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/evgenii-studitskikh/claude-code-saas-studio/startnpx skills add evgenii-studitskikh/Claude-Code-SaaS-Studio --skill startgit clone --depth 1 https://github.com/evgenii-studitskikh/Claude-Code-SaaS-StudioWrote 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/evgenii-studitskikh/claude-code-saas-studio/start)<a href="https://agentmods.dev/skills/evgenii-studitskikh/claude-code-saas-studio/start"><img src="https://agentmods.dev/badge/skills/evgenii-studitskikh/claude-code-saas-studio/start.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 | $0.00035 | $0.00483 |
| Opus 5 | $0.00017 | $0.00242 |
| Sonnet 5 | $0.00007 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
start 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.
What it actually says
Orient the user within the SaaS Studio and route them to the correct starting skill based on where they are in the product lifecycle. Non-autonomous: asks one scoped question, presents options, waits for the user's choice before doing anything else.
Phases
- Probe stage — ask the user which best describes their situation: (a) no idea yet, (b) vague concept / rough idea, (c) clear design / written spec, (d) existing codebase to extend. Wait for their answer before continuing.
- Detect artifacts — check whether
docs/specs/idea-validation.md,docs/specs/prd.md,docs/specs/architecture.mdalready exist to refine the routing; do not assume a stage if evidence contradicts the user's answer. - Route — apply routing logic: (a/b) no idea or vague → recommend
/validate-idea; (c) clear design → recommend/write-prdif no PRD exists, or/setup-stackif PRD exists; (d) existing code → recommend/studio-statusfirst, then/write-prdif no PRD exists, else/design-architecture. - Show the studio map — print a concise phase overview: Navigation skills → Product & UX → Engineering → Billing (
/design-pricing → /setup-billing) → Harden (/qa-plan → /test-setup → /write-tests;/security-audit · /threat-model · /compliance-check) → Infra & Launch, with a one-line description of each phase. Highlight where the user is right now. - Confirm next step — present the recommended skill as a suggestion, not a command. Let the user accept, override, or ask questions.
Output
Routing guidance only — this skill writes no files. Ends by naming the exact slash command the user should run next.
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 · 22 lines · 35 tokens per session scan A 9bb86c5e0a60
start is a skill published in the GitHub repository evgenii-studitskikh/Claude-Code-SaaS-Studio (1 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 483 once invoked, about $0.0002 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
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
gemigo-cli
Use when the user wants to publish an already-built static website or front-end app through GemiGo, such as a Vite/React/Vue static build, plain HTML/CSS/JS page, landing page, demo, docs site, or small browser app, and get a hosted public URL.
ap-juror
L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.
agenticx-query-data-source
Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.