What is screenshot-to-code AGENTS.md?

A set of project instructions for a screenshot-to-code application, covering its Python backend, frontend, hosted version, prompts, and required checks.

Use it when changing the backend or frontend, writing multi-line prompts, working with the hosted branch, or running the required tests, type checks, and linting.

It gives an agent consistent rules for working in that project and verifying changes after editing code.

How abi/screenshot-to-code configures Codex and OpenCode

About the project

Screenshot to Code is an AI application that turns screenshots, mockups, Figma designs, and screen recordings into functional website code for stacks including HTML, Tailwind, React, Vue, Bootstrap, and Ionic. It is for developers and designers who want to turn visual references into working prototypes, either through the hosted app or a locally run React/Vite and FastAPI application. The catalogue instructions help agents operate this screenshot-to-code workflow.

abi/screenshot-to-code · 81,047 stars · on GitHub · screenshottocode.com

Reuse

Borrowing it

Nothing to install: this file belongs to abi/screenshot-to-code. 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/abi/screenshot-to-code/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/abi/screenshot-to-code

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/abi/screenshot-to-code/agents-md/github.svg)](https://agentmods.dev/instructions/abi/screenshot-to-code/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/abi/screenshot-to-code/agents-md"><img src="https://agentmods.dev/badge/instructions/abi/screenshot-to-code/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/abi/screenshot-to-code/agents-md"><img src="https://agentmods.dev/badge/instructions/abi/screenshot-to-code/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 839 This file is loaded in full into every session.

When invoked 839 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00839	$0.00839
Opus 5.5	$0.00336	$0.00336
Sonnet 5.5	$0.00168	$0.00168
Haiku 4.5	$0.00084	$0.00084

Measured 2mo ago against content hash 0d44a766fe4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

screenshot-to-code 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 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Agent Instructions

Python environment:

Always use the backend Poetry virtualenv (backend-py3.10) for Python commands.
Preferred invocation: cd backend && poetry run <command>.
If you need to activate directly, use Poetry to discover it in the current environment:
- cd backend && poetry env activate (then run the source .../bin/activate command it prints)

Testing policy:

Always run backend tests after every code change: cd backend && poetry run pytest.
Always run type checking after every code change: cd backend && poetry run pyright.
Type checking policy: no new warnings in changed files (pyright).

Frontend

Frontend: cd frontend && pnpm lint

If changes touch both, run both sets.

Prompt formatting

Prefer triple-quoted strings ("""...""") for multi-line prompt text.
For interpolated multi-line prompts, prefer a single triple-quoted f-string over concatenated string fragments.

Hosted

The hosted version is on the hosted branch. The hosted branch connects to a saas backend, which is a seperate codebase at ../screenshot-to-code-saas

Cursor Cloud specific instructions

Dependencies are refreshed automatically on startup (poetry install in backend/, pnpm install in frontend/); no manual install is needed. Cursor Cloud environment setup should run bash /agent/repos/screenshot-to-code/scripts/cursor-cloud-install.sh; the script changes to the repo root before installing so it works regardless of the startup working directory.

Services (see README.md for the canonical commands):

Backend (FastAPI + WebSocket): from backend/, poetry run uvicorn main:app --reload --port 7001.
Frontend (Vite/React): from frontend/, pnpm dev → open http://localhost:5173. The Vite dev server binds to localhost only, so use http://localhost:5173, not http://127.0.0.1:5173 (the latter refuses the connection).
Frontend talks to the backend over a WebSocket (VITE_WS_BACKEND_URL, default ws://127.0.0.1:7001); generation streams over that socket, other routes are plain HTTP.

Read the full file on GitHub · 48 lines

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.

2mo ago First seen · 48 lines · 839 tokens per session scan A 0d44a766fe4e

Subscribe to this mod's changes

screenshot-to-code AGENTS.md is an instructions file published in the GitHub repository abi/screenshot-to-code (81,047 stars, last pushed yesterday), licensed MIT. It adds 839 tokens to every session, about $0.0034 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.

screenshot-to-code AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
screenshot-to-code AGENTS.mdabi/screenshot-to-code	Instructions file	81k	yesterday	MIT	A	839	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

screenshot-to-code: Instructions file for Codex