Markagent: UI/Web Feedback Annotator for AI Agents

Vibe coding feedback. Annotate webpages, screenshot & export agent prompts for Claude Code, Cursor, Codex, OpenCode, Antigravity.

Markagent is the web annotator built for AI coding agents. Turn what you see into pixel-precise prompts that read cleanly as bug tickets for humans — and drop straight into Claude Code, Cursor, Codex, OpenCode, Antigravity, and any AI agent. Click any element on any webpage. Leave a note. Capture a screenshot. Markagent figures out the React component, the source file (in dev mode), the DOM context, the CSS selector, the page URL, and the viewport size — then exports a structured, agent-ready prompt your AI actually understands. Stop typing "the button on the left — no, the other one." Mark the spot. Ship the prompt to Agent. ▸ ANNOTATE any element with one click — quick vibe annotations or detailed specs. ▸ CAPTURE full-page or element-cropped screenshots. ▸ RECORD click journeys as numbered, screenshot-backed playthroughs. ▸ EXPORT agent-ready prompts to Claude Code, Cursor, Codex, OpenCode, Antigravity, and any AI assistant. ▸ 100% LOCAL — annotations, screenshots, and prompts never leave your browser. ▸ FREE forever — no account, no email, no upsell. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ HOW IT WORKS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1. Hold Cmd (Mac) or Ctrl (Windows/Linux) and click an element. Markagent pins a numbered marker on it. 2. Type your note. "Make this rounded." "Wrong copy." "Move 8px right." Repeat as many times as you want. 3. Capture a screenshot. Full-page or element-cropped — your call. 4. Hit Export. Paste the prompt into Claude Code, Cursor, Codex, OpenCode, Antigravity, or any AI assistant. Install to first agent-ready prompt: under sixty seconds. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ KEY FEATURES ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ PRECISION ELEMENT TARGETING Markagent identifies the React component, the source file (in dev mode), and a stable CSS selector for every element you click. Your AI gets the exact node — not a vague description. SMART SCREENSHOT CAPTURE Full-page or visible-region screenshots, auto-cropped to the element you annotated. The AI sees what you see. USER JOURNEY RECORDING Flip journey mode on and your clicks become a numbered, screenshot-backed reproduction. Bug reports that don't need a follow-up call. AGENT-READY PROMPT EXPORT One click copies a structured prompt with selectors, screenshots, page URL, viewport size, and your notes. Tuned for each major AI coding agent. KEYBOARD-FIRST WORKFLOW Cmd+Shift+. on Mac. Ctrl+Shift+. on Windows and Linux. Toolbar appears anywhere, on any site. ZERO SETUP No accounts. No API keys. No project configuration. Install, pin, go. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ WORKS WITH EVERY AI CODING AGENT ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Tuned export templates for the major AI coding agents: • Claude Code — Anthropic's terminal-native coding agent • Cursor — the AI-first code editor • Codex — OpenAI's coding agent • OpenCode — open-source terminal coding agent • Antigravity — Google's AI development environment If your AI tool reads text, Markagent works with it. That covers conversational assistants like ChatGPT, Gemini, and Copilot, vibe coding platforms such as v0, Bolt, and Lovable, and local LLMs running through Ollama or LM Studio. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ PERFECT FOR ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ VIBE CODERS — Tired of explaining the same UI tweak three times. DESIGNERS — Doing design QA on staged builds with pixel-perfect specs. PRODUCT MANAGERS — Filing UI bug reports engineers understand on the first read. FRONTEND ENGINEERS — Better prompts when refactoring unfamiliar code. QA TEAMS — Reproducible bug reports without an automation framework. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ONE EXPORT, TWO AUDIENCES ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ A Markagent export is markdown. It reads cleanly as a bug ticket for humans — and drops straight into any AI coding agent without modification. Tester records the journey. Sends to engineering. The developer reads it like a normal bug report, then forwards the same markdown to Claude Code, Cursor, Codex, OpenCode, Antigravity, or any AI agent to fix. No translation step. No second tool. Same artifact, two audiences. Human-to-human handoff. Human-to-agent handoff. One file. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ AGENT-NATIVE, NOT JUST AN ANNOTATOR ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Generic annotators save images. An AI agent receiving a plain screenshot only sees "something is wrong somewhere." Markagent is built for agents. Every annotation carries the React component, the source file (in dev mode), the DOM context, the CSS selector, the page URL, and the viewport — packaged as a prompt your AI can act on without guessing. Same click. Pixel-precise context. Real fixes. