harvey-design-system-mcp: Instructions file for Codex

AGENTS.md

harvey-design-system-mcp AGENTS.md is an instructions file for Codex, OpenCode from thenpceo/harvey-design-system-mcp. It costs 1,196 tokens per session, scanned A, original, MIT.

Instructions for working with the Harvey design system MCP and its presentation website. A design system is a shared set of visual rules and components used to keep interfaces consistent.

In plain words
What is it for?
It is for running and previewing the local prototype, using Harvey’s fonts and design guidance, and keeping the demo presentation-only.
Why use it?
It helps keep prototypes aligned with Harvey’s approved layout, typography, branding, and presentation constraints.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is thenpceo/harvey-design-system-mcp's own configuration. It tells Codex and OpenCode how to work on harvey-design-system-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything harvey-design-system-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thenpceo/harvey-design-system-mcp. 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/thenpceo/harvey-design-system-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/thenpceo/harvey-design-system-mcp

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.

agentmods badge for harvey-design-system-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thenpceo/harvey-design-system-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/thenpceo/harvey-design-system-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/thenpceo/harvey-design-system-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thenpceo/harvey-design-system-mcp/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.

agentmods 80×15 button for harvey-design-system-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thenpceo/harvey-design-system-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thenpceo/harvey-design-system-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,196 This file is loaded in full into every session.
When invoked 1,196 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01196 $0.01196
Opus 5 $0.00598 $0.00598
Sonnet 5 $0.00239 $0.00239
Haiku 4.5 $0.00120 $0.00120

Measured 8d ago against content hash 3b4f419805fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

harvey-design-system-mcp 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 8d 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 · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prototype Instructions

Run the local server yourself and open the preview in the browser available to this environment. Do not give the user server-start instructions when you can run it.

Before making substantial visual changes, use the Product Design plugin's get-context skill when the visual source is unclear or no longer matches the current goal. When the user gives durable prototype-specific design feedback, preferences, or decisions, record them in AGENTS.md.

When implementing from a selected generated mock, treat that image as the source of truth for layout, component anatomy, density, spacing, color, typography, visible content, and hierarchy.

Use Harvey's actual HarveySerifFont for display and header typography. Do not substitute Instrument Serif. Keep the proprietary font unbundled unless redistribution rights are established; the prototype may load the official WOFF2 from Harvey's public asset endpoint and must retain a documented failure fallback.

Keep the website presentation-only. It explains the design system and MCP for a human demo, but it must not hold API keys, submit model jobs, or render media. The installed Harvey MCP supplies brand-governed plans and audits; your AI agent of choice orchestrates built-in GPT Image, the separate fal MCP, and HyperFrames. Public-facing copy must say “your AI agent of choice” rather than naming Codex as the required host.

On first use and for every image, motion, or video production request, the Harvey MCP should recommend the companion setup without blocking plan-only work: create a fal.ai API key at https://fal.ai/dashboard/keys, connect https://mcp.fal.ai/mcp with the key stored only in the agent's secret configuration, and install the HeyGen HyperFrames skills with npx skills add heygen-com/hyperframes before invoking /hyperframes. Never collect or echo a real fal key.

Harvey image and film direction has two canonical modes. warm-prismatic-people uses credible professionals in candid work, warm amber practicals, a cool window edge, rich detailed blacks, foreground glass, gentle optical bloom, and restrained translucent edge echoes. architectural-oblique uses sharp upward or downward views of modern glass-and-steel structures, graphic diagonals, stable facade grids, cool glass, and small warm reflections. Never regress to generic enterprise stock, empty glossy offices, direct-to-camera sales posing, cold flat lighting, or arbitrary legal clichés.

Harvey's current production geometry uses two small, deliberate radii: 4px on buttons, inputs, selects, and compact controls; 8px on large media, editorial cards, and selected feature panels. Keep structural grid seams and full-bleed section boundaries square, and reserve pills/circles for media and carousel controls. The observed current warm-paper surface is #F2F1F0, with 32px desktop and 28px compact page gutters.

Motion examples must show an end product, not only abstract timing diagrams. The canonical partnership announcement is exactly 10 seconds over one uninterrupted architectural-oblique plate. Default to a full-frame Harvey Ink legibility overlay and Ivory identity/copy; do not place the lockup or goal on a floating white card or rectangle. Keep the lockup inside the center 50% of frame and optically center the visible artwork rather than centering unequal source canvases: a 3px angled divider stays fixed while Harvey is unmasked sliding left from center and the authorized partner identity is unmasked sliding right. Both identities stay at full opacity for the entire entrance and begin completely outside their divider-side overflow masks, so the artwork appears through a hard mask edge with no logo dissolve. In the visible web demo, render both identities approximately 50% larger than the initial implementation and keep the divider, optical lockup center, and frame on the same horizontal axis. At 3.6 seconds, crossfade overlays only and reveal the goal statement word by word at a 70–110ms stagger; center-align the eyebrow and goal by default in a field no wider than roughly 50% of frame, unless an intentionally approved alternate layout is selected. Leave a clean architectural tail from 9.4–10.0 seconds. Use cubic-bezier(0.22, 1, 0.36, 1) / power3.out, stable type, and long reading holds. All logos, partner identity, claims, captions, and actions stay separate from generated footage; unsourced or unauthorized partnership work is visibly concept-only and cannot be published.

Read the full file on GitHub · 28 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.

  1. 8d ago First seen · 28 lines · 1,196 tokens per session scan A 3b4f419805fe

Subscribe to this mod's changes

harvey-design-system-mcp AGENTS.md is an instructions file published in the GitHub repository thenpceo/harvey-design-system-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,196 tokens to every session, about $0.0060 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 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 · 5,153 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

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens