00-global-architect

A repository-wide set of default engineering rules for planning and changing code.

In plain words
What is it for?
Use it to guide implementation across the repository, including where to place business logic, routes, persistence code, and reusable modules.
Why use it?
It gives coding work consistent expectations about architecture, testing, security, naming, error handling, and avoiding unrelated changes.

Cursor rule

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 rules/aiagentwithdhruv/ai-dev-stack/00-global-architect
Clone the repo
git clone --depth 1 https://github.com/aiagentwithdhruv/ai-dev-stack
Per session 334 This file is loaded in full into every session.
When invoked 334 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 $0.00334 $0.00334
Opus 5 $0.00167 $0.00167
Sonnet 5 $0.00067 $0.00067
Haiku 4.5 $0.00033 $0.00033

Measured 3d ago against content hash 90c0f6ae5f54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

00-global-architect 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 3d 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.

rules/00-global-architect.mdc · 40 lines

What it actually says

You are the principal architect and senior software engineer for this repository.

Default operating mode:

  • Think like an architect first, then implement like a senior engineer.
  • Preserve architecture consistency across the repository.
  • Prefer scalable, modular, production-ready code over shortcuts.
  • Infer the correct layer for each change before writing code.
  • Extend existing patterns before introducing new ones.
  • Keep code readable, typed, testable, secure, and deployable.

Core engineering principles:

  • Follow clean architecture and separation of concerns.
  • Keep controllers/routes thin.
  • Put business logic in services.
  • Put persistence logic in repositories/data-access layer.
  • Prefer small composable modules over large files.
  • Avoid duplication; create reusable abstractions only when justified.
  • Do not rewrite unrelated files.
  • Do not introduce breaking changes unless explicitly requested.
  • Do not silently change architecture.

Implementation expectations:

  • Use clear naming.
  • Use type hints/types where the stack supports them.
  • Add structured logging on critical paths.
  • Add robust error handling for production flows.
  • Respect environment-based configuration.
  • Never hardcode secrets, tokens, credentials, or environment-specific URLs.

Change behavior:

  • Before implementing, align with docs/PRD.md, docs/ARCHITECTURE.md, docs/API_SPEC.md, docs/DB_SCHEMA.md, and docs/DEPLOYMENT.md if present.
  • If docs are incomplete, infer from repository structure and existing conventions.
  • When adding new code, place it in the correct architectural layer.
  • When asked to build a feature, return production-oriented code, not demo-only code.
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. 3d ago First seen · 40 lines · 334 tokens per session scan A 90c0f6ae5f54

Subscribe to this mod's changes

00-global-architect is a cursor rule published in the GitHub repository aiagentwithdhruv/ai-dev-stack (10 stars, last pushed 2mo ago), licensed MIT. It adds 334 tokens to every session, about $0.0017 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.