and-application-planes.md. Draw the control-plane policy and lifecycle responsibilities apart from application-plane request and data serving, including asynchronous handoffs and failure behavior. - Choose isolation per resource. Load
references/tenancy-and-data-partitioning-models.md. Compare pooled, bridge, silo, and hybrid choices by data, compute, cache, queue, search, and operational resource. Record why the choice meets the promise and what can trigger a change. - Connect the commercial path. Load
references/onboarding-identity-entitlements-metering-billing.md. Trace signup, identity, provisioning, configuration, entitlement evaluation, usage capture, invoice authority, suspension, support, and reactivation without making billing or security policy implicit. - Design lifecycle and operations. Load
references/tenant-aware-operations-capacity-and-cost.md. Cover deployment, observability, quotas, hot tenants, restore scope, export/deletion, cost attribution, and escalation. Route evidence-heavy decisions to the specialist owners. - Record and challenge. Use
templates/saas-architecture-brief.md,templates/tenancy-decision-record.md, andtemplates/tenant-lifecycle-checklist.md. Test cross-tenant safety, lifecycle idempotency, entitlement lag, billing disagreement, restore scope, and noisy-neighbor behavior.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 6.8 KB
- README.md 2.0 KB
- references/control-and-application-planes.md 1.6 KB
- references/onboarding-identity-entitlements-metering-billing.md 1.7 KB
- references/source-index.md 2.3 KB
- references/tenancy-and-data-partitioning-models.md 1.8 KB
- references/tenant-aware-operations-capacity-and-cost.md 1.9 KB
- references/tenant-domain-model-and-boundaries.md 2.1 KB
- templates/saas-architecture-brief.md 1.7 KB
- templates/tenancy-decision-record.md 824 B
- templates/tenant-lifecycle-checklist.md 1.4 KB
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.
- 9d ago First seen · 70 lines · 121 tokens per session scan A eeefc867297d
multi-tenant-saas-architecture is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 1,385 once invoked, about $0.0006 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.
Other skills, from other repositories
technical-integrations
Hunt existing integration patterns and design vendor/framework-agnostic API, RFC, SDK, and integration plans for new external vendor integrations.
xurl-api-probing
Probe APIs directly and methodically before assuming the client or app layer is at fault.
routing
Version: 1.0 Autor: BACH System Datum: 2026-02-18 API-Key: Nicht erforderlich (OSRM public, Nominatim).
weather
Version: 1.0 Autor: BACH System Datum: 2026-02-18 API-Key: Nicht erforderlich (wttr.in).
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
implement-fastapi-routes
The file docstring contains a description of the FastAPI routes we need to implement. Implement these routes.