What is agentic-saas-blueprint CLAUDE.md?

Development rules for an agentic SaaS application built with Next.js, TypeScript, Prisma, Supabase, Stripe, and related tools. The rules cover design, testing, privacy, and external-service behavior.

Use them when planning or implementing features, writing Vitest tests, changing themes or responsive layouts, handling payments or email, or modifying database and authentication code.

They make important project decisions explicit, such as supporting light and dark themes, testing before implementation, protecting personal data, and allowing the app to build without service keys.

How Mohabz35/agentic-saas-blueprint configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Mohabz35/agentic-saas-blueprint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Mohabz35/agentic-saas-blueprint/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Mohabz35/agentic-saas-blueprint

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mohabz35/agentic-saas-blueprint/claude-md/github.svg)](https://agentmods.dev/instructions/mohabz35/agentic-saas-blueprint/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mohabz35/agentic-saas-blueprint/claude-md"><img src="https://agentmods.dev/badge/instructions/mohabz35/agentic-saas-blueprint/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mohabz35/agentic-saas-blueprint/claude-md"><img src="https://agentmods.dev/badge/instructions/mohabz35/agentic-saas-blueprint/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 610 This file is loaded in full into every session.

When invoked 610 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00610	$0.00610
Opus 5	$0.00305	$0.00305
Sonnet 5	$0.00122	$0.00122
Haiku 4.5	$0.00061	$0.00061

Measured 10d ago against content hash b6ef185fcd03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agentic-saas-blueprint CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Default to action. Ask one clarifying question only when ambiguity blocks progress. When asked to plan, deliver complete file paths and code blocks. When asked to build, write the failing test, the code, the commit. When

CLAUDE.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[PROJECT NAME]

[One sentence: what this product is and who it's for]

Production URL: [URL or "TBD"] Branch in active development: main Canonical contact email: [your contact email]

Stack (locked)

Next.js 15 App Router · TypeScript strict · Tailwind (theme tokens, no literals) · Prisma + Supabase · NextAuth v5 · Stripe · Resend · Vitest · Vercel Cron

Non-negotiables

No hardcoded color literals. Use text-text-app, bg-bg-public, text-gold, etc. Tokens flip on [data-theme] in globals.css automatically.
Light + dark mode work on every component, day one.
Mobile-first. Test 375 / 768 / 1280px.
Cards with a destination are clickable <Link> wrappers with hover lift + gold halo.
Admin views show real data with stat tiles, search, filters, pagination.
TDD. Failing vitest first, then impl.
No em-dashes in source files.
PII (SSN, full EIN, card numbers) scrubbed server-side before persistence.
Soft-fail on external services. Every Plaid/Stripe/Resend integration sits behind an env-gated wrapper. App builds without third-party keys.

Workflow

Brainstorm → save spec to docs/superpowers/specs/
Plan → save plan to docs/superpowers/plans/ (file paths + full code, no placeholders)
Subagent execute → task-by-task with TDD + spec review + code-quality review
tsc --noEmit && vitest run && next build → commit → push to main
Verify deploy fired via Vercel MCP. Webhook is unreliable; if commit SHA doesn't match latest READY deploy, run vercel deploy --prod --yes.
Curl /api/health. Confirm 200.

Anti-patterns

"Hotfix" comments that disable features instead of fixing root cause
Building single-theme UI with plans to "add light later"
Component-by-component sweep migrations (use a single CSS specificity layer scoped to [data-theme='light'])
Skipping mobile review
Bare HTML tables in admin pages
Plans with placeholders ("TODO", "fill in details")
Commits without typecheck + vitest first
Trusting the Vercel auto-deploy webhook without verification

Read the full file on GitHub · 50 lines

Changes

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 · 50 lines · 610 tokens per session scan A b6ef185fcd03

Subscribe to this mod's changes

agentic-saas-blueprint CLAUDE.md is an instructions file published in the GitHub repository Mohabz35/agentic-saas-blueprint (22 stars, last pushed 3mo ago), licensed MIT. It adds 610 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

agentic-saas-blueprint: Instructions file for Claude Code