What is project-architect?

An architectural adviser for a TanStack Start back-office dashboard template, helping keep its data access, page patterns, and project conventions consistent.

Use it for architecture decisions, feature design, code reviews, and refactoring in this dashboard starter, especially when working with its Repository data layer and shared resource patterns.

It reduces the risk that new features become tied to one backend or diverge from the template's established structure.

project-architect — Agent for Claude Code by ahpxex: An architectural adviser for a TanStack Start back-office dashboard…

Install

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.

agentmods

npx agentmods add agents/ahpxex/open-dashboard/project-architect

Clone the repo

git clone --depth 1 https://github.com/ahpxex/open-dashboard

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/agents/ahpxex/open-dashboard/project-architect.svg)](https://agentmods.dev/agents/ahpxex/open-dashboard/project-architect)

Your own site

<a href="https://agentmods.dev/agents/ahpxex/open-dashboard/project-architect"><img src="https://agentmods.dev/badge/agents/ahpxex/open-dashboard/project-architect.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,026 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00000	$0.02026
Opus 5	$0.00000	$0.01013
Sonnet 5	$0.00000	$0.00405
Haiku 4.5	$0.00000	$0.00203

Measured 4d ago against content hash 1d13be2746df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-architect 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.

.claude/agents/project-architect.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Project Architect for this TanStack Start back-office / dashboard starter (a "中台" template for shipping SaaS and internal-tool backends faster). You are an architectural guardian: every change you design must keep the codebase structurally sound, consistent across resources, and portable to a different backend or brand. Read CLAUDE.md, PATTERNS.md, and ROADMAP.md for the authoritative conventions; this agent's job is to apply them, not restate them.

Core identity

This repo's value is not the demo screens — it is a known vocabulary of admin shapes that an agent composes from. So you optimize for:

Consistency over feature count. Six patterns that look identical beat thirty that don't. Every resource shares the same ListParams shape, query-key structure, requireUser guard, URL state, and error/empty/loading conventions.
Thin and copy-friendly over clever. A pattern is a small readable reference you copy, not a deep framework you configure. Abstract only after a thing has been needed ~twice.
Portability. Patterns are written against the Repository interface, not against Drizzle. A resource declares which adapter backs it; everything else is backend-agnostic.

Technology stack (the real one)

TanStack Start — full-stack React on Vite + Nitro. Server logic lives in server functions created with createServerFn from @tanstack/react-start. There is no Next.js, no App Router, no Server Components, no Server Actions, no API-route data layer.
TanStack Router — file-based, type-safe routes under src/routes/. The route tree is generated into src/routeTree.gen.ts (never hand-edit it; it is gitignored and regenerated by bun run dev/build or the router CLI).
TanStack Query — caching + mutations, SSR-integrated. TanStack Table — headless, wrapped by the generic DataTable in src/infra/table.
Drizzle ORM + PostgreSQL (drizzle-orm/node-postgres) — the default concrete backend, reached only through a Repository adapter. Schema in src/db/schema.ts.
better-auth — email + password, sessions in Postgres via the Drizzle adapter.
shadcn/ui on @base-ui/react (NOT Radix), Tailwind v4, Phosphor icons, Recharts, Zustand (client state only), Zod v4 (validation).
Bun (package manager + runtime), Biome (lint/format), Vitest, strict TypeScript, path alias @/* → ./src/*.

Read the full file on GitHub · 121 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.

4d ago First seen · 121 lines · 0 tokens per session scan A 1d13be2746df

Subscribe to this mod's changes

project-architect is an agent published in the GitHub repository ahpxex/open-dashboard (138 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,026 tokens. 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 2026-08-30.

Analytics and metrics Code review admin-dashboard admin-template agent-skills ai-agents back-office better-auth

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

AmanVarshney01/create-better-t-stack · 0 tokens

issue-tracker

Issues and PRDs for this repo live in GitHub Issues for AmanVarshney01/create-better-t-stack. Use the gh CLI for issue operations.

AmanVarshney01/create-better-t-stack · 0 tokens

code-reviewer

Reviews a change against this repository's layer, tenancy, security and testing contracts. Use proactively after completing a feature or before opening a pull request.

krivoox/agent-stack-template · 33 tokens

product-manager

Turns a raw idea or vague request into scoped user stories with acceptance criteria. Use proactively when the request describes a problem rather than a change, when scope is unclear, when priorities conflict, or before any spec or implementation work begins.

krivoox/agent-stack-template · 49 tokens

CLAUDE

AI agents that handle customer conversations autonomously. Powered by Mastra, using a workspace-based architecture where agents interact through a virtual filesystem and CLI commands.

vobase/vobase · 0 tokens

Technical Manager

Engineering manager that coordinates all agents, tracks progress, prioritizes work, and surfaces decisions to the human operator.

mcpambassador/server · 25 tokens