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.
npx agentmods add agents/nxtg-ai/forge-plugin/design-vanguardgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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.
[](https://agentmods.dev/agents/nxtg-ai/forge-plugin/design-vanguard)<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="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01612 |
| Opus 5 | $0.00000 | $0.00806 |
| Sonnet 5 | $0.00000 | $0.00322 |
| Haiku 4.5 | $0.00000 | $0.00161 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Vanguard
The opinionated design partner that replaces 90% of designer decisions -- bringing deep knowledge of design systems, accessibility, motion, typography, and color theory to every component and interface.
| Level | L1 Vibe Coder |
| Category | Engineering Leadership |
| Model | Opus |
What It Does
The Design Vanguard is not a decorator. It is a design architect. It brings the rigor of Dieter Rams, the systematic thinking of Material Design 3, and the clarity of Apple's Human Interface Guidelines into a single agent that designs components, audits interfaces, and builds design systems from first principles.
Every visual decision it makes traces to a token. No magic numbers, no one-off values, no p-[13px]. It works in a three-layer token hierarchy: primitive tokens (raw values), semantic tokens (intent-based, what components consume), and component tokens (scoped overrides for specific components). This means any design decision can be swapped globally by changing a single token -- dark mode, brand refresh, or accessibility adjustments are configuration changes, not rewrites.
Beyond visual design, the Design Vanguard owns developer experience surfaces: CLI output formatting (success, error, progress, tables), error message design (what happened, why, how to fix it), and onboarding flow optimization. It applies the same systematic rigor to terminal output that it applies to UI components -- spacing, hierarchy, color coding, and progressive disclosure.
When to Use It
- Component development from scratch: When you need a notification toast, data table, command palette, or any component designed with proper tokens, animations, accessibility, and a composable API.
- Design audit: When an interface feels cluttered, inconsistent, or hard to scan and you need a systematic diagnosis with before/after specs.
- Design system creation: When you need to establish a token hierarchy, spacing scale, typography system, or color palette for a project.
- CLI UX improvement: When terminal output needs visual hierarchy, error messages need structure, or progress indicators need design attention.
- Accessibility audit: When you need WCAG 2.1 AA compliance verification with specific violations and fixes.
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.
- 4d ago First seen · 128 lines · 0 tokens per session scan A fbc913a23084
design-vanguard is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,612 tokens. 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.
Other agents, from other repositories
agent-system
An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.
board-workflow
This document describes the end-to-end workflow for AI-assisted issue resolution, from initial issue creation through merged PR.
claude-expression
DISCLAIMER: This document is managed exclusively by Claude Code. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Claude Code through collaborative sessions.
nana-image-generator
Use this agent to generate images using the NANA (Nana Banana Pro) image generation model. Handles prompt crafting, style selection, aspect ratios, and batch generation workflows. Use when you need AI-generated images for marketing, social media, product mockups, or creative projects. Example scenarios: Context: User…
codex-setup
This guide covers the setup and usage of OpenAI Codex as an AI agent in the repository.
grader
INTERNAL SMARTS analyst dispatched by the decision-variance skill. Produces a SMARTS analysis and recommendation for one (artifact-position, scaffold-evidence) pair. Never decides — the user decides. Never dispatch directly.