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.
npx agentmods add instructions/sultanmuqimi/forge/claude-mdgit clone --depth 1 https://github.com/SultanMuqimi/ForgeWrote 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.
[](https://agentmods.dev/instructions/sultanmuqimi/forge/claude-md)<a href="https://agentmods.dev/instructions/sultanmuqimi/forge/claude-md"><img src="https://agentmods.dev/badge/instructions/sultanmuqimi/forge/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03177 | $0.03177 |
| Opus 5 | $0.01588 | $0.01588 |
| Sonnet 5 | $0.00635 | $0.00635 |
| Haiku 4.5 | $0.00318 | $0.00318 |
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 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.
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.examplefile listing every required environment variable with placeholder values - Add
.envand.env.localto.gitignoreimmediately - 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
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 · 353 lines · 3,177 tokens per session scan A 2adb074be5c1
Forge CLAUDE.md is an instructions file published in the GitHub repository SultanMuqimi/Forge (5 stars, last pushed 4mo ago), licensed MIT. It adds 3,177 tokens to every session, about $0.0159 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 2026-08-31.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.