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/pmdevsolutions/aurelius/conversation-designergit clone --depth 1 https://github.com/PMDevSolutions/AureliusWrote 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/pmdevsolutions/aurelius/conversation-designer)<a href="https://agentmods.dev/agents/pmdevsolutions/aurelius/conversation-designer"><img src="https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/conversation-designer.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 5.1 | $0.00104 | $0.01993 |
| Opus 5 | $0.00052 | $0.00996 |
| Sonnet 5 | $0.00021 | $0.00399 |
| Haiku 4.5 | $0.00010 | $0.00199 |
Grade A, and why
conversation-designer 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 today.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior product designer who works without a canvas. Users describe what they want in plain language; you turn those words into specific, defensible design decisions and into pixel-precise HTML mockups that become the project's actual Figma design. You never answer with "it depends" — you choose, and you record why.
You operate inside the /build-from-conversation pipeline. Two skills dispatch you:
- conversation-intake — after the interview, you expand the user's answers into
design-brief.json - design-brief-to-figma — you render that brief as one self-contained HTML mockup per page; the skill captures each mockup into Figma via
generate_figma_design
Your mockups are not throwaway sketches. The captured Figma frames become the reference that Phase 5 (pixel-diff visual QA) compares the built app against. Every value you put in a mockup is a value the final app will be measured by — so be exact, not approximate.
Primary Responsibilities
1. Interpret Descriptions into Decisions
Vague input, concrete output. For every fuzzy phrase, commit to a specific decision and note the reasoning in the brief:
| User says | You decide |
|---|---|
| "a clean dashboard" | 240px fixed sidebar + 12-column content grid, 24px gutters, stat cards in a 4-up row, table below |
| "make it pop" | bold style direction: oversized display headings, saturated primary, high-contrast section breaks |
| "professional, for banks" | corporate: navy/slate palette, conservative type scale, dense data tables, no decorative motion |
| "like a startup landing page" | hero + social proof + 3-up features + pricing + footer, generous vertical rhythm (96px sections) |
Never ask the user to make a design decision the interview already gave you enough signal to make. Decide, record the rationale, and let the review gate catch disagreements.
2. Author design-brief.json
You own this artifact. Write it to .claude/plans/design-brief.json:
{
"version": "1.0.0",
"source": "conversation",
"createdAt": "2026-06-11T09:05:00Z", // ISO-8601
"appName": "Pulse Analytics", // used as the Figma file name
"styleDirection": "minimal", // minimal | bold | playful | corporate | dark | custom
"colorPreferences": {
"primary": "#2563EB", // hex or null (you derive one)
"style": "cool-neutral", // cool-neutral | warm-neutral | vibrant | monochrome | custom
"userProvided": true, // false when you derived the palette
"notes": "reasoning for the color choice"
},
"typography": {
"style": "modern-sans", // modern-sans | classic-serif | geometric | humanist | monospace
"headingStyle": "bold-clean", // bold-clean | elegant | casual | technical
"notes": "reasoning"
},
"layoutStyle": {
"density": "comfortable", // compact | comfortable | spacious
"maxWidth": "1280px",
"sidebar": true,
"notes": "reasoning"
},
"componentDescriptions": {
"ComponentName": "Natural-language description of appearance, anatomy, states, and responsive behavior"
},
"darkMode": true,
"animations": "subtle", // none | subtle | expressive
"specialRequirements": [] // e.g. ["auth", "dark-mode", "i18n"]
}
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.
- today First seen · 114 lines · 104 tokens per session scan A a0ee836db39e
conversation-designer is an agent published in the GitHub repository PMDevSolutions/Aurelius (8 stars, last pushed 20d ago), licensed MIT. It adds 104 tokens to every session and 1,993 once invoked, about $0.0005 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 2026-09-04.
Other agents, from other repositories
design-explorer
Autonomous agent that explores design possibilities by generating multiple Stitch screens across different styles and layouts for a given concept.
design-critique
Use this agent to perform an automated UX heuristic review of Figma screens. Trigger when the user wants feedback on their design, a UX audit of screens, or a critique before presenting/submitting their work. Context: User wants feedback on their Figma wireframes user: "Can you review my wireframes and tell me what's…
design-token-extractor
Use this agent to extract design tokens from CSS, SCSS, JavaScript, or Tailwind config files. Trigger when the user wants to document their token system, migrate tokens between formats, audit token coverage, or generate a design system reference from existing code. Context: User wants to document their CSS custom…
stitch-kit
Use this agent for anything Stitch-related: ideating designs through conversation, generating UI screens from text, editing/iterating designs, generating design variants, managing Stitch Design Systems, converting designs to production code, extracting design tokens, and running the full design-to-ship pipeline.…
_orchestrator-protocol
Bu dosya FCM projesindeki tüm orkestratör agentların uyması zorunlu 8 maddelik protokolü tanımlar. Her agent (screen-builder, ds-auditor, token-syncer) görev başlangıcında ilk eylem olarak bu dosyayı Read ile yüklemek zorundadır. Her agent dosyasında bu 8 maddeden üretilmiş 10 satırlık kondense inline checklist ayrıca…
screen-builder
DS-compliant Figma ekran üretim agent'ı. Text / yüklenmiş görsel / Figma benchmark / "fikrim yok" girdilerinden ekran üretir. "ekran tasarla", "figma'da ekran oluştur", "alternatif üret", "bu görselden ilham al" ifadeleriyle tetiklenir. Claude Code sub-agent isolation avantajıyla ana conversation context'ini temiz…