What is Forge CLAUDE.md?

A set of project-wide instructions for an AI coding assistant, covering code quality, security, and how to make decisions when requirements are unclear.

Use it to guide coding work in Forge-generated projects and set baseline expectations for implementation and security.

It gives the assistant consistent rules to follow across a project, including keeping code readable and protecting secrets.

How SultanMuqimi/Forge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to SultanMuqimi/Forge. 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/SultanMuqimi/Forge/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/SultanMuqimi/Forge

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/sultanmuqimi/forge/claude-md/github.svg)](https://agentmods.dev/instructions/sultanmuqimi/forge/claude-md)

Your own site

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

Per session 3,177 This file is loaded in full into every session.

When invoked 3,177 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	$0.03177	$0.03177
Opus 5.5	$0.01271	$0.01271
Sonnet 5.5	$0.00635	$0.00635
Haiku 4.5	$0.00318	$0.00318

Measured 2mo ago against content hash 2adb074be5c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Forge 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 · 353 lines

How it starts

The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Universal Rules

Forge Quality Standards | Applies to Every Project

YOUR ROLE

You are Claude Code working on a project generated via Forge. This file defines the universal standards for how you write code, regardless of the stack. Read this carefully and follow every rule. If a stack-specific CLAUDE.md also exists in this project, those rules combine with these — never override them.

Before you write a single line of code, read this entire file.

CORE PRINCIPLES

Clarity over cleverness. Readable code beats clever code. Always.
Boring is good. Use proven patterns. Avoid experimental approaches unless there is a real reason.
Match complexity to scale. A simple app does not need microservices. A prototype does not need Kubernetes. Build what fits.
If you are unsure, ask the user. Do not guess on business logic.
Finish what you start. Do not leave half-implemented functions. Do not leave TODO comments for things you could do now.

SECURITY — NON-NEGOTIABLE

These rules apply to every project, every time, no exceptions.

Secrets and Configuration

Never hardcode secrets. API keys, passwords, tokens, database URLs all go in environment variables
Create a .env.example file listing every required environment variable with placeholder values
Add .env and .env.local to .gitignore immediately
Never commit real credentials, even briefly

Authentication

Passwords must be hashed with bcrypt (cost factor 12+) or argon2 — never plain text, never MD5, never SHA1
Use JWT with short expiration (15 minutes for access tokens, 7 days for refresh tokens) or server-side sessions
Always validate tokens on every protected request
Implement proper logout that invalidates tokens/sessions server-side

Input Validation

Every API endpoint validates its inputs before doing anything else
Use a validation library (Zod, Joi, Pydantic, FluentValidation, etc.) — never trust raw input
Validate types, ranges, formats, and lengths
Reject unknown fields, do not silently accept them

Read the full file on GitHub · 353 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 · 353 lines · 3,177 tokens per session scan A 2adb074be5c1

Subscribe to this mod's changes

Forge CLAUDE.md is an instructions file published in the GitHub repository SultanMuqimi/Forge (5 stars, last pushed 6mo ago), licensed MIT. It adds 3,177 tokens to every session, about $0.0127 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.

Forge CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Forge CLAUDE.mdSultanMuqimi/Forge	Instructions file	5	6mo ago	MIT	A	3,177	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	yesterday	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

Forge: Instructions file for Claude Code