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 trunghaiy/appshot --skill appshot-coregit clone --depth 1 https://github.com/trunghaiy/appshotWrote 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/trunghaiy/appshot/appshot-core)<a href="https://agentmods.dev/skills/trunghaiy/appshot/appshot-core"><img src="https://agentmods.dev/badge/skills/trunghaiy/appshot/appshot-core/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/trunghaiy/appshot/appshot-core"><img src="https://agentmods.dev/badge/skills/trunghaiy/appshot/appshot-core.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 | $0.00047 | $0.10911 |
| Opus 5.5 | $0.00019 | $0.04364 |
| Sonnet 5.5 | $0.00009 | $0.02182 |
| Haiku 4.5 | $0.00005 | $0.01091 |
Grade A, and why
appshot-core 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.
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 — 836 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Appshot Core — Foundation
Reference skill for all Appshot skills. Read this before executing appshot-videos or appshot-images.
Architecture
- Remotion 4.0 + React 18 + Tailwind CSS 3.4
- Config defines app metadata and brand only — scenes are custom
.tsxfiles, not config entries - Each project has an orchestrator component (e.g.,
FooPreview.tsx) that sequences custom scenes via Remotion<Sequence>+<SceneWrap> - All primitives are brand-aware via a
brandprop derived from the config'sBrandColors
Project Context (auto-injected)
- Package manifest: !
cat package.json 2>/dev/null || cat pubspec.yaml 2>/dev/null || cat app.json 2>/dev/null - App colors: !
find . -maxdepth 4 \( -name 'colors.xml' -o -name 'Colors.swift' -o -name 'colors.ts' -o -name 'theme.ts' -o -name 'Color.kt' -o -name 'tailwind.config.js' -o -name 'tailwind.config.ts' \) 2>/dev/null | head -5 | xargs head -50 2>/dev/null - App icon: !
find . -maxdepth 5 \( -name 'ic_launcher.png' -o -name 'icon.png' \) -type f 2>/dev/null | head -3 - Store metadata: !
cat fastlane/metadata/en-US/full_description.txt 2>/dev/null || cat fastlane/metadata/en-US/description.txt 2>/dev/null || cat fastlane/metadata/android/en-US/full_description.txt 2>/dev/null - README excerpt: !
head -80 README.md 2>/dev/null
Extraction & Context Caching
Both appshot-videos and appshot-images use this extraction process. Results are cached to .appshot-context.json so extraction only runs once per project.
Check for cached context
Before scanning, check if .appshot-context.json exists in the project root. If it does:
- Load and present a summary to the user
- Ask: "I found a previous extraction. Confirm this is still correct, or re-scan?"
- If confirmed, skip extraction and proceed to the calling skill's next phase
- If re-scan requested, run extraction below and overwrite the file
Extraction steps
Step 1: Detect framework
Check for marker files in this order. Stop at the first match.
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 First seen · 836 lines · 47 tokens per session scan A 670c9af6b724
appshot-core is a skill published in the GitHub repository trunghaiy/appshot (49 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 10,911 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
aso-playbook
Beginner-friendly App Store Optimization guide covering keyword research, screenshot design, rating management, and A/B testing for iOS and Android. By @WeiYipei — practical ASO for indie developers and small teams.
gingiris-aso-growth
A broad guide to growing mobile apps through App Store Optimization, launch planning, creator-made content, and marketing on platforms such as TikTok, Instagram, and YouTube Shorts.
gr-aso
A skill for app-store optimization, or improving how an app is found and presented in the App Store and Google Play, plus launch planning for a new app. It covers listing text, screenshots and video, ratings, creator content, advertising, and localization.
storeshots
Make App Store and Google Play screenshots with the storeshots CLI (offline, no API keys). It writes benefit headlines, translates them, and renders exact-size images with device frames. Use when the user wants store screenshots, app listing or ASO images, localized screenshots in more languages, a Play Store feature…
aso-research
Researches and improves an app's visibility on the App Store and Google Play with Applyra's data (keyword rankings and their history, keyword difficulty and traffic, store autocomplete, niche analysis, competitors, top charts, the ASO Health audit of a listing), and scores a draft title, subtitle, short description or…
app-planner
Guides you through comprehensive iOS/Swift app planning and analysis. Use for new apps (concept to architecture) or existing apps (audit current state, plan improvements, evaluate tech stack). Covers product planning, technical decisions, UI/UX design, and distribution strategy.