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 yschimke/skills --skill design-parity-reviewgit clone --depth 1 https://github.com/yschimke/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/yschimke/skills/design-parity-review)<a href="https://agentmods.dev/skills/yschimke/skills/design-parity-review"><img src="https://agentmods.dev/badge/skills/yschimke/skills/design-parity-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/yschimke/skills/design-parity-review"><img src="https://agentmods.dev/badge/skills/yschimke/skills/design-parity-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 | $0.00133 | $0.02584 |
| Opus 5 | $0.00067 | $0.01292 |
| Sonnet 5 | $0.00027 | $0.00517 |
| Haiku 4.5 | $0.00013 | $0.00258 |
Grade A, and why
design-parity-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 11d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design parity — reviewing code against its design
design-parity is a tool-neutral bot that proves a UI pull request is at
parity with its intended design. On a UI PR it:
- resolves which design reference matches the changed component,
- renders the new code — the candidate — via
compose-preview, - diffs candidate vs reference (visual + semantic + token),
- posts a verdict in the PR — e.g. "implements Figma
Button/Primary; padding 12dp vs spec 16dp; dark-theme contrast fails AA."
The candidate side is the upstream compose-preview renderer (the
compose-preview skill). What design-parity
owns is the reference side and the correspondence layer that decides
which design maps to which code.
Source
Maintained at github.com/yschimke/skills
under skills/design-parity-review/. The tool ships from
yschimke/design-parity and on npm
as design-parity — run it with
npx design-parity …, no checkout needed. That repo's
docs/README.md
indexes the full contracts; when it disagrees with this skill, it wins.
Which direction is this?
The two directions are different tools and it is worth being explicit, because picking the wrong one wastes a lot of setup:
| You want | Direction | Skill |
|---|---|---|
| "Does this PR's code match the Figma design?" | design → code | this skill |
| "Publish our component system into Figma as a sticker sheet" | code → design | compose-design-catalog → figma-catalog-import |
| "Is the rendered UI different from last commit?" | neither — no design involved | compose-preview-review |
Round-tripping — running both directions on one project — is supported and covered in references/round-trip.md. Read the direction policy section below first: which side is canonical is a committed decision, not a per-run choice.
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.
- 11d ago First seen · 206 lines · 133 tokens per session scan A 9c27bfc3cfb6
design-parity-review is a skill published in the GitHub repository yschimke/skills (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 133 tokens to every session and 2,584 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…
ideagram
Turn a concept, feature description, blog post, or pitch into a single beautiful, on-brand illustration by matching it to a real unDraw illustration in a local library and recoloring it to the brand accent — genuine illustrator quality, not an AI-drawn approximation. Use whenever the user asks to "make an…
design-standards
Apply production-grade design standards when building or reviewing pages, components, or UI. Use this skill whenever the user asks to build a page, design a component, lay out a section, review the UI, fix the layout, or check design quality. Triggers on build a page, create a component, design a section, hero, card…
image-to-psd
A skill that reconstructs images as editable, layered Photoshop files. It separates the repaired background, visual components, and text into layers instead of leaving the page as one flat image.
review-arch
Conduct a principal-level architecture review of a system, specification, diagram, or set of design decisions. Use when asked to review an architecture, evaluate a design, assess coupling/cohesion, check for anti-patterns, audit system boundaries, or produce an Architecture Review Board (ARB) style verdict. Also use…
review-impl
Review implementation changes for a given task against architectural standards. Use when reviewing a PR, evaluating recently committed code, assessing whether implementation changes are correct and architecturally sound, or when asked to 'review my changes', 'check this implementation', 'review what I built', 'is this…