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 agentmods add instructions/trunghaiy/appshot/claude-mdgit 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/instructions/trunghaiy/appshot/claude-md)<a href="https://agentmods.dev/instructions/trunghaiy/appshot/claude-md"><img src="https://agentmods.dev/badge/instructions/trunghaiy/appshot/claude-md.svg" alt="Measured on agentmods" 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 | $0.00308 | $0.00308 |
| Opus 5 | $0.00154 | $0.00154 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
appshot CLAUDE.md 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 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.
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.
What it actually says
Appshot — Claude Code Project Brief
App Store preview video generator for mobile apps (iOS/Android). AI skills scan a target app's codebase, propose a narrative, and write custom Remotion scene components using shared animation primitives.
- Creator: Kian Nguyen
- License: MIT
Key constraint
All video output is 886×1920px (App Store native for iPhone 6.7"). Every sizing rule in the skills and components is calibrated for this canvas width. PhoneFrame scale: 1.5. Text outside PhoneFrame: body 24px+, titles 34px+.
Where things live
template/src/components/— 10 animation primitives (the product)skills/appshot-core/— extraction, config schema, primitives catalogskills/appshot-videos/— video creative director +references/code-guide.mdskills/appshot-images/— screenshot creative director.claude/skills/— auto-populated bynpx skills add, do NOT edit directly
Build
npm run dev # Remotion Studio preview
npm run build # Render 886×1920 MP4 (H.264, CRF 18, yuv420p, bt709)
Git
Conventional commits: feat(videos):, fix(skill):, chore:, refactor:, docs:
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.
- 5d ago First seen · 30 lines · 308 tokens per session scan A bf19b0f604cf
appshot CLAUDE.md is an instructions file published in the GitHub repository trunghaiy/appshot (42 stars, last pushed 3mo ago), licensed MIT. It adds 308 tokens to every session, about $0.0015 per session on Opus 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 instructions, from other repositories
storeshots-mcp CLAUDE.md
Instructions for mtbun/storeshots-mcp, a project described as: Store-ready App Store & Google Play screenshots from any MCP client. Device frames, benefit-driven headlines, exact store dimensions. No API keys.
claude-code-apple-skills CLAUDE.md
Claude Code instructions for rshankras/claude-code-apple-skills, covering claude.md, repository purpose, architecture, skill structure and yaml frontmatter (required).
storeshots-mcp AGENTS.md
Instructions for mtbun/storeshots-mcp, covering agents.md, what this project is, architecture, non-negotiable principles and layout contract (compose).
indie-app-shipping AGENTS.md
Instructions for cuongdev/indie-app-shipping, covering agents.md — indie app shipping, strategic frame, platform selection (decide first), workflow for a new app and decision framework: deepen or park.
app-store-operator CLAUDE.md
Instructions for meyusufdemirci/app-store-operator, covering app store operator — mcp server, codebase, server wiring, tool module contract and prompts.
apple-ads-mcp CLAUDE.md
Claude Code instructions for zelentsov-dev/apple-ads-mcp, covering apple ads mcp, product, architecture, safety and consumer setup.