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/mtbun/storeshots-mcp/agents-mdgit clone --depth 1 https://github.com/mtbun/storeshots-mcpWrote 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/mtbun/storeshots-mcp/agents-md)<a href="https://agentmods.dev/instructions/mtbun/storeshots-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mtbun/storeshots-mcp/agents-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 | $0.01332 | $0.01332 |
| Opus 5 | $0.00666 | $0.00666 |
| Sonnet 5 | $0.00266 | $0.00266 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
storeshots-mcp AGENTS.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 4d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guide for coding agents and human contributors working on storeshots-mcp.
What this project is
A TypeScript toolkit that renders App Store and Google Play marketing screenshots. The deterministic render engine is a standalone core, exposed through three thin surfaces:
- MCP server (primary distribution): standard stdio transport, so it works in every MCP client (Claude Code, Claude Desktop, Cursor, Windsurf, Antigravity, Codex, Gemini CLI, VS Code, Zed).
- CLI:
npx storeshots <command>for humans and scripts. - Claude Code skill (
skill/SKILL.md): carries the guided workflow, delegates all rendering to the MCP tools or CLI.
The core does deterministic pixel work only. All copywriting, translation, and benefit selection is done by the calling agent. Read README.md first for the product surface.
Architecture
src/
index.ts MCP server entry: registers tools, stdio transport
cli.ts CLI entry: same core, argv interface
presets.ts Platform presets (dimensions, layout metrics, safe areas)
render/
compose.ts Single-screenshot composition pipeline + layout variants
frame.ts Built-in programmatic frames + renderCustomDevice (BYO frame)
panorama.ts Continuous gradient sliced across a set
text.ts Headline layout, sizing, luminance-based color
showcase.ts Multi-screenshot preview strip
validate.ts Store dimension/format checks
tools/ One file per MCP tool, thin wrappers over render/
skill/
SKILL.md Claude Code skill: workflow layer only, no code (planned)
assets/
fonts/ Bundled OFL-licensed font files only
showcase.png README hero image, rendered from real app screens (sources
live outside this repo; scripts/make-demo.mjs regenerates an
equivalent strip from generated mock screens instead)
test/
scripts/
make-demo.mjs Generates mock app screens, demo set, and the showcase
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.
- 4d ago First seen · 99 lines · 1,332 tokens per session scan A 217a1faebce9
storeshots-mcp AGENTS.md is an instructions file published in the GitHub repository mtbun/storeshots-mcp (20 stars, last pushed 1mo ago), licensed MIT. It adds 1,332 tokens to every session, about $0.0067 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
appshot AGENTS.md
Instructions for trunghaiy/appshot, covering agents.md, repository overview, architecture, repository structure and agent skills specification.
appshot CLAUDE.md
Instructions for trunghaiy/appshot, covering appshot — claude code project brief, key constraint, where things live, build and git.
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).
prompt-to-asset copilot-instructions.md
Copilot instructions for MohamedAbdallah-14/prompt-to-asset, covering copilot instructions — prompt-to-asset, asset generation — always-on rule, three execution modes (four paths including free api), mcp tool surface (25 tools) and fallback when mcp is unavailable.
imagine-mcp AGENTS.md
AGENTS.md instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.
pixeltamer-gpt-image-skill CLAUDE.md
Instructions for gabelul/pixeltamer-gpt-image-skill, covering claude.md — pixeltamer, what this is, architecture, how the skill works and the two backends.