What is tstack CLAUDE.md?

Project-specific instructions for tstack, a multi-tenant SaaS starter kit: one product serving multiple organizations with separated data. It documents the apps, shared package, database, authentication, tools, and commands in its Turborepo and Bun monorepo, a repository containing several related apps and packages.

Use it when working on the tstack API, web frontend, mobile app, shared schemas, authentication, organization-specific data, or development commands.

It gives coding agents the project facts they need before changing code, reducing wrong paths, commands, package names, or assumptions about the backend, web app, and mobile app.

How narpatsinghpurohit/tstack configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to narpatsinghpurohit/tstack. 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/narpatsinghpurohit/tstack/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/narpatsinghpurohit/tstack

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/narpatsinghpurohit/tstack/claude-md/github.svg)](https://agentmods.dev/instructions/narpatsinghpurohit/tstack/claude-md)

Your own site

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

Per session 1,609 This file is loaded in full into every session.

When invoked 1,609 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.01609	$0.01609
Opus 5.5	$0.00644	$0.00644
Sonnet 5.5	$0.00322	$0.00322
Haiku 4.5	$0.00161	$0.00161

Measured 2mo ago against content hash 5dd15c9431df, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tstack CLAUDE.md 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 2mo 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.

CLAUDE.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Config

Setting	Value
Project name	tstack
Shared package	`@tstack/shared`
Backend	`apps/api/` (NestJS, port 8000)
Web	`apps/web/` (React + Vite, port 5173)
Mobile	`apps/mobile/` (React Native)
Database	MongoDB + Mongoose
Auth	JWT (access + refresh tokens)
Multi-tenant field	`orgId`
Tenant entity	Organization
Package manager	bun
Linter	Biome
Queue	BullMQ + Redis
Email	Nodemailer (SMTP)

Skills and agents read this table to adapt to your project. Update values above when forking for a new project. For example, change orgId to workspaceId or companyId if that fits your domain.

Project overview

Multi-tenant SaaS starter kit (Turborepo + Bun monorepo). NestJS + Mongoose backend, React 19 + Vite web frontend, React Native mobile app. Zod schemas shared between all apps via the shared package. Fork this repo and build your product on top.

Quick reference

What	Where
Backend	`apps/api/`
Web frontend	`apps/web/`
Mobile app	`apps/mobile/`
Shared schemas	`packages/shared/src/schemas/`
Permission constants	`packages/shared/src/constants/`
Permission helpers	`packages/shared/src/permissions/`
Types	`packages/shared/src/types/`
Feature specs	`specs/`

Commands

bun install          # Install all deps
bun run dev          # Start all apps (Turborepo)
bun run build        # Build all
bun run lint         # Biome check
bun run test         # Run all tests
bun run type-check   # TypeScript check
bun seed             # Run all seeders
bun seed --fresh     # Re-seed (overwrites role permissions)
bun seed --class=X   # Run single seeder

Architecture rules

Backend (NestJS)

Controller → Service → Repository → Mongoose (never skip layers)
Every entity repository extends BaseRepository (auto-scopes queries by tenant field)
Every endpoint needs @Can(PERMISSIONS.X) or @CanAny(...) + @CurrentUser() for tenant scoping
Validation via ZodValidationPipe with schemas from the shared package
DTOs defined ONLY in packages/shared/src/schemas/, never locally
Seeding via DatabaseSeeder with dedicated Seeder classes
Queue processing via BullMQ processors in core/queue/

Read the full file on GitHub · 142 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.

2mo ago First seen · 142 lines · 1,609 tokens per session scan A 5dd15c9431df

Subscribe to this mod's changes

tstack CLAUDE.md is an instructions file published in the GitHub repository narpatsinghpurohit/tstack (5 stars, last pushed 7mo ago), licensed MIT. It adds 1,609 tokens to every session, about $0.0064 per session on Opus 5.5. 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.

tstack CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tstack CLAUDE.mdnarpatsinghpurohit/tstack	Instructions file	5	7mo ago	MIT	A	1,609	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

tstack: Instructions file for Claude Code