design-vanguard

design-vanguard is an agent for Claude Code from nxtg-ai/forge-plugin. It costs 445 tokens per session (10,311 once invoked), scanned A, original, MIT.

An agent for designing and reviewing user interfaces and reusable design systems. It organizes visual decisions through design tokens—named values for things like color, spacing, and typography—so changes can be made consistently.

In plain words
What is it for?
Designing interface components, auditing screens, defining design-system tokens, and building consistent visual rules across an application.
Why use it?
It helps avoid scattered one-off styling choices and makes broader changes, such as dark mode or accessibility adjustments, easier to manage. It also considers components, accessibility, motion, typography, and color.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the nxtg-forge plugin — 27 skills, 24 commands, 33 agents shipped together

Good fit Designing interface components, auditing screens, defining design-system tokens, and building consistent visual rules across an application.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/nxtg-ai/forge-plugin/design-vanguard
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.

Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin

Made for: Claude Code.

Or install nxtg-forge, the plugin that ships this one along with the rest of its 27 skills, 24 commands, 33 agents.

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 design-vanguard

README.md
[![agentmods](https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/design-vanguard/github.svg)](https://agentmods.dev/agents/nxtg-ai/forge-plugin/design-vanguard)
Your own site
<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/design-vanguard"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/design-vanguard/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 design-vanguard

Your own site · 80×15
<a href="https://agentmods.dev/agents/nxtg-ai/forge-plugin/design-vanguard"><img src="https://agentmods.dev/badge/agents/nxtg-ai/forge-plugin/design-vanguard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 445 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,311 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00445 $0.10311
Opus 5.5 $0.00178 $0.04124
Sonnet 5.5 $0.00089 $0.02062
Haiku 4.5 $0.00044 $0.01031

Measured 1mo ago against content hash 7f2341270dfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-vanguard 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.

plugins/nxtg-forge/agents/design-vanguard.md · 1,033 lines

How it starts

The opening of the file, as written. The whole thing — 1,033 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge Design Vanguard

You are the Design Vanguard — the opinionated, exacting design partner for NXTG-Forge. You do not decorate. You architect experiences. You are the reason users trust this product on sight and developers want to build with its components.

You replace the need for a human designer in 90% of decisions by bringing deep knowledge of design systems, accessibility, motion, typography, color theory, information architecture, and developer experience. When you are uncertain, you say so and present options with trade-offs — but you are rarely uncertain.

Orchestrator MCP Integration

When working on design tasks managed by forge-orchestrator:

  • forge_get_tasks — Check your assigned tasks and their requirements
  • forge_get_plan — Read the master plan for design context
  • forge_get_knowledge — Look up past design decisions, component patterns, audit findings
  • forge_capture_knowledge — Record design decisions, token definitions, audit results (category: "learnings")
  • forge_complete_task — Mark your task done with a summary of what was designed/built

If orchestrator tools are not available, proceed with local context only.


I. Design Philosophy

You stand on the shoulders of these traditions. Know them cold.

Dieter Rams — 10 Principles of Good Design

  1. Innovative — Exploit new possibilities, never for novelty alone
  2. Useful — Satisfy functional, psychological, and aesthetic criteria
  3. Aesthetic — Only well-executed objects can be beautiful
  4. Understandable — The structure clarifies the product; self-explanatory at best
  5. Unobtrusive — Neither decoration nor art — it serves a purpose
  6. Honest — Does not manipulate or promise what it cannot deliver
  7. Long-lasting — Avoid fashion; never appear antiquated
  8. Thorough — Nothing is arbitrary; care shows respect for the user
  9. Environmentally friendly — Conserve resources; minimize visual and physical pollution
  10. As little design as possible — Back to purity, back to simplicity

Read the full file on GitHub · 1,033 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. 1mo ago Changed · +905 lines · +445 tokens per session 7f2341270dfb
  2. 1mo ago First seen · 128 lines · 0 tokens per session scan A fbc913a23084

Subscribe to this mod's changes

design-vanguard is an agent published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 445 tokens to every session and 10,311 once invoked, about $0.0018 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.

Related

Other agents, from other repositories

gauntlet-critic

DAE gauntlet critic. Grades one candidate against a concrete reference (the bar) and returns a single falsifiable gap, or ties-or-wins. Never edits. Dispatched each round of the gauntlet loop at CP5 by atdd:atdd-team (references/gauntlet.md).

swingerman/engineer · 69 tokens

ux-reviewer

Master UX and accessibility engineer — Kodelyth. A decade-seasoned product engineer who has shipped interfaces used by hundreds of millions of people at $300B-scale companies. Reviews frontend code with the eye of a UX architect — not by rules, but by deeply understanding how humans think and feel when they use…

sifxprime/kodelyth-ecc · 93 tokens

image-architect

AI image generation specialist. Generates hero sections, OG images, social cards, thumbnails, and UI mockups. Platform-aware — uses native image generation on Antigravity (Gemini Imagen 3) and Codex (DALL-E 3), fal.ai MCP on Claude Code and Windsurf, and falls back to production-quality SVG on any platform with no API…

sifxprime/kodelyth-ecc · 95 tokens

ui-designer

Design user interface and experience.

nth5693/gemini-kit · 10 tokens

steve-jobs-advisor

Use this agent when you need visionary product leadership, strategic business guidance, or inspiration to think differently about innovation and design. Perfect for product decisions, company culture questions, creative challenges, or when you need someone to push you beyond conventional thinking. Examples: Context…

eddiebelaval/squire · 0 tokens

ux-reviewer

UX friction code reviewer — read-only, spawned by /aiagentminder:self-review.

lwalden/AIAgentMinder · 21 tokens