Borrowing it
Nothing to install: this file belongs to theimaginaryfoundation/what-iff. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/theimaginaryfoundation/what-iff/main/.agents/skills/design-review/SKILL.mdgit clone --depth 1 https://github.com/theimaginaryfoundation/what-iffWrote 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/theimaginaryfoundation/what-iff/design-review)<a href="https://agentmods.dev/skills/theimaginaryfoundation/what-iff/design-review"><img src="https://agentmods.dev/badge/skills/theimaginaryfoundation/what-iff/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/theimaginaryfoundation/what-iff/design-review"><img src="https://agentmods.dev/badge/skills/theimaginaryfoundation/what-iff/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 | $0.00162 | $0.01653 |
| Opus 5.5 | $0.00065 | $0.00661 |
| Sonnet 5.5 | $0.00032 | $0.00331 |
| Haiku 4.5 | $0.00016 | $0.00165 |
Grade A, and why
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design review
Turns a branch into a picture of itself. The audience is whoever has to answer "does this look right?" — usually the person who designed it, who should not have to read a unified diff of a Tailwind class list to find out.
The one thing to understand first
A passing visual suite proves nothing about an intentional design change.
When a designer changes a screen they also regenerate its baseline and commit
it, so by review time toHaveScreenshot() compares the new render against
the new baseline and passes. The Playwright report is green and empty. The
change is invisible because it was done correctly.
So this report does not read a test run. It reads git: the before is the baseline committed at the merge base, the after is the baseline on this branch. That is why it needs no backend, no browser and no Docker, and why it finishes in about a second.
The visual suite still matters — it is what catches the unintended change, where the code moved and the baseline did not. That is a different question with its own command; see "When to also run the suite" below.
The design-review label
For a PR, the usual answer is not to run anything: add the design-review
label. .github/workflows/design-review.yml builds the report, uploads it as
the design-review artifact, and posts a sticky comment naming the screens
that moved and by how much. Pushing to a labelled PR refreshes both.
gh pr edit <N> --add-label design-review
Prefer this when the PR is already pushed — the reviewer gets a permanent link on the PR rather than a file on someone's laptop. Build it locally when iterating on uncommitted work, which the label cannot see.
Fork PRs get the artifact but no comment; their token is read-only.
Produce the report
From web/app/:
npm run design:review
Or from the repo root, make design-review. Either writes
.dev/design-review/report.html — one self-contained file with the images
inlined, so it can be sent to someone who will never clone the repo.
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 · 153 lines · 162 tokens per session scan A 3e27184f8a0b
design-review is a skill published in the GitHub repository theimaginaryfoundation/what-iff (19 stars, last pushed today), licensed Apache-2.0. It adds 162 tokens to every session and 1,653 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 2026-09-14.
Other skills, from other repositories
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
design-review
Five-dimension design audit (frontend UI/UX · server data-model & flow · endpoint spec · daemon-runtime/SDK & local-cache-first · built-in skill/agent-role), executed by a NON-implementing agent. Every dimension gets a verdict; N/A only with a stated reason. A dimension the design silently skipped must be surfaced as…
cinematic-shot
Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo. Use when asked for a…
compare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
design-with-images
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
preview-shots
Open image shots (screenshots, snapshot baselines, montages, renders) in ONE macOS Preview window so the user can eyeball them. Use when the user asks to open / show / pull up / review shots in Preview or Finder, or right after producing visual artifacts the user should look at before signing off.