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 skills add mattgierhart/PRD-driven-context-engineering --skill prd-v04-visual-prototype-gategit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/skills/mattgierhart/prd-driven-context-engineering/prd-v04-visual-prototype-gate)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v04-visual-prototype-gate"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v04-visual-prototype-gate/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/skills/mattgierhart/prd-driven-context-engineering/prd-v04-visual-prototype-gate"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v04-visual-prototype-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00142 | $0.01519 |
| Opus 5.5 | $0.00057 | $0.00608 |
| Sonnet 5.5 | $0.00028 | $0.00304 |
| Haiku 4.5 | $0.00014 | $0.00152 |
Grade A, and why
prd-v04-visual-prototype-gate 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Prototype Gate
Position in workflow: v0.4 Screen Flow Definition → v0.4 Visual Prototype Gate → v0.5 Red Team Review
Screens on paper are hypotheses. Screens rendered visually are testable. This skill converts SCR- entries into structured prompts for Google Stitch (or any UI generation tool), then captures feedback routed back to specific SoT IDs.
Rule: No product advances past v0.4 without a visual prototype reviewed by at least one stakeholder.
Consumes
- SCR-* entries (from Screen Flow Definition) — Each SCR- becomes one Stitch prompt. 1:1 mapping, no exceptions.
- PER-* entries (from Persona Definition) — User context shapes copy, complexity, and emotional framing per screen.
- UJ-* entries (from User Journey Mapping) — Journey position determines each screen's emotional beat (uncertainty → clarity → confidence).
- DES-* entries (from Screen Flow Definition) — Shared components referenced in prompts for visual consistency.
- BR-* business rules — Constraints affecting visual layout (pricing tiers, role-based visibility, data rules).
Produces
- Stitch Prompt Block per SCR- — One structured prompt per screen, ready to paste into Stitch. Grouped by UJ- journey for context.
- Prototype Context Brief — Product context + design style preamble (pasted once into Stitch before screen prompts).
- Feedback Capture Template — Table mapping each prototype screen to its SCR- ID for structured review. See
assets/feedback-capture-template.md. - No new SoT IDs — This skill visualizes existing IDs. Feedback routes back to SCR-, DES-, or CFD- entries.
Step-by-Step Process
Step 1: Confirm Inputs Exist
Check that Screen Flow Definition is complete:
- At least 3 SCR- entries exist with Purpose, Key Elements, and Related IDs populated
- At least 1 UJ- journey references those screens
- Design style preference confirmed with user (or default: "Clean B2B SaaS, minimal, professional")
If SCR- entries are incomplete, stop and run prd-v04-screen-flow-definition first.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 132 lines · 142 tokens per session scan A c740e755521c
prd-v04-visual-prototype-gate is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (181 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 1,519 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
loft
Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks.…
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.
moai-design-craft
Intent-First design craft specialist covering design direction, domain vocabulary, design memory, and post-build critique. Use when establishing design intent or auditing code against design principles.
mulmoterminal-theme
Build a colour scheme of your own for MulmoTerminal — one that joins Midnight, Nord, Daylight and Solarized in Settings' theme picker and can then be pinned per project. Writes themes in /.mulmoterminal/config.json, the whole-app palette (panels, borders, accent, text). Settings → Theme can copy an existing theme and…