lavish-axi

For when a rich editor is not rich enough.

HTML is the new markdown. Lavish is the new editor for your HTML artifacts.

Agents are good at producing rich HTML artifacts, but the human-agent collaboration loop on such artifacts is lacking and falls back into screenshots and long responses for “tell me what to change.” That loses the thing HTML is best at: interactivity.

Lavish Editor opens agent-generated HTML files in a local browser, lets you pinpoint elements, selected text, or Mermaid diagram nodes and send feedback to the agent to address.

• Local-first - Review local HTML artifacts with a local CLI and no cloud dependency in the core feedback loop; hosted sharing through third-party ht-ml.app is explicit and opt-in.
• Human-AI collaboration - Annotate elements, selected text ranges, and Mermaid diagram nodes, and send messages to the agent without leaving Lavish Editor.
• Battery included - Lavish Editor teaches your agent good visualization for common use cases such as product or technical plans, design explorations and more out of the box.

Lavish Editor is an AXI, which means -

• It's just a CLI any capable agent can run without setup.
• It's optimized for agent ergonomics. TOON output, long polling, and contextual disclosure making it highly token efficient.
• The skill and hooks below only handle discovery; agents learn to use the AXI by using it.

Quick Start

Install the Lavish skill in the Agent Skills format with npx skills:

npx skills add kunchenguid/lavish-axi --skill lavish

That is the entire setup - no npm install needed. The skill teaches your agent to run Lavish through npx -y lavish-axi, so the CLI comes along on demand. Its frontmatter also includes Hermes Agent metadata, so Hermes-compatible harnesses can categorize and surface it as a first-class productivity skill. This installs the public lavish skill. The repository also contains an internal lavish-design brand skill for maintainers; default npx skills add ... --list and skills.sh discovery hide it unless INSTALL_INTERNAL_SKILLS=1 is set.

Then, in agents that expose skills as slash commands (Claude Code, for example), invoke it directly:

/lavish let's discuss our plan here

Or just ask for anything that is easier to grasp visually - a plan, comparison, diagram, table, code view, or report - and the agent loads the skill on its own when it recognizes the task.

By default the skill lands in the current project's skills directory (.claude/skills/, for example); add -g to install it for all projects (~/.claude/skills/).

Other Ways to Use Lavish

The skill is the recommended path, but it is not the only one.

Zero setup

Lavish is an AXI, so any capable agent can run the CLI directly with nothing installed at all. Just tell your agent:

Use `npx lavish-axi` to write a product or technical plan for what we discussed.

Session hook

Want Lavish's ambient context - including your live open sessions - fed into every agent session instead of loading on demand? Install the CLI globally and opt into the hook:

npm install -g lavish-axi
lavish-axi setup hooks

This installs a SessionStart hook for Claude Code, Codex, OpenCode, and GitHub Copilot CLI that surfaces open sessions, visualization playbooks, and usage guidance at the start of each session. Unlike the skill, the hook also shows your live open sessions, so a fresh agent session can resume an in-flight review. Restart your agent session after running this so the new hook takes effect.

From source

git clone https://github.com/kunchenguid/lavish-axi.git
cd lavish-axi
pnpm install --frozen-lockfile
pnpm run build
pnpm link

How It Works

┌───────────────┐
│ Agent writes  │
│ artifact.html │
└───────┬───────┘
        ▼
┌────────────────────────┐
│ lavish-axi <file_path> │
│ opens local browser UI │
└───────┬────────────────┘
        ▼
┌────────────────────────┐
│ Human annotates text   │
│ or elements, sends     │
│ chat, or browser audit │
│ reports layout issues  │
└───────┬────────────────┘
        ▼
┌────────────────────────┐
│ lavish-axi poll waits  │
│ and returns prompts    │
│ or layout warnings     │
└────────────────────────┘

