What is designStack AGENTS.md?

Design rules for an AI coding assistant working on product interfaces. They require using concrete visual references, summarizing intended UI changes first, and following a project design bible when one exists.

Guiding UI and CSS changes, checking whether a design bible exists, and deciding when to ask for a reference or flag a mismatch before editing visuals.

They reduce unapproved visual guesswork and help keep colors, fonts, spacing, and components consistent with the project's documented design.

designStack AGENTS.md — Instructions file by harshii0509

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 instructions/harshii0509/designstack/agents-md

Clone the repo

git clone --depth 1 https://github.com/harshii0509/designStack

Made for: Codex, OpenCode.

Per session 365 This file is loaded in full into every session.

When invoked 365 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.

Model	Per session	Once invoked
Fable 5	$0.00365	$0.00365
Opus 5	$0.00182	$0.00182
Sonnet 5	$0.00073	$0.00073
Haiku 4.5	$0.00036	$0.00036

Measured 2d ago against content hash 1161f8e20dac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

designStack 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 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.

AGENTS.md · 33 lines

What it actually says

designStack — Design Rules for Codex CLI

This file is read automatically by Codex CLI. It applies the designStack four principles and your project's Design Bible to every AI-assisted code change.

Four principles (always apply these)

Think in references, not descriptions. If the user says "make it look better", ask for a reference or specific element — don't guess what "better" means.
Summarize before changing. Before editing any UI or CSS file, write one sentence saying what you're about to change and why. Wait for confirmation.
Read the Bible before touching visuals. If design/DESIGN-BIBLE.md exists in this project, read it before making any visual, layout, or style change. Apply its color, font, spacing, and component rules.
Flag drift, don't silently fix. If you notice a value (color, font size, spacing) that doesn't match the Design Bible, say so before changing it.

Design Bible

Fallback (no Design Bible)

If design/DESIGN-BIBLE.md does not exist in this project, tell the user:

"I don't see a Design Bible for this project. Run /ds-context in Claude Code to set one up — it takes 5 minutes and I'll follow your brand rules automatically after that."

Generated by designStack — the AI design companion for designers building their own products.

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.

2d ago First seen · 33 lines · 365 tokens per session scan A 1161f8e20dac

Subscribe to this mod's changes

designStack AGENTS.md is an instructions file published in the GitHub repository harshii0509/designStack (13 stars, last pushed 3mo ago), licensed MIT. It adds 365 tokens to every session, about $0.0018 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.

Frontend

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

designStack AGENTS.md