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 ncklrs/claude-chrome-user-testing --skill screenshot-annotatorgit clone --depth 1 https://github.com/ncklrs/claude-chrome-user-testingWrote 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/ncklrs/claude-chrome-user-testing/screenshot-annotator)<a href="https://agentmods.dev/skills/ncklrs/claude-chrome-user-testing/screenshot-annotator"><img src="https://agentmods.dev/badge/skills/ncklrs/claude-chrome-user-testing/screenshot-annotator/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/ncklrs/claude-chrome-user-testing/screenshot-annotator"><img src="https://agentmods.dev/badge/skills/ncklrs/claude-chrome-user-testing/screenshot-annotator.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 | $0.00000 | $0.02145 |
| Opus 5 | $0.00000 | $0.01073 |
| Sonnet 5 | $0.00000 | $0.00429 |
| Haiku 4.5 | $0.00000 | $0.00215 |
Grade A, and why
screenshot-annotator 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 9d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot Annotator Skill
This skill provides visual annotation capabilities for screenshots taken during user testing. Annotations help highlight issues, confusion points, and notable elements in test screenshots.
Purpose
Add visual markers (boxes, highlights, callouts) to screenshots before capturing them. This makes test reports more actionable by clearly showing where issues occurred.
Annotation Types
Box
A rectangular border around an element.
| Variant | Border Style | Use Case |
|---|---|---|
error |
3px solid red | Form errors, broken functionality |
confusion |
3px dashed red | User hesitation, unclear elements |
warning |
3px solid orange | Frustration triggers, warnings |
success |
3px solid green | Task completion, positive elements |
info |
3px solid blue | General callouts |
Highlight
A semi-transparent overlay on an element.
| Color | Opacity | Use Case |
|---|---|---|
| Yellow | 40% | Draw attention to area |
| Orange | 30% | Frustration trigger match |
| Red | 25% | Critical issue area |
Callout
A numbered circle positioned near an element, used for referencing multiple issues.
Color Palette
error/confusion: #dc2626 (red-600)
warning: #f59e0b (amber-500)
success: #16a34a (green-600)
info: #2563eb (blue-600)
highlight: #fbbf24 (amber-400)
How to Add Annotations
Use browser_evaluate to inject annotation elements before taking a screenshot. All DOM manipulation must use safe methods (createElement, appendChild, setAttribute).
Step 1: Get Element Position
First, find the target element and get its bounding box:
// Via browser_evaluate
const element = document.querySelector('[data-testid="submit-btn"]');
const rect = element.getBoundingClientRect();
const position = {
x: rect.left + window.scrollX,
y: rect.top + window.scrollY,
width: rect.width,
height: rect.height
};
return position;
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.
- 9d ago First seen · 311 lines · 0 tokens per session scan A b3a3f7e2d215
screenshot-annotator is a skill published in the GitHub repository ncklrs/claude-chrome-user-testing (19 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,145 tokens. 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
accessibility-audit
Use when wCAG compliance audit — semantic HTML, ARIA, keyboard navigation, color contrast, and screen reader testing. Use when working with accessibility audit.
age-inclusive-design
Design for users of all ages. Use when user asks to 'make accessible for older adults', 'improve age-inclusive design', 'help elderly users', 'reduce age-related friction', 'design for all ages', 'age-friendly interface'.
design-qa
Set up or run design QA gates — token + hardcoded-value lint, automated a11y (axe), contrast, visual regression across variants/states/themes/RTL, and the manual a11y checklist. Use when the user wants CI quality gates, to prevent design regressions, or to QA a component/screen before shipping.
uxloom
Validates UI/UX designs with UXLoom — models user journeys as state machines and proves what screens are missing (unreachable states, dead ends, empty/loading/error coverage, WCAG contrast, touch targets, localization overflow) before code exists. Use when designing screens or user flows, validating AI-generated UI…
ux-researcher
!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/design-mindset-and-rules.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults".
a11y-content-judgment
Load this skill when an audit needs the judgment-shaped WCAG criteria that scanners cannot decide — are page titles, headings, form labels, link text in context, and image alternatives actually useful, meaningful, and descriptive for the person relying on them (2.4.2, 2.4.6, 2.4.4, 1.1.1), and is navigation consistent…