agentmods.dev

Diffuse-Native-Apps: Skill for Claude Code

.agents/skills/screenshots/SKILL.md

screenshots is a skill for Claude Code, Codex from hoangsonww/Diffuse-Native-Apps. It costs 32 tokens per session (342 once invoked), scanned A, original, MIT.

A guide for regenerating documentation images from live Mac, iPhone, iPad, Watch, and Android apps. It provides capture scripts and checks that a permission failure or wrong screen does not replace an image with unusable output.

In plain words
What is it for?
Use it after user-interface changes or when documentation needs new screenshots, including web media generated from the app.
Why use it?
It prevents stale screenshots and catches common capture mistakes, such as black images or an Android home screen being saved as an app image. The scripted process makes repeated captures comparable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is hoangsonww/Diffuse-Native-Apps's own configuration. It tells Claude Code and Codex how to work on Diffuse-Native-Apps itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Diffuse-Native-Apps configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 Scripts/build-web-media.py # derive web/media/*.jpg.

not rated 11repo 1mo ago A scan 32 tokens original MIT
View source ↗ hoangsonww/Diffuse-Native-Apps hoangsonww.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/Diffuse-Native-Apps. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hoangsonww/Diffuse-Native-Apps/master/.agents/skills/screenshots/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/Diffuse-Native-Apps

Made for: Claude Code, Codex.

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 screenshots

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangsonww/diffuse-native-apps/screenshots/github.svg)](https://agentmods.dev/skills/hoangsonww/diffuse-native-apps/screenshots)
Your own site
<a href="https://agentmods.dev/skills/hoangsonww/diffuse-native-apps/screenshots"><img src="https://agentmods.dev/badge/skills/hoangsonww/diffuse-native-apps/screenshots/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 screenshots

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangsonww/diffuse-native-apps/screenshots"><img src="https://agentmods.dev/badge/skills/hoangsonww/diffuse-native-apps/screenshots.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 342 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00342
Opus 5.5 $0.00013 $0.00137
Sonnet 5.5 $0.00006 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured yesterday against content hash 6c37e8ed5812, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

screenshots 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 yesterday.

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.

.agents/skills/screenshots/SKILL.md · 26 lines

What it actually says

Screenshots

Replace PNGs in docs/screenshots/. Do not invent marketing images.

Use the scripts; they encode the traps.

Scripts/capture-macos-screenshots.sh          # or one screen by name
Scripts/capture-simulator-screenshots.sh      # ios | ipados | watchos
Scripts/capture-android-screenshots.sh        # or one screen by name
python3 Scripts/build-web-media.py            # derive web/media/*.jpg
  • A denied Screen Recording permission yields a black PNG, not an error. The scripts check colour variance before replacing a committed file.
  • Granting Screen Recording to a debug build does not stick — ad-hoc signing changes identity each rebuild. macOS captures run screencapture from the terminal instead.
  • Android navigation is gated: a missing tap target fails rather than photographing whatever is in front, and the script refuses when Diffuse is not foreground. That is how a phone home screen once shipped as android-search.png.
  • The Android library is seeded from Fixtures/ and the capture-on-open pruned, so comparisons show real changes and reruns are reproducible.
  • simctl launch only forwards SIMCTL_CHILD_-prefixed variables; anything else is argv.
  • Update the date at the top of docs/screenshots/README.md when images are replaced.
  • Scripts/generate-icons.py is for app icons, not these shots.
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. yesterday First seen · 26 lines · 32 tokens per session scan A 6c37e8ed5812

Subscribe to this mod's changes

screenshots is a skill published in the GitHub repository hoangsonww/Diffuse-Native-Apps (11 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 342 once invoked, about $0.0001 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 2026-11-07.

Creative and mediaDocumentsandroiddevice-monitoringgradleiosipadosjetpack-compose
Related

screenshots compared with skills from other repositories

screenshots next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
screenshotshoangsonww/Diffuse-Native-AppsSkill111mo agoMITA32Claude Code, Codex
motion-design-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA129Claude Code
android-adaptive-layout-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA147Claude Code
android-gradle-architecture-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA74Claude Code
r8-shrink-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA87Claude Code
xml-to-compose-migration-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA78Claude Code
swift-adaptive-layout-prokelvinkosbab/AppBootstrapAISkill8yesterdayMITA129Claude Code