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 MartinOlivero/saas-builder --skill saas-routergit clone --depth 1 https://github.com/MartinOlivero/saas-builderWrote 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/martinolivero/saas-builder/saas-router)<a href="https://agentmods.dev/skills/martinolivero/saas-builder/saas-router"><img src="https://agentmods.dev/badge/skills/martinolivero/saas-builder/saas-router/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/martinolivero/saas-builder/saas-router"><img src="https://agentmods.dev/badge/skills/martinolivero/saas-builder/saas-router.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00189 | $0.02199 |
| Opus 5 | $0.00095 | $0.01099 |
| Sonnet 5 | $0.00038 | $0.00440 |
| Haiku 4.5 | $0.00019 | $0.00220 |
Grade A, and why
saas-router 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SaaS Router
This skill is the brain of the saas-builder plugin. It runs before any product work and decides which specialist skill should handle the request.
The one rule that cannot be broken
Do NOT write code, design a UI, or pick a stack before routing through this skill. Jumping straight to implementation is the most common failure mode — it produces generic output that ignores what the user actually needs. Route first, build second.
Analogy: this is the triage nurse at a hospital. Nobody goes straight to surgery. The nurse asks two or three quick questions, then sends the patient to the right specialist.
Workflow
Step 1 — Ask 2-3 quick routing questions
Do not interrogate. Ask only what is needed to classify the request. Pick from:
- "What are you building — a landing page, a dashboard, or a full app/SaaS?"
- "Do you already know exactly what it should do, or are you still shaping the idea?"
- "Is there an existing product/codebase, or are we starting from zero?"
If the user's first message already answers these (e.g. "build me a pricing landing page for my course"), skip straight to routing — do not re-ask what is already known.
Step 2 — Route to the right specialist
Match the request (English or Spanish) against this table and activate the matching skill. The plugin covers the whole build lifecycle — discovery, architecture, build, secure, monetize, polish, ship.
Plan & design
| User says / wants | Route to |
|---|---|
| "SaaS", "platform", "app", "MVP", "product" / "idea para", idea not fully defined | product-discovery → architecture-primer → build skills → ui-design |
| "architecture", "how do I structure this", "scale", "what stack" / "cómo lo estructuro", "qué stack" | architecture-primer |
| "landing", "sales page", "lead capture" / "página de ventas", "captar leads" | landing-page (structure + copy) + design-taste-frontend (visual execution) |
| "portfolio", "marketing site", "agency site", "editorial/blog", "make a website that doesn't look AI-generated", website redesign / "portfolio", "sitio de marketing", "que no parezca hecho por IA", "rediseñar mi web" | design-taste-frontend |
| "dashboard", "admin", "backoffice", "internal tool", "data table", product/app UI / "panel", "tablero", "interfaz de la app" | ui-design (dashboard mode) |
| Component, colors, design system for an app, dark mode for product UI / "componente", "design system de la app" | ui-design |
| "copy this design", "make it look like this screenshot/site", reference image of a web they like / "cloná esta web", "hacelo como esta captura" | image-to-code |
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.
- 10d ago First seen · 110 lines · 189 tokens per session scan A 7489a0be8b4e
saas-router is a skill published in the GitHub repository MartinOlivero/saas-builder (2 stars, last pushed 22d ago), licensed MIT. It adds 189 tokens to every session and 2,199 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
architecture-paradigm-microkernel
Applies microkernel architecture with minimal core and plugin extensibility. Use when building platforms where third parties extend core functionality.
plan
Use when a task needs structured planning before implementation. Supports --delegate and round=N[,M].
preplan
Use when a problem needs clarification and agreement before planning begins. Supports --deep and --delegate.
ralph
Use when implementing a plan or executing a prompt that requires verified completion.
pathfind
Use when you have problems but don't know what to build.
analyze
Use when deep investigation is needed — project structure, requirement gaps, or root cause diagnosis. Supports --delegate.