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 wahidyankf/ose-public --skill web-testing-design-fidelitygit clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/web-testing-design-fidelity)<a href="https://agentmods.dev/skills/wahidyankf/ose-public/web-testing-design-fidelity"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/web-testing-design-fidelity/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/wahidyankf/ose-public/web-testing-design-fidelity"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/web-testing-design-fidelity.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 | $0.00074 | $0.00706 |
| Opus 5.5 | $0.00030 | $0.00282 |
| Sonnet 5.5 | $0.00015 | $0.00141 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
web-testing-design-fidelity 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 2d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Testing: Design Fidelity
Methodology for judging whether a running, rendered page matches its intended design and follows good visual-design practice — the design-team advocate of the live-site tester triad (alongside spec-aware exploratory testing and spec-blind usability testing).
Reference Modules
- Why This Agent Exists and Inputs — the design-fidelity gap this agent closes; URL(s), design goal, and optional refinements.
- Relationships and Boundary and
Non-Destructive Constraint — relationship to other
agents, the
swe-reviewerhard boundary, allowed/forbidden actions. - Methodology and Ground-Truth Sources — design-fidelity comparison, design-practice review's seven principles, the five ground-truth sources.
- Design Dimensions Checklist — the full dimension-by-dimension checklist.
- Mandatory Systematic Checks — the two forcing functions (raw-element audit, styling-consistency matrix).
- Browser Driving — how to drive the browser, Locale + Evidence Awareness.
- Finding Anatomy and Severity —
DWT-###anatomy, severity and priority scales. - Output Modes Overview and
Output Mode: plan — the output-mode selection table and the
explicitly authorized
planmode's document set. - Output Modes: delivery/local-tmp, and Procedure
— the
deliveryandlocal-tmpmodes, and the procedure summary. - Quality Guidelines and Constraints — quality guidelines and hard constraints.
What ships with it
16 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.
- README.md 591 B
- reference/browser-driving.md 2.9 KB
- reference/design-dimensions-checklist.md 1.8 KB
- reference/finding-anatomy-and-severity.md 3.5 KB
- reference/ground-truth-sources.md 1.9 KB
- reference/inputs.md 2.5 KB
- reference/mandatory-systematic-checks.md 2.3 KB
- reference/methodology.md 2.3 KB
- reference/non-destructive-constraint.md 1.0 KB
- reference/output-mode-plan.md 3.6 KB
- reference/output-modes-delivery-localtmp-and-procedure.md 4.2 KB
- reference/output-modes-overview.md 1.9 KB
- reference/quality-guidelines-and-constraints.md 1.8 KB
- reference/README.md 1.9 KB
- reference/relationships-and-boundary.md 3.3 KB
- reference/why-this-agent-exists.md 1.8 KB
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.
- 2d ago First seen · 51 lines · 74 tokens per session scan A fd7796189954
web-testing-design-fidelity is a skill published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 706 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 2026-10-14.
Other skills, from other repositories
chrome-tokens
Use this skill when you need to reference Chrome Design System token data or generate a token map.
repro-public
Reproduce a bug in the public-facing rendered site (not the admin). Attach a container, start the demo dev server, drive public routes with agent-browser, and capture the reproduction as screenshots plus a replayable transcript.
agent-annotations
Create or edit element annotations in desktop Browser tabs, or update saved annotation comments through the plugin RPC.
quill-code
Edit the @posthog/quill design system locally and consume the change in products/desktop before it is published to npm. Use when changing quill components/primitives/tokens, when a quill change must be tested inside the Code app, or when the user mentions quill, the design system, the .local-quill tarball, or the…
a11y-keyboard-playwright
Write keyboard-only test variants and focus management checks using Playwright: navigation patterns, focus expectations, helpers, and file structure conventions.
kernelcad-authoring
Write or edit .kcad.ts TypeScript models; run kernelcad evaluate or kernelcad export stl|step|dxf|3mf|glb -o .