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 yorrick/agent-skills --skill visual-design-reviewgit clone --depth 1 https://github.com/yorrick/agent-skillsWrote 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/yorrick/agent-skills/visual-design-review)<a href="https://agentmods.dev/skills/yorrick/agent-skills/visual-design-review"><img src="https://agentmods.dev/badge/skills/yorrick/agent-skills/visual-design-review/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/yorrick/agent-skills/visual-design-review"><img src="https://agentmods.dev/badge/skills/yorrick/agent-skills/visual-design-review.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 | $0.00053 | $0.01448 |
| Opus 5.5 | $0.00021 | $0.00579 |
| Sonnet 5.5 | $0.00011 | $0.00290 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
visual-design-review 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual design review
Help an experienced reader see the whole design, challenge its assumptions, and steer the choices that matter. The review interface is concise and visual; the specification remains the implementation reference.
This skill organizes the review. It does not supply a rendering framework, replace the planning workflow, or authorize implementing the system being discussed.
Establish what needs a decision
- Read the relevant existing spec, evidence, and conversation. Identify the objective, constraints, current versus proposed behavior, and decisions already made. Preserve accepted choices. Flag new evidence that challenges them without changing their status; ask the user to revisit a choice when its consequences require a changed decision.
- Distinguish verified facts, estimates, assumptions, and unresolved questions. Attach source references to claims and decisions so the reader can inspect the evidence on demand.
- Treat behavior the source does not mention as unknown, not as absent or forbidden. Describe a proposed mechanism's intended benefit without promising a guarantee that has not been established, especially across crashes, retries, or concurrent work.
- Surface choices with meaningful consequences for behavior, system boundaries, cost, security, operations, or reversibility. Use judgment about consequence; do not turn every implementation detail into a checkpoint.
- Give each decision a stable identifier, such as D1, that survives view and document changes. Define the actual question and its affected components before choosing a visual.
- If no consequential choice is open, say so and show only the requested explanation or compact recap. Do not manufacture alternatives or ask for another approval.
Compose with available capabilities
- Discover the skills and rendering tools available in the current environment before selecting the delivery surface. Respect the user's requested format.
- For a process flowchart or interactive process walkthrough, load the shared
flowchartskill when available. Let it own process layout and keyboard guidance instead of copying those rules here. - For an inline surface owned by an available visualization skill, load that skill and follow its rendering contract. Codex's bundled
visualizeskill is one such capability; do not assume it or its host APIs exist in Claude Code. - A standalone browser document or a supported Mermaid diagram can be selected up front when that matches the request and available capabilities. Neither requires a Codex-specific host. Missing explicitly requested skills or unsupported chosen formats must be reported; do not silently substitute, auto-install dependencies, or switch delivery surfaces after a failure.
- Choose the representation that answers the question. Do not require every review to contain every diagram type:
- Architecture diagrams: boundaries, responsibilities, trust, and what changes.
- Flowcharts: decisions, process order, and reachable outcomes.
- Sequence diagrams: who communicates with whom, timing, and failure handling.
- State diagrams: lifecycle changes and valid transitions.
- Tables: a few alternatives and qualitative tradeoffs.
- Quantitative charts: measured or explicitly estimated cost, latency, capacity, or other quantities. Show units, sources, and assumptions; do not fabricate precision or turn qualitative judgments into arbitrary scores.
- Mockups: user-visible behavior or interaction choices.
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 · 62 lines · 53 tokens per session scan A 9201922b92fd
visual-design-review is a skill published in the GitHub repository yorrick/agent-skills (11 stars, last pushed 11d ago), licensed MIT. It adds 53 tokens to every session and 1,448 once invoked, about $0.0002 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.