Borrowing it
Nothing to install: this file belongs to synaptic-ai-consulting/AAMAD. 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/synaptic-ai-consulting/AAMAD/main/.cursor/skills/visual-regression/SKILL.mdgit clone --depth 1 https://github.com/synaptic-ai-consulting/AAMADWrote 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/synaptic-ai-consulting/aamad/visual-regression)<a href="https://agentmods.dev/skills/synaptic-ai-consulting/aamad/visual-regression"><img src="https://agentmods.dev/badge/skills/synaptic-ai-consulting/aamad/visual-regression/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/synaptic-ai-consulting/aamad/visual-regression"><img src="https://agentmods.dev/badge/skills/synaptic-ai-consulting/aamad/visual-regression.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 | $0.00070 | $0.00730 |
| Opus 5.5 | $0.00028 | $0.00292 |
| Sonnet 5.5 | $0.00014 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
visual-regression 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual regression
Repeatable screenshot comparison for UI projects. Playwright Test toHaveScreenshot lives in the generated MVP, not in the AAMAD installer. Do not add Playwright to AAMAD itself. Do not require Playwright MCP or a Playwright CLI skill.
Invocation: *review-ui (first baseline after Human judgment), *test-visual / *qa (run), *update-visual-baselines (operator-approved update).
@frontend.eng scaffolds specs and updates snapshots. @qa.eng runs the suite. @ux.designer does not install Playwright or edit application source.
Read reference.md for thresholds, fixtures, ignore regions, and the match-is-not-good-design rule.
When to run
Run when UI is in scope and this turn captures, runs, or updates visual baselines.
Stop if there is no user-facing UI, or frontend.md records a no-UI skip. Write not tested in project-context/2.build/ux-review.md with that rationale.
Brownfield: snapshot changed routes and states only.
Procedure
- Read
ux.mdviewports, routes, and state matrix (brownfield: changed routes only). - If no UI / no-UI skip: record not tested in
ux-review.mdand stop. - Add Playwright Test as a generated-app devDependency for the project stack. Serve any URL the app already uses. Do not assume React. Record the install and script in
setup.md/frontend.md. - Write specs that exercise the primary-task states from
ux.mdand calltoHaveScreenshotper route × state × viewport. - First baseline: only after
ux-review.mdHuman judgment has no open high-severity findings, or the operator accepted them. Commit snapshots next to the spec. - Later runs:
npx playwright testor the recorded script. Failures are Mechanical findings; attach the diff path. - Updating a baseline: present one proposal and stop. Do not overwrite snapshots in the same turn. After the operator approves, write only the approved files. Same halt-and-wait pattern as
*sync-docs.
What ships with it
1 file 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.
- 4d ago First seen · 59 lines · 70 tokens per session scan A f9d52e7de574
visual-regression is a skill published in the GitHub repository synaptic-ai-consulting/AAMAD (88 stars, last pushed 4d ago), licensed Apache-2.0. It adds 70 tokens to every session and 730 once invoked, about $0.0003 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 2026-10-25.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.