react-starter-kit AGENTS.md

Project-specific instructions for working on a web application split across several related packages, including its frontend, API, email templates, database, infrastructure, and documentation.

In plain words
What is it for?
Use them when changing features, running database commands, checking builds, or working across this monorepo—a repository that contains multiple connected applications and shared packages.
Why use it?
They give a coding agent the project’s layout, tools, commands, and runtime limits so it can make changes that fit the existing codebase.

Instructions file for CodexOpenCode

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 instructions/kriasoft/react-starter-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/kriasoft/react-starter-kit

Made for: Codex, OpenCode.

Per session 1,319 This file is loaded in full into every session.
When invoked 1,319 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01319 $0.01319
Opus 5 $0.00660 $0.00660
Sonnet 5 $0.00264 $0.00264
Haiku 4.5 $0.00132 $0.00132

Measured yesterday against content hash 3dc195ff07db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

react-starter-kit AGENTS.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 yesterday.

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.

AGENTS.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Monorepo Structure

  • apps/web/ – Astro marketing site, served by an edge worker that also routes traffic to the app/api workers via service bindings
  • apps/app/ – Main SPA (React, TanStack Router file-based routing)
  • apps/api/ – API server (Hono + tRPC + Better Auth)
  • apps/email/ – React Email templates (built before API dev server starts)
  • packages/ui/ – shadcn/ui components (new-york style)
  • packages/core/ – Shared utilities
  • db/ – Drizzle ORM schemas and migrations (Neon PostgreSQL)
  • infra/ – Terraform (Hyperdrive and optional R2 storage; Wrangler owns Workers and DNS)
  • docs/ – VitePress docs; docs/adr/ for architecture decision records

Tech Stack

  • Toolchain: Bun >=1.4.0 (package manager, scripts, local API server), TypeScript 6.0, ESM ("type": "module")
  • Production runtime: Cloudflare Workers (workerd) – not Bun. Code that ships must run on Workers APIs.
  • Frontend: React 19, TanStack Router, TanStack Query, Jotai, shadcn/ui (new-york), Tailwind CSS v4
  • Backend: Hono, tRPC 11, Better Auth (email OTP, passkey, Google OAuth, organizations)
  • Database: Neon PostgreSQL, Drizzle ORM (snake_case casing), Cloudflare Hyperdrive
  • Email: React Email, Resend
  • Testing: Vitest, Happy DOM, PGlite (in-process Postgres, no service to start)
  • Deployment: Cloudflare Workers (Wrangler), Terraform

Commands

bun dev                        # Start web + api + app concurrently
bun run build                  # Build email, web, api, and app workspaces
bun run test                   # Vitest (watch mode; --run for single run)
bun lint                       # ESLint with cache
bun typecheck                  # tsc --build (builds apps/email for its types)
bun infra:check                # Terraform fmt + validate, no credentials or state
bun ui:add <component>         # Add shadcn/ui component to packages/ui
bun deploy:{staging,production} # Build and deploy api → app → web; no migrations

# Per-app: bun {web,app,api}:{dev,build,deploy}; test for app/api, check for web
# Database: bun db:{push,generate,migrate,studio,seed,export}
#   :staging / :production on migrate, studio, export; seed stops at :staging;
#   generate is local-only, and push refuses a non-local database

Read the full file on GitHub · 77 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.

  1. yesterday First seen · 77 lines · 1,319 tokens per session scan A 3dc195ff07db

Subscribe to this mod's changes

react-starter-kit AGENTS.md is an instructions file published in the GitHub repository kriasoft/react-starter-kit (23,671 stars, last pushed 8d ago), licensed MIT. It adds 1,319 tokens to every session, about $0.0066 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 2026-08-30.

Related

Other instructions, from other repositories