What is agentic-design-system AGENTS.md?

Repository instructions for an AI-focused design system, a collection of reusable rules and patterns for designing user interfaces.

Use them when designing or reviewing interfaces, checking loading, empty, and error states, calibrating against visual references, or polishing a public product or site.

They direct design and review work to the appropriate workflow and set expectations for visual quality, usability states, and verification.

How aa-on-ai/agentic-design-system configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to aa-on-ai/agentic-design-system. 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/aa-on-ai/agentic-design-system/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/aa-on-ai/agentic-design-system

Made for: Codex, OpenCode.

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/aa-on-ai/agentic-design-system/agents-md/github.svg)](https://agentmods.dev/instructions/aa-on-ai/agentic-design-system/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/aa-on-ai/agentic-design-system/agents-md"><img src="https://agentmods.dev/badge/instructions/aa-on-ai/agentic-design-system/agents-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/aa-on-ai/agentic-design-system/agents-md"><img src="https://agentmods.dev/badge/instructions/aa-on-ai/agentic-design-system/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 472 This file is loaded in full into every session.

When invoked 472 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	$0.00472	$0.00472
Opus 5.5	$0.00189	$0.00189
Sonnet 5.5	$0.00094	$0.00094
Haiku 4.5	$0.00047	$0.00047

Measured 1mo ago against content hash b5d8dbf75054, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentic-design-system 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 1mo 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Design System agent instructions

Start here

For visual or frontend work, read skills/agentic-design-system/SKILL.md. It is the only execution entrypoint. Follow its scoped loop:

understand → choose → work → prove → decide

For a substantial design build or review handoff, the orchestrator uses skills/ember/SKILL.md by default to read the evidence already collected and present Ember's review. Ember does not create a second execution loop, independent reviewer, or new permission to edit.

Do not start with routing/ROUTING.md. The orchestrator links it only for maintainer work or a matching specialist route.

Repository boundary

Read contracts/visual-foundation.v2.json through the orchestrator and select the applicable profile before substantial generation or review.
Load project context from DESIGN.md, project files, and named references. Preserve the existing product and chosen direction unless the task authorizes a change.
Review-only requests stay read-only. An authorized local build or fix does not need duplicate permission, but external writes, deployment, installation, spending, and destructive actions retain their own authority.
Workbench implementation is separate from the default installed skill workflow.

Verification

Source checks are advisory. Rendered evidence supports the verdict:

python3 skills/design-review/scripts/anti-pattern-check.py <your-file.tsx>
python3 skills/design-review/scripts/state-check.py <your-file.tsx>
python3 skills/design-review/scripts/accessibility-check.py <your-file.tsx>
node skills/design-review/scripts/capture.mjs "<running-route-url>" \
  --states default,loading,empty,error --out evidence/<slug>

Choose task-relevant states and breakpoints. Block a ready verdict on confirmed Foundation v2 never rules or failed required accessibility, layout, semantic, interaction, or modal evidence.

Specialist suite

Read the full file on GitHub · 49 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.

1mo ago Changed · -22 lines · -269 tokens per session b5d8dbf75054
2mo ago First seen · 71 lines · 741 tokens per session scan A 0767672625d9

Subscribe to this mod's changes

agentic-design-system AGENTS.md is an instructions file published in the GitHub repository aa-on-ai/agentic-design-system (6 stars, last pushed 10d ago), licensed MIT. It adds 472 tokens to every session, about $0.0019 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.

Design and UX

agentic-design-system AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentic-design-system AGENTS.mdaa-on-ai/agentic-design-system	Instructions file	6	10d ago	MIT	A	472	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agentic-design-system: Instructions file for Codex