What is ForgeStart AGENTS.md?

Project instructions for ForgeStart, an open-source Next.js starter application for building operational software such as stock tools, business customer systems, or internal administration tools. It describes the framework, database, login system, permissions, and development workflow.

Use it when adding or changing features involving authentication, user roles, organizations, file uploads, settings, audit records, localization, database access, Docker, or the Next.js application structure.

It tells a coding agent which technologies and project conventions to follow, reducing inconsistent implementation choices. It also clarifies that the project is a foundation rather than a finished product.

How Onurlulardan/ForgeStart configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Onurlulardan/ForgeStart. 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/Onurlulardan/ForgeStart/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Onurlulardan/ForgeStart

Made for: Codex, OpenCode.

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/onurlulardan/forgestart/agents-md/github.svg)](https://agentmods.dev/instructions/onurlulardan/forgestart/agents-md)

Your own site

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

Per session 2,406 This file is loaded in full into every session.

When invoked 2,406 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	$0.02406	$0.02406
Opus 5.5	$0.00962	$0.00962
Sonnet 5.5	$0.00481	$0.00481
Haiku 4.5	$0.00241	$0.00241

Measured 1mo ago against content hash c0b5edae8fe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ForgeStart 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 1mo 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.

AGENTS.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file guides AI agents working on ForgeStart. Read it before making code changes.

Project Identity

ForgeStart is an open-source Next.js starter template derived from the architectural patterns used in ForgeCRUD. It is a clone-and-extend application foundation with real authentication, RBAC, organizations, uploads, settings, audit trails, Docker workflows, and operational checks — intended as a head start for specialized operational software (stock tracking, B2B CRM, internal admin tools), not as a finished product.

The public project name is ForgeStart. Avoid reintroducing older names such as Next Starter, Next Starter V2, nextjsstarter, or nextjstemplate in user-facing code, docs, package metadata, seed data, UI labels, or generated assets.

Current Stack

Next.js 16 App Router with React 19.
TypeScript with strict project-wide checking.
Auth.js v5 with JWT sessions.
PostgreSQL as the only supported database.
Drizzle ORM and Drizzle Kit as the only database layer.
shadcn/ui, Base UI primitives, Lucide icons and Tailwind CSS 4 for UI.
next-intl for localization with tr and en.
Yarn 4 with nodeLinker: node-modules.
Docker Compose for PostgreSQL, migration, seed, realtime, storage and production-like app runs.
Vitest, React Testing Library and Playwright for verification.

Architecture Map

Important folders:

app/                  Next.js routes, pages, layouts, APIs and server actions
components/           App-level components owned by this starter
components/ui/        shadcn-style primitives
db/                   Drizzle schema, connection helpers, migration runner and seeds
drizzle/              Generated SQL migrations committed to source control
i18n/                 next-intl routing and request config
lib/api/              API helpers and route response utilities
lib/api/client/       Client-side API wrappers
lib/auth/             Permission checks, session enrichment and server auth helpers
lib/branding/         Default and database-backed branding helpers
lib/query/            TanStack Query keys and hooks
lib/storage/          Upload validation, storage providers and upload service
lib/system/           Health, setup doctor, version and migration helpers
lib/theme/            Theme presets, tokens and application
lib/validation/       Zod schemas
messages/             Locale JSON files
public/brand/         Default ForgeStart logo assets
scripts/              Local and Docker workflow scripts
server/               Realtime Socket.IO server
tests/e2e/            Playwright smoke and auth setup

Read the full file on GitHub · 250 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.

1mo ago First seen · 250 lines · 2,406 tokens per session scan A c0b5edae8fe1

Subscribe to this mod's changes

ForgeStart AGENTS.md is an instructions file published in the GitHub repository Onurlulardan/ForgeStart (22 stars, last pushed 5mo ago), licensed MIT. It adds 2,406 tokens to every session, about $0.0096 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 2026-08-30.

admin-dashboard nextjs permissions saas starter-template

plan-forge database.instructions.md

Database patterns for .NET — Dapper/EF Core 10, parameterized queries, migration strategy.

srnichols/plan-forge · 1,890 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 · 9,715 tokens

ForgeStart: Instructions file for Codex