What is mockup-fidelity?

A measurement-based workflow for checking whether a React or React Native interface matches a reference mockup. It compares rendered screens, including different states and dialogs, and records visual and functional differences.

It is for testing implemented web or mobile interfaces against screenshots or mockups and documenting which elements are present, different, or missing.

Small layout, styling, or interaction differences are easy to miss when checking by eye or reading source code. This identifies mismatches in the running interface and helps close the gaps.

mockup-fidelity — Skill for Claude Code by fledgeling-co

Install

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.

Any agent

npx skills add fledgeling-co/fledgeling-plugins --skill mockup-fidelity

Clone the repo

git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Or install mockup-fidelity, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/mockup-fidelity/github.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/mockup-fidelity)

Your own site

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/mockup-fidelity"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/mockup-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/mockup-fidelity"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/mockup-fidelity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 338 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,180 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00338	$0.08180
Opus 5.5	$0.00135	$0.03272
Sonnet 5.5	$0.00068	$0.01636
Haiku 4.5	$0.00034	$0.00818

Measured 1mo ago against content hash 3b941b26cbc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mockup-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 1mo ago.

The scan reads SKILL.md. This mod also ships 18 executable files (assets/diff/analyze.js, assets/diff/capture-subtree.js, assets/diff/capture.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/mockup-fidelity/skills/mockup-fidelity/SKILL.md · 501 lines

How it starts

The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mockup Fidelity

Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. Turns mockup-fidelity's categorical promises into a numbered quota ledger (9 detector classes, 11 affordance classes, frames × states) and its stated maxima into a bound ledger read back off the artifact, requires the exit code and each inconclusive reason string to be quoted rather than summarised — because on this engine capture.mjs --assert can only return 3 — turns Phase 2's "goes through proctor" into four files each phase must open, and routes Phase 6's code changes out. Other models skip it.

First, two quick exits

An empty or bare invocation gets one question, not an inventory of nothing. If the request is just "check fidelity", "does it match", or "audit the UI" with no reference and no target named, ask in one line for the reference (what renders the truth) and the target (what to fix), then stop.

If the request names either one, or describes a screen concretely enough to find it, that is a brief — start Phase 0.

Read the full file on GitHub · 501 lines

Files

What ships with it

55 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.

Changes

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 Changed 3b941b26cbc0
1mo ago First seen · 501 lines · 338 tokens per session scan A 9bd360dacc90

Subscribe to this mod's changes

mockup-fidelity is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 338 tokens to every session and 8,180 once invoked, about $0.0014 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 2026-09-04.

Design and UX E2E testing Testing

qa-test-planner

Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.

davila7/claude-code-templates · 34 tokens

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.

plugin87/ux-ui-agent-skills · 37 tokens

visual-validation

Autonomous screenshot verification — captures, compares, and AI-evaluates UI changes for visual regressions.

alinaqi/maggy · 23 tokens

design-ship

One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…

yonatangross/orchestkit · 84 tokens

testing-coach

How to test: screen readers, keyboard passes, automated checks and CI.

Community-Access/accessibility-agents · 19 tokens

shaft-accessibility-testing

Use when testing web or mobile accessibility for WCAG conformance, keyboard and focus behavior, semantics, errors, or user impact.

ShaftHQ/SHAFT_ENGINE · 31 tokens