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/abi/screenshot-to-code/agents-mdgit clone --depth 1 https://github.com/abi/screenshot-to-codeWhat 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 | $0.00839 | $0.00839 |
| Opus 5 | $0.00419 | $0.00419 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
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 2d 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 — 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 thesource .../bin/activatecommand 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→ openhttp://localhost:5173. The Vite dev server binds tolocalhostonly, so usehttp://localhost:5173, nothttp://127.0.0.1:5173(the latter refuses the connection). - Frontend talks to the backend over a WebSocket (
VITE_WS_BACKEND_URL, defaultws://127.0.0.1:7001); generation streams over that socket, other routes are plain HTTP.
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.
- 2d ago First seen · 48 lines · 839 tokens per session scan A 0d44a766fe4e
screenshot-to-code AGENTS.md is an instructions file published in the GitHub repository abi/screenshot-to-code (76,986 stars, last pushed 18d ago), licensed MIT. It adds 839 tokens to every session, about $0.0042 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.