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 buddyh/agent-skills --skill app-screenshotsgit clone --depth 1 https://github.com/buddyh/agent-skillsWrote 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/buddyh/agent-skills/app-screenshots)<a href="https://agentmods.dev/skills/buddyh/agent-skills/app-screenshots"><img src="https://agentmods.dev/badge/skills/buddyh/agent-skills/app-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.
<a href="https://agentmods.dev/skills/buddyh/agent-skills/app-screenshots"><img src="https://agentmods.dev/badge/skills/buddyh/agent-skills/app-screenshots.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 | $0.00079 | $0.01142 |
| Opus 5.5 | $0.00032 | $0.00457 |
| Sonnet 5.5 | $0.00016 | $0.00228 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
app-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 2mo 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Screenshots
Systematically capture every view/screen of an application for marketing, product sites, README assets, and documentation.
Workflow
1. Discover all views/screens in the app
2. Build + launch the app (if not already running)
3. Navigate to each view and screenshot it
4. Save named screenshots to output directory
5. Generate a manifest (summary.md)
Step 1: Discover Views
Analyze the project to enumerate all distinct views/screens. Methods by project type:
Swift/SwiftUI macOS apps: Grep for View structs, WindowGroup, Window, Settings, sheets, popovers, menu bar panels. Check for multiple window types, onboarding flows, settings tabs.
Web apps: Check routes (React Router, Next.js pages, Express routes). Each route = one screenshot minimum. Also check for modals, drawers, settings panels.
Electron apps: Check BrowserWindow creation, route handlers, IPC window openers.
Present the discovered view list to the user for confirmation before proceeding:
Found 8 views:
1. Main window (default state)
2. Settings > General
3. Settings > Appearance
4. Settings > Shortcuts
5. Popdown menu
6. Onboarding wizard
7. Empty state
8. Active session state
Proceed? Any views to add/skip?
Step 2: Build + Launch
Build and launch the app if it's not already running. If it is, skip this step.
Step 3: Capture Each View
Navigate to each view and capture it. Sequential only -- one view at a time.
macOS Native Apps (Swift/SwiftUI)
# Get window ID for the app
WINDOW_ID=$(osascript -e 'tell application "System Events" to get id of first window of (first process whose name is "AppName")')
# Screenshot specific window (no shadow, no sound)
screencapture -l $WINDOW_ID -o -x "$OUTPUT_DIR/view-name.png"
For views that require navigation (settings tabs, popovers):
- Use AppleScript or accessibility APIs to click/navigate
- Or instruct the user: "Please open Settings > Appearance, then press Enter"
- Wait, then capture
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.
- 2mo ago First seen · 154 lines · 79 tokens per session scan A f7eea9807642
app-screenshots is a skill published in the GitHub repository buddyh/agent-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 1,142 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 2026-08-31.
app-screenshots compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| app-screenshotsbuddyh/agent-skills | Skill | 5 | 3mo ago | MIT | A | 79 | Claude Code, Codex |
| frontend-designanthropics/claude-plugins-official | Skill | 46k | yesterday | Apache-2.0 | A | 40 | Claude Code |
| display-glasses-with-jetpack-compose-glimmerandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 112 | Claude Code |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| readtw93/Waza | Skill | 7.5k | 6d ago | MIT | A | 61 | Claude Code |
| visual-editBuilderIO/skills | Skill | 4.7k | 5d ago | MIT | A | 42 | Claude Code |
| visual-planBuilderIO/skills | Skill | 4.7k | 5d ago | MIT | A | 32 | Claude Code |