• File-path identity - Sessions are keyed by the canonical HTML file path, so agents do not need opaque IDs.
• Portable artifacts - The artifact runs in an iframe while Lavish injects a small SDK for annotations, snapshots, feedback controls, and render-time layout checks. Lavish does not inject any design system, so the saved HTML file renders identically whether you open it through lavish-axi or directly in a browser. Before writing HTML, choose a design system in strict priority order: follow a user-requested look first; otherwise inspect the project the artifact is about - the subject or product whose content or UI it represents, which may differ from your current working directory - and match that project's Tailwind or theme config, CSS variables or design tokens, component library, brand assets, or existing styled pages. If the artifact previews, proposes, or mocks a specific app's UI, render it in that app's own design system so it faithfully shows the product, even when you are running in a different repo. Only when both come up empty, run lavish-axi design for a copy-pasteable Tailwind CSS v4 + DaisyUI v5 CDN fallback, a content-to-playbook router, and Mermaid diagram tooling. That fallback guidance recommends DaisyUI's luxury theme by default, warns not to @apply DaisyUI classes inside Tailwind browser-runtime style blocks, includes an optional layout safety CSS snippet for dense nested grid/flex layouts, and provides a pinned Mermaid CDN snippet with initialization for flows, architecture, state, and sequence diagrams.
• Open-time layout gate - The browser chrome masks each artifact until the real in-iframe layout audit reports no error-severity findings. Warning-only artifacts reveal normally; error findings notify the agent through the same layout_warnings poll path and keep the curtain up until a clean reload. The user can click Show anyway, and a bounded safety timeout reveals with a persistent layout-issues banner so review is never blocked indefinitely.
• Layout warnings - After fonts load and layout settles, the injected SDK audits the real browser render for page horizontal overflow, element overflow, clipped or visibly spilling text, and overlapping text. Intentional horizontal scrollers using overflow-x: auto or scroll are excluded from horizontal checks, and overflow-y: auto or scroll is treated as intentional for vertical overflow. Current findings are returned from lavish-axi poll as layout_warnings with selector, kind, overflowPx, viewportWidth, severity, and persistent. Fresh error-severity findings should be fixed and rechecked before asking the human to review; repeated or warning-only findings can be surfaced to the human with a note when the cause is not obvious.
• Local assets - Copy local images, CSS, fonts, and scripts next to the HTML artifact and reference them with relative paths from that directory; root-prefixed paths such as /assets/logo.png will not resolve through Lavish's artifact route.
• Export and sharing - lavish-axi export writes <name>.export.html by inlining local assets only, stripping the annotation SDK, and leaving remote CDN/font references as links that still need network access. lavish-axi share publishes the same local-inlined HTML to ht-ml.app, a third-party hosting service not part of Lavish. Publishing sends the artifact to ht-ml.app's servers, public by default, or private and password-protected with --password; the response includes a secret update_key shown once for later management. Bundling never fetches remote URLs, Lavish itself does not set a CSP, local reads stay confined and size-capped, and absolute file:// paths outside safe inlined asset references are redacted before output. Per-asset and per-bundle inline caps default to 10 MB and 25 MB, overridable with LAVISH_AXI_EXPORT_MAX_ASSET_BYTES and LAVISH_AXI_EXPORT_MAX_BUNDLE_BYTES. Unresolved local assets or export notices such as author-set CSP meta tags and redacted file URLs are surfaced in command or browser output. Use --token or LAVISH_AXI_HTML_APP_TOKEN for an optional bearer token; set LAVISH_AXI_HTML_APP_API_URL only when overriding the ht-ml.app API base.
• Live reload - Lavish watches the HTML artifact file by default and preserves the artifact iframe scroll position across reloads. To also reload on sibling asset changes, add data-lavish-live-reload-root to the root element or <meta name="lavish-live-reload" content="root">.
• Feedback controls - Native controls (radios, checkboxes, inputs, selects, buttons, labels, disclosure summaries, contenteditable) are interactive automatically, so they do not need data-lavish-action. For reversible choices, let option clicks update local state, then queue exactly one final answer from a per-question submit or Queue answer button with window.lavish.queuePrompt(). Mark only custom (non-native) clickable elements with data-lavish-action so Lavish does not annotate them, and use data-lavish-question or queueKey when pre-send updates for the same question should replace each other. Queued annotation preview pills and chat history share a scrollable Conversation panel above a sticky composer, so long feedback queues do not push the text box or send controls off screen. The browser chrome keeps editing actions in the overflow menu (copy path, reload artifact, copy DOM snapshot, export standalone HTML, publish link, end session), while the composer exposes Send & End beside Send to Agent to submit queued prompts and user-ended attribution together.
• Keyboard shortcuts - In the chrome composer, Enter sends queued prompts and Shift+Enter inserts a newline. In the annotation card, Enter queues the annotation, Shift+Enter inserts a newline, and Ctrl+Enter (Cmd+Enter on macOS) queues it and sends all queued prompts immediately. Cmd+I or Ctrl+I toggles between annotate and explore mode from either the browser chrome or the artifact iframe, including while focus is in a textarea or control.
• Agent presence - The browser shows when no agent is listening, keeps queued feedback and fresh layout warnings for the next successful lavish-axi poll send even across reloads, and only blocks human sends while the agent is working on delivered feedback. The no-timeout poll writes an immediate stderr banner and periodic stderr heartbeats while stdout stays reserved for the final response; if the poll is interrupted or times out, re-run it because queued feedback is never lost.
• Session end etiquette - Lavish tracks who ended a session: a human clicking End session (or Send & End) in the browser is a user-initiated end, while lavish-axi end <html-file> is agent-initiated. A plain lavish-axi <html-file> after a user-initiated end refuses to reopen the browser and returns guidance instead; pass --reopen only when the user asks for further review or something important needs their visual attention. Agent-initiated ends keep reopening normally, same as before. lavish-axi poll's ended response and the feedback response for the final batch before an end both carry next_step guidance telling the agent to stop polling and deliver remaining updates in chat instead of reopening.
• Precise targets - Text annotations include selected text plus range anchors, so agents are not limited to whole-element selectors.
• Mermaid diagrams - Rendered Mermaid diagrams become pannable and zoomable while you explore (drag to pan, scroll to zoom) and freeze when you turn on annotation so a click lands on a single node. Clicking a node annotates the whole node and sends the agent its diagram id, node id, and rendered label instead of just a CSS selector. Lavish only enhances the live render, so the saved HTML still opens identically anywhere.
• Server cleanup - The detached server stops after the last session ends when nothing is connected, or after LAVISH_AXI_IDLE_TIMEOUT_MS (default 30 minutes) with no browser or poll connections. Set LAVISH_AXI_IDLE_TIMEOUT_MS=0 or off to disable idle self-shutdown.
• Local-first state - Session state stays under ~/.lavish-axi/ by default, or LAVISH_AXI_STATE_DIR when set.
• Network binding - The server binds to loopback (127.0.0.1) by default. Set LAVISH_AXI_HOST to bind elsewhere; a wildcard (0.0.0.0 or ::) binds every interface. Binding beyond loopback exposes an unauthenticated server that can read and serve arbitrary local files to anything that can reach it, so only do so on a trusted network. Set LAVISH_AXI_LINK_HOST to control the hostname written into generated session links (defaults to the bind address, or loopback when bound to a wildcard).

CLI Reference