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 agentmods add skills/arozumenko/sdlc-skills/visual-testingnpx skills add arozumenko/sdlc-skills --skill visual-testinggit clone --depth 1 https://github.com/arozumenko/sdlc-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/arozumenko/sdlc-skills/visual-testing)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/visual-testing"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/visual-testing.svg" alt="Measured on agentmods" 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 | $0.00176 | $0.01222 |
| Opus 5 | $0.00088 | $0.00611 |
| Sonnet 5 | $0.00035 | $0.00244 |
| Haiku 4.5 | $0.00018 | $0.00122 |
Grade A, and why
visual-testing 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 5d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual testing
Catch unintended visual change. Rendered UI is deterministic enough that a pixel which moved without an intended cause is worth seeing — a card that lost its shadow, a table that overflows on tablet, a button that drifted but still works. This skill screenshots each screen and diffs it against a baseline captured when the UI was last correct.
Two halves, kept separate on purpose:
- Capture is agent-driven. You open the thing under test in whatever browser or device tool you already have and save a PNG. No headless browser is bundled or installed — capture rides on the tooling that already exists (a connected browser, a Playwright/Appium session, a running app's automation).
- Diff is browser-free.
scripts/visual-diff.mjsshells out toreg-cli(resolved local-first, elsenpx --yes reg-cli@latest, so nothing is added topackage.json) to compare, manage baselines, and write a report.
Workflow
- Render the thing under test.
- A generated static page → build it, then open the HTML from disk (
file://); the pages are self-contained, no server needed. - A running app → drive it to the screen/state with the automation you already use (Playwright for web, the device tooling for mobile). This is the same navigation a functional check performs — the visual diff is an extra assertion, not a separate run.
- A generated static page → build it, then open the HTML from disk (
- Capture each screen into a
current/directory, one PNG per variant, named by the scheme below. Seereferences/capturing.mdfor driving each source and controlling the noise that makes diffs flaky. - Diff against the baseline:
Exitnode scripts/visual-diff.mjs --current <current/> --baseline <baselines/> --diff <out/>0= no change; exit1= something changed (report at<out/>/report.html). - Review the report. An intended change (a redesign, a shipped restyle) →
promote it:
node scripts/visual-diff.mjs --current <current/> --baseline <baselines/> --diff <out/> --updatethen commit the updated baselines. An unintended change → a finding: fix the cause (or file the defect with the diff image); do not update the baseline.
What ships with it
4 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.
- 5d ago First seen · 85 lines · 176 tokens per session scan A b4a530c92175
visual-testing is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed yesterday), licensed MIT. It adds 176 tokens to every session and 1,222 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…