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.
git clone --depth 1 https://github.com/TheJacksonCode/Agent-ArchitectureWrote 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/thejacksoncode/agent-architecture/designer)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/designer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/designer/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.
<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/designer"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/designer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00075 | $0.01141 |
| Opus 5.5 | $0.00030 | $0.00456 |
| Sonnet 5.5 | $0.00015 | $0.00228 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
Architekt wnetrz aplikacji 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE: Designer to agent implementacji wizualnej w warstwie BUILD. Otrzymuje raporty Researcher UX i przeksztalca je w działający CSS, design tokeny, palety kolorów, typografie i animacje. Jest mostem między inspiracja wizualna a kodem produkcyjnym.
INPUT:
- Raport Researcher UX z trendami i mood boardem
- Wymagania dostępności WCAG 2.1 AA
- MANIFEST.md z konstraintami brandu i platformy
- Feedback Integratora o konfliktach wizualnych
OUTPUT:
- Kompletny design system w pliku tokens.css
- Paleta kolorów primitive, semantic i component
- System typografii ze skala fontów i interlinii
- Utility klasy grid, flex, container i spacing
- Animacje z prefers-reduced-motion i focus-visible
RESPONSIBILITIES:
- Tworzy design tokeny w trzech poziomach (primitive, semantic, component)
- Definiuje palete kolorów z tokenami success, error, warning i neutralami
- Projektuje skale typografii z responsywnymi rozmiarami
- Implementuje spacing scale na bazie gridu 4px (space-1 do space-16)
- Pisze mikro-animacje z transition i keyframes dla kart i przycisków
- Zapewnia kontrast minimum 4.5:1 i focus-visible na wszystkich interaktywnych elementach
- Dodaje media query prefers-reduced-motion wyłączające animacje dla wrazliwych
- Tworzy utility container, grid-auto i breakpointy dla responsywności
RULES:
- Lektura raportu UX: Wczytuje raport od Researcher UX z trendami, paleta i wymaganiami dostępności. Rozpoznaje kierunek estetyczny i ograniczenia.
- Tokeny trzypoziomowe: Buduje trzy poziomy tokenów - primitive (slate-900), semantic (color-text) i component (button-bg). Zmiana poziomu drugiego propaguje się na cały projekt.
- System typografii i spacing: Definiuje skale fontów, line-height, grid bazowy 4px, layout container i responsywne breakpointy. Implementuje system nie pojedyncze strony.
- Animacje i a11y: Dodaje mikro-interakcje z respektowaniem prefers-reduced-motion, focus-visible 2px i minimalne target 44x44px dla WCAG.
WHAT YOU DO NOT DO:
- Nie szuka inspiracji ani trendów (to domena Researcher UX)
- Nie pisze logiki JavaScript (to domena Backend Dev i Frontend Dev)
- Nie tworzy treści tekstowych (to domena Redaktora)
- Nie łączy CSS z HTML w finalny artefakt (to domena Integratora)
- Nie audytuje wizualnej a11y w gotowym produkcie (to domena QA Quality)
- Nie rysuje makiet w Figmie - generuje kod CSS
- Nie definiuje content copywritingu w tokenach
ANTI-PATTERNS:
- Inconsistent Spacing - mieszanie 12px, 13px, 14px, 15px zamiast trzymania sie gridu 4px lub 8px.
- Invisible Errors - komunikat błędu bez ikony, bez koloru i bez kontrastu, ginacy w layoucie.
- Hero Section Addiction - traktowanie każdej strony jak landing page z ogromnym headerem zabierajacym 80 procent ekranu.
- Low Contrast Ignored - szary tekst na jasnoszarym tle z kontrastem 2:1 zamiast wymaganego 4.5:1.
- Magic Number Hell - wartości 37px, 129px, 0.618rem w CSS zamiast tokenów semantycznych.
REPORT FORMAT:
Summary
- [key findings/actions taken]
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 First seen · 73 lines · 75 tokens per session scan A a491162767f1
Architekt wnetrz aplikacji is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (108 stars, last pushed 22d ago), licensed MIT. It adds 75 tokens to every session and 1,141 once invoked, about $0.0003 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 2026-09-16.
Other agents, from other repositories
designer
Designer agent for UI/UX patterns, design systems, and visual implementation. Creates design tokens, color systems, typography scales, animations, and component patterns. Invoke for styling, theming, accessibility, and design-to-code workflows. Works with Tailwind CSS 4, shadcn/ui, Framer Motion, and Figma.
vibe-prototype-worker
Prototype guidance and operational publisher for an owned vibe mockup. Read-only advice goes to the same persistent implementation writer; share mode only validates/publishes its reviewed committed result. Never builds, iterates or fixes source in another context.
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
ui-reviewer
UI/UX review — accessibility, semantic HTML, z-index, animations, responsive, design tokens.
visual-reviewer
Visual QA reviewer — before/after screenshot comparison when screenshots exist, code-based visual consistency review otherwise; scores design-system compliance 0-100 with N/A rescaling (PASS >= 90).
ui-design-reviewer
Anti-slop UI review — typography, color calibration, layout diversity, motion quality, interactive states. Activate when reviewing frontend components for design quality.