design

A project rule that tells an AI coding agent to read DESIGN.md before making changes. It also sets expectations for architecture updates, documentation, errors, logging, and tests.

In plain words
What is it for?
Guiding architectural changes, README updates, error handling, log content, and regression-test additions.
Why use it?
It keeps code changes aligned with the project's documented design and requires behavior changes and bug fixes to stay documented and tested.

Cursor rule for Cursor

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/stass/blew/design
Clone the repo
git clone --depth 1 https://github.com/stass/blew

Made for: Cursor.

Per session 186 This file is loaded in full into every session.
When invoked 186 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 $0.00186 $0.00186
Opus 5 $0.00093 $0.00093
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00019 $0.00019

Measured 2d ago against content hash 339a17dc341a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design 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 2d 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.

.cursor/rules/design.mdc · 19 lines

What it actually says

When this rule loads, input: "Rule loaded: design.mdc." The project architecture and design is described in DESIGN.md Please analyze @DESIGN.md before implementing changes and make your plans based on that.

When making architectural changes, make sure to update DESIGN.md as well so it reflects the changes made.

Don't hedge or add fallback values -- make a reasoned decision on what values should be available and use them, throw errors when unexpected things happend instead of adding fallbacks

Don't use emojis in documentation or logs.

Whenever we update user facing functionality or behvaior update README.md to reflect the changes.

For every new change make sure tests still pass. If we are fixing a bug -- add a new test to cover it.

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. 2d ago First seen · 19 lines · 186 tokens per session scan A 339a17dc341a

Subscribe to this mod's changes

design is a cursor rule published in the GitHub repository stass/blew (16 stars, last pushed 3mo ago), licensed BSD-2-Clause. It adds 186 tokens to every session, about $0.0009 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 2026-08-30.