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 evgenii-studitskikh/Claude-Code-SaaS-Studio --skill design-architecturegit 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/design-architecture)<a href="https://agentmods.dev/skills/evgenii-studitskikh/claude-code-saas-studio/design-architecture"><img src="https://agentmods.dev/badge/skills/evgenii-studitskikh/claude-code-saas-studio/design-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/evgenii-studitskikh/claude-code-saas-studio/design-architecture"><img src="https://agentmods.dev/badge/skills/evgenii-studitskikh/claude-code-saas-studio/design-architecture.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 | $0.00035 | $0.00556 |
| Opus 5 | $0.00017 | $0.00278 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
design-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.
What it actually says
Produce a lightweight but durable architecture document that records how the Next.js, Supabase, and Stripe layers interact, where the module boundaries sit, and why key decisions were made. Non-autonomous: every significant decision is surfaced as an option before it is recorded.
Phases
- Load context — read
docs/specs/prd.mdanddocs/specs/flows.md. If neither exists, stop and direct the user to earlier skills. Identify the top architectural concerns implied by the feature list (e.g., multi-tenancy, file uploads, scheduled jobs, real-time updates). - Propose system layers — present a concise layer diagram in text: (1) Next.js App Router pages and server components, (2) server actions / route handlers as the API surface, (3) Supabase Postgres with RLS as the data store, (4) Supabase Auth for identity, (5) Stripe for billing. Ask the user to confirm or amend this model.
- Define module boundaries — propose the top-level directory structure under
app/,lib/,components/, andsupabase/. Call out which paths are tenant-scoped and how the tenant ID flows through the request. Present for approval. - Surface and decide ADRs — for each significant decision (e.g., "use server actions vs. route handlers for mutations", "use Supabase Realtime vs. polling", "row-level security strategy"), present the options with trade-offs, recommend one, and record the user's choice as an ADR using
.claude/templates/adr.md. Each ADR goes indocs/specs/adr/NNNN-{slug}.md. - Write architecture doc — fill
docs/specs/architecture.mdwith the approved layer diagram, module map, and ADR index. Underfullreview, present each section; underlean/solo, write after a single confirmation. - Next step — on approval, point to
/design-schemato translate the architecture into database tables.
Output
docs/specs/architecture.md + one docs/specs/adr/NNNN-{slug}.md per decision. Writes nothing without approval.
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 · 23 lines · 35 tokens per session scan A 379725a16b64
design-architecture 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 556 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, Select, 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.
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.
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.
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.