preview-report

preview-report is a skill for Claude Code from k-kohey/axe. It costs 39 tokens per session (594 once invoked), scanned C, original, MIT.

A batch tool that captures screenshots from multiple SwiftUI preview blocks and puts them into a Markdown report. SwiftUI is Apple's framework for building interfaces on its platforms.

In plain words
What is it for?
Use it to check changed Swift files, create visual reports for pull requests, and review UI across multiple files.
Why use it?
It lets you review several views together instead of opening and checking each preview separately.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the axe-preview plugin — 5 skills shipped together

Good fit Use it to check changed Swift files, create visual reports for pull requests, and review UI across multiple files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/k-kohey/axe/preview-report
View source ↗ k-kohey/axe
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 k-kohey/axe --skill preview-report
Clone the repo
git clone --depth 1 https://github.com/k-kohey/axe

Made for: Claude Code.

Or install axe-preview, the plugin that ships this one along with the rest of its 5 skills.

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.

agentmods badge for preview-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/k-kohey/axe/preview-report/github.svg)](https://agentmods.dev/skills/k-kohey/axe/preview-report)
Your own site
<a href="https://agentmods.dev/skills/k-kohey/axe/preview-report"><img src="https://agentmods.dev/badge/skills/k-kohey/axe/preview-report/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.

agentmods 80×15 button for preview-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/k-kohey/axe/preview-report"><img src="https://agentmods.dev/badge/skills/k-kohey/axe/preview-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 594 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00594
Opus 5.5 $0.00016 $0.00238
Sonnet 5.5 $0.00008 $0.00119
Haiku 4.5 $0.00004 $0.00059

Measured 5d ago against content hash 0eb52ca84da1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

preview-report scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/k-kohey/axe/main/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/k-kohey/axe/main/install.sh | sh
claude-plugin/skills/preview-report/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Batch Preview Report

Capture screenshots of all #Preview blocks across multiple SwiftUI files and generate a report.

Steps

1. Determine target files

If $ARGUMENTS specifies files, use those directly. $ARGUMENTS may contain only View names (e.g. ContentView) instead of file paths, so resolve each to a .swift path (e.g. TodoApp/ContentView.swift) using Glob.

If no arguments are provided, detect changed Swift files:

FILES=$(git diff --name-only --diff-filter=ACMR HEAD -- '*.swift')
if [ -z "$FILES" ]; then
  echo "No changed Swift files found. Specify files explicitly."
  exit 1
fi

2. Generate the report

axe preview report $FILES --format md --output <output-dir>

When $ARGUMENTS is provided, use $ARGUMENTS instead of $FILES:

axe preview report $ARGUMENTS --format md --output <output-dir>

This generates:

  • axe_swiftui_preview_report.md — Markdown report with embedded image references
  • axe_swiftui_preview_report_assets/*.png — Individual preview screenshots

3. Display the results

Read the generated Markdown report with the Read tool. Then read each preview image in the assets directory to show them to the user.

4. Summarize

Provide a summary of all captured previews, noting:

  • Total number of #Preview blocks found
  • Any previews that failed to capture (and likely reasons from stderr)
  • Quick observations about the UI state of each view

Options

  • Use -j <n> to control parallel simulator count for faster capture
  • Use --reuse-build to skip rebuilding if the project was recently built
  • Replace --format md with --format html for an interactive HTML report with lightbox

Use Cases

  • PR review: Capture all changed views before creating a pull request
  • Visual regression: Compare previews across branches
  • Documentation: Generate a visual catalog of UI components

Prerequisites

Run this if the command fails because axe is not found::

curl -fsSL https://raw.githubusercontent.com/k-kohey/axe/main/install.sh | sh

Read the full file on GitHub · 75 lines

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.

  1. 5d ago First seen · 75 lines · 39 tokens per session scan C 0eb52ca84da1

Subscribe to this mod's changes

preview-report is a skill published in the GitHub repository k-kohey/axe (99 stars, last pushed 22d ago), licensed MIT. It adds 39 tokens to every session and 594 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-01.

Related

preview-report compared with skills from other repositories

preview-report next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
preview-reportk-kohey/axeSkill9922d agoMITC39Claude Code
ios-expertpersonamanagmentlayer/pclSkill4411d agoApache-2.0A64Claude Code
ttb-skill-native-swiftui-componentstqtuan1201/TTBaseUIKitSkill233mo agoMITA55Claude Code, Codex
ax-design-refKasempiternal/axiom-v2Skill48mo agoMITA64Claude Code
ax-designKasempiternal/axiom-v2Skill48mo agoMITA41Claude Code
swiftui-liquid-glassthiennc-tesoglobal/ios-skillsSkill31mo agononeA60Claude Code
swiftui-responsive-layoutthiennc-tesoglobal/ios-skillsSkill31mo agononeA76Claude Code