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/r0stefan/webstudio-ai-agent/agents-mdgit clone --depth 1 https://github.com/R0STEFAN/webstudio-ai-agentWrote 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/r0stefan/webstudio-ai-agent/agents-md)<a href="https://agentmods.dev/instructions/r0stefan/webstudio-ai-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/r0stefan/webstudio-ai-agent/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 | $0.01902 | $0.01902 |
| Opus 5 | $0.00951 | $0.00951 |
| Sonnet 5 | $0.00380 | $0.00380 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
webstudio-ai-agent 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Webstudio AI Assistant Guide & Rules
Project Architecture & Workflow
This repository contains the Webstudio visual web builder and an AI agent design workflow.
AI Design & Cloud Sync Protocol:
- Local State Source of Truth: All site pages, instances, and styles are stored in
.webstudio/data.json. - Assets: All images and fonts reside in
.webstudio/assets/. - Design Tokens as CSS Classes (DRY Styles): NEVER duplicate styles across repeating elements (buttons, cards, badges, headings). Always declare and attach reusable Design Tokens as CSS classes using
ws:tokens={[token('<class-name>', css...)]}(e.g.btn-primary,card-surface,badge-success— do NOT prefix withtoken-). - Execution Skill: Always use the
webstudio-ai-designerskill (.agents/skills/webstudio-ai-designer/SKILL.md) when creating or modifying Webstudio designs. - Native MCP Tools (100% Local): All 70+ official Webstudio MCP tools run locally via:
npx webstudio mcp single-op-call <tool> --input-file <payload.json> # Setup once per project: npm i webstudio && node scripts/setup-local-mcp.mjs --local - Asset Upload & Cloud Sync Protocol:
- When generating new local images in
.webstudio/assets/, run:
This automatically uploads images via the session cookie innpm run upload-assets.webstudio/session.json, remaps all imagesrcprops indata.build.props, and syncs with Webstudio Cloud. - To manually push project structure to Webstudio Cloud:
npx webstudio import --to "<shareLink>"
- When generating new local images in
- Strict Breakpoints & Responsive Design Rules:
- ONLY Standard Webstudio Breakpoints: Webstudio strictly supports 4 standard breakpoints:
Base(Desktop / default, no media query)@media (max-width: 991px)(Tablet)@media (max-width: 767px)(Mobile landscape / general mobile)
- ONLY Standard Webstudio Breakpoints: Webstudio strictly supports 4 standard breakpoints:
Webstudio AI Assistant Guide & Rules
Project Architecture & Workflow
This repository contains the Webstudio visual web builder and an AI agent design workflow.
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 · 91 lines · 1,902 tokens per session scan A 8e5c4a191439
webstudio-ai-agent AGENTS.md is an instructions file published in the GitHub repository R0STEFAN/webstudio-ai-agent (0 stars, last pushed 2d ago), licensed MIT. It adds 1,902 tokens to every session, about $0.0095 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 2026-08-31.
Other instructions, from other repositories
gortex CLAUDE.md
Claude Code instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
peon-ping GEMINI.md
Instructions for PeonPing/peon-ping, covering gemini.md - peon-ping, project overview, main technologies, architecture and building and running.
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
free-ai-gateway AGENTS.md
Instructions for zaber-dev/free-ai-gateway, covering 🤖 free-ai gateway - agentic development guidelines, 🏛️ monorepo architecture & package boundaries, 🛑 strict architectural rules for agents, 💻 essential developer commands and build all packages across monorepo.
codevira CLAUDE.md
Instructions for sachinshelke/codevira, covering codevira — persistent project memory, when to call which codevira tool, at the start of every session, before modifying any file and before adopting a pattern, library, or naming convention.
agent-guides AGENTS.md
AGENTS.md instructions for sawrus/agent-guides, covering agents — root guidance, dynamic guidance loading, general development practices, git workflow and makefile conventions.