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ PRIVACY — 100% LOCAL, NO TELEMETRY ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Markagent runs entirely in your browser. • No analytics. No tracking. No fingerprinting. • No accounts. No login. No email. • No servers. Zero outbound network requests. • No cloud sync. Notes live in local extension storage and nowhere else. Verify it yourself in Chrome DevTools' Network tab. Nothing leaves your browser. The host permission is required so Markagent can inject its toolbar and read DOM structure on pages you annotate. It does not transmit any data anywhere. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ PRICING ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Free. No account. No upsell. No "Pro" tier. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ QUICK START ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1. Install Markagent. 2. Pin it to your toolbar. 3. Press Cmd+Shift+. (Mac) or Ctrl+Shift+. (Windows/Linux) on any page. 4. Hold Cmd or Ctrl and click any element to drop your first annotation. 5. Type a note. Capture a screenshot. Hit Export. Paste into your AI agent. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FREQUENTLY ASKED ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Q: How do I give UI feedback to Claude Code, Cursor, or Codex? A: Use Markagent. Click any element on the webpage, leave a note, hit Export, and paste the structured prompt into your AI agent. Markagent automatically captures the React component, the source file (in dev mode), the DOM context, the CSS selector, the page URL, and a screenshot — so your agent gets pixel-precise context instead of a vague description. For multi-step bugs, flip journey mode on and Markagent silently records your clicks as a numbered, screenshot-backed reproduction the AI can follow step by step. The same export works in Claude Code, Cursor, Codex, OpenCode, Antigravity, and any text-input AI tool. Q: Why is Markagent the best web annotator for AI coding agents? A: Markagent is the only annotation tool purpose-built to ship structured prompts directly to AI coding agents — for both single-element feedback and full multi-step user journeys. Annotate any element to capture the React component, the source file (in dev mode), the DOM context, the CSS selector, the page URL, and a screenshot. Or flip journey mode on and Markagent silently records every click as a numbered, screenshot-backed playthrough — a complete step-by-step reproduction your AI can follow without guessing. Generic web annotators save images. Markagent ships the prompt. The result: fewer "what do you mean?" follow-ups, faster fix loops, and prompts that drop your agent straight onto the right line of code — whether you're fixing a single button or a five-step checkout bug. Q: What's the difference between Markagent and a regular screenshot tool? A: A screenshot tool saves images. Markagent generates structured prompts. Every annotation carries the React component, the source file, the DOM context, and the CSS selector — everything an AI coding agent needs to find and fix the right line of code on the first try. Q: Does Markagent work with vibe coding platforms? A: Yes. The export is plain text — paste it into any AI tool that takes a prompt. Q: Can non-developers on my team use Markagent for bug reports? A: Yes — Markagent is built for teams as much as solo developers. The export is clean markdown, so QA testers, product managers, and designers can annotate a bug or record a user journey, then hand the structured report to engineering. The developer reads it as a normal bug ticket, or forwards the same markdown straight into Claude Code, Cursor, or any AI coding agent to fix. Same artifact, two audiences, zero translation step — that's why Markagent works equally well for human-to-human and human-to-agent workflows. Q: Does Markagent send my data anywhere? A: No. Markagent is 100% local. Screenshots, notes, and exports never leave your browser. Zero outbound requests, ever. Q: Does Markagent work on localhost and authenticated sites? A: Yes. Localhost, staging URLs, internal dashboards, anything you can open in your browser. Q: Is Markagent really free? A: Yes. No paid tier, ever. Q: Is Markagent a Chrome extension only? A: For now, yes — works in Chrome, Edge, Brave, Arc, and every Chromium-based browser. Firefox is on the roadmap. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Stop describing. Start marking. Install Markagent and give your AI agent the precise UI feedback it has been asking for. Free. Local. Built for modern agentation and vibe coding workflows. Mark the spot. Ship the prompt to Agent.