What is forja AGENTS.md?

Development instructions for Forja, a desktop app for working with AI coding command-line tools. Forja uses Electron, React, and TypeScript in a monorepo, meaning one repository contains multiple related apps and packages.

Building and developing Forja's desktop, website, documentation, mobile, and shared packages from the monorepo root.

It gives contributors the project structure and the correct commands and conventions for making changes across the repository.

How nandomoreirame/forja configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to nandomoreirame/forja. 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/nandomoreirame/forja/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/nandomoreirame/forja

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/nandomoreirame/forja/agents-md/github.svg)](https://agentmods.dev/instructions/nandomoreirame/forja/agents-md)

Your own site

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

Per session 1,905 This file is loaded in full into every session.

When invoked 1,905 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	$0.01905	$0.01905
Opus 5.5	$0.00762	$0.00762
Sonnet 5.5	$0.00381	$0.00381
Haiku 4.5	$0.00191	$0.00191

Measured 2mo ago against content hash b11db83e1a50, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

forja 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 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.

AGENTS.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What is Forja

Forja is a desktop GUI client for Vibe Coders and other AI coding CLIs, built as a pnpm monorepo with Electron + React + TypeScript. It features a hybrid rendering approach with xterm.js for terminal emulation and React for rich markdown/code output.

Status: Active development. v1.9.2. Cross-platform: macOS, Linux, Windows.

Monorepo Structure

pnpm workspaces with apps/* and packages/*:

Package	Path	Description
`@forja/desktop`	`apps/desktop/`	Electron desktop app (main product)
`@forja/site`	`apps/site/`	Next.js 15 marketing site (port 3030)
`@forja/docs`	`apps/docs/`	Fumadocs documentation site (port 3031)
`@forja/mobile`	`apps/mobile/`	Expo remote control app (React Native)
`@forja/tsconfig`	`packages/tsconfig/`	Shared TypeScript configs (base, react, node, nextjs)
`@forja/shared`	`packages/shared/`	Shared types and constants (WebSocket bridge, IPC types)

All packages reference each other via workspace:* protocol.

Build Commands

# Development (all from monorepo root)
pnpm dev              # Desktop app (Vite + Electron concurrently)
pnpm dev:site         # Marketing site (Next.js, port 3030)
pnpm dev:docs         # Documentation site (Fumadocs, port 3031)
pnpm dev:mobile       # Mobile app (Expo)

# Build
pnpm build            # Desktop: TypeScript compile + Vite build
pnpm build:electron   # Desktop: full Electron build (dmg/AppImage/deb/nsis)
pnpm build:site       # Site: Next.js static export
pnpm build:docs       # Docs: Next.js build

# Testing
pnpm test             # All workspaces (pnpm -r run test)
pnpm test:desktop     # Desktop only (multi-project: frontend + electron + scripts)

# Cleanup
pnpm clean            # Clean all workspace build artifacts

Running Desktop Tests

# From root (filters to @forja/desktop)
pnpm test:desktop -- path/to/file.test.ts    # Specific file
pnpm test:desktop -- --project frontend      # Frontend tests only (happy-dom)
pnpm test:desktop -- --project electron      # Electron tests only (node)
pnpm test:desktop -- --watch                 # Watch mode

# From apps/desktop/ directly
pnpm test path/to/file.test.ts
pnpm test --project frontend
pnpm test --reporter=verbose
pnpm test:coverage

Read the full file on GitHub · 194 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 · 194 lines · 1,905 tokens per session scan A b11db83e1a50

Subscribe to this mod's changes

forja AGENTS.md is an instructions file published in the GitHub repository nandomoreirame/forja (12 stars, last pushed 7d ago), licensed MIT. It adds 1,905 tokens to every session, about $0.0076 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.

forja AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
forja AGENTS.mdnandomoreirame/forja	Instructions file	12	7d ago	MIT	A	1,905	Codex, OpenCode
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	5,516	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	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

forja: Instructions file for Codex