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 HoangNguyen0403/agent-skills-standard --skill quality-engineering-visual-baselinegit clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/quality-engineering-visual-baseline)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/quality-engineering-visual-baseline"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/quality-engineering-visual-baseline/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/hoangnguyen0403/agent-skills-standard/quality-engineering-visual-baseline"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/quality-engineering-visual-baseline.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 | $0.00067 | $0.00771 |
| Opus 5.5 | $0.00027 | $0.00308 |
| Sonnet 5.5 | $0.00013 | $0.00154 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
quality-engineering-visual-baseline 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.
Quality Engineering: Visual Baseline
Priority: P1 (HIGH)
Capture
- One baseline per scenario, viewport, theme, and locale that the plan names; never one baseline per developer machine. Capture in the CI image only; a locally captured baseline is a draft.
- Freeze animations and the clock before capture; wait for network idle and fonts loaded.
- Name baselines
<screen>-<state>-<viewport>[-dark][-<locale>].pngnext to the spec in the tool's snapshot folder.
Mask, Then Threshold
- Mask every dynamic region before comparing: clocks, counters, avatars, ads, maps, third-party embeds, randomised ids. A masked region is compared as a solid block, so a layout shift inside it still fails.
- Thresholds are per region and small: text and controls
0.1%max diff pixels, images and charts1%. A suite-wide threshold above1%is a disabled check. - Full detail in Masking and Thresholds.
Classify a Failure
A screenshot diff is VISUAL_DIFF. It is REAL_REGRESSION unless the whole diff lies inside a region that should have been masked or thresholded (then fix the mask, not the baseline). Layout shift, missing element, wrong color, or clipped text is a product change until the product owner says otherwise.
Update a Baseline
- A baseline changes only through a reviewed diff: before and after images in the PR, the intended product change linked, and an approver named in the commit. See Baseline Update Review.
- Never blind
--update-snapshots: it approves every diff in the run, including the regression you have not seen yet. - Update only the baselines whose diff was reviewed, scoped with
--grepand the spec path; regenerate the rest from the same commit so unrelated drift stays visible.
Red Flags
"just update the snapshots" · "bump the threshold to 5%" · "mask the whole header" · "it looks the same to me" — each accepts a regression sight unseen. Stop; review the diff image, name the intended change, then update the one 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.
- 1mo ago First seen · 62 lines · 67 tokens per session scan A 52c3ed0b3b2d
quality-engineering-visual-baseline is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (582 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 771 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 2026-09-14.
Other skills, from other repositories
verify
Build/launch/drive recipe for verifying apps/docs changes at runtime (demos, docs pages, llms.txt).
browser-automation
Playwright browser automation via MCP. Covers E2E testing, UI review, web scraping, screenshot capture, and general browser interaction. MCP-first — CLI is fallback only.
mobile-testing
Mobile E2E testing patterns — Flutter integrationtest, Patrol, Maestro, golden testing, device matrix, and test data management. Use when writing E2E tests for mobile applications.
test-e2e
Plans, authors, and executes end-to-end tests for mobile and web platforms. User-invoked entry point via /test-e2e; not for autonomous or subagent use.
test-integration
Audits I/O adapters, sets up test infrastructure, and systematically improves integration test coverage. User-invoked entry point via /test-integration; not for autonomous or subagent use.
patrol-e2e-testing
Use when writing E2E/integration tests, testing native interactions like permissions or system dialogs, capturing UI regressions, or validating cross-platform behavior (Patrol 4.x).