preview-design

preview-design is a skill for Claude Code from egregore-labs/egregore. It costs 71 tokens per session (680 once invoked), scanned A, original, MIT.

A tool for rendering a real document, handoff, platform board, or related artifact through the project's local MERIDIAN design code before that design is released.

In plain words
What is it for?
Use it to preview markdown documents, handoff JSON, the project board, or other supported surfaces with the bundled rendering script.
Why use it?
It lets a team inspect how a proposed design convention appears on actual outputs and catch issues before shipping.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths.

Good fit Use it to preview markdown documents, handoff JSON, the project board, or other supported surfaces with the bundled rendering script.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/egregore-labs/egregore/preview-design
Install

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.

Any agent
npx skills add egregore-labs/egregore --skill preview-design
Clone the repo
git clone --depth 1 https://github.com/egregore-labs/egregore

Made for: Claude Code.

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.

agentmods badge for preview-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/egregore-labs/egregore/preview-design/github.svg)](https://agentmods.dev/skills/egregore-labs/egregore/preview-design)
Your own site
<a href="https://agentmods.dev/skills/egregore-labs/egregore/preview-design"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/preview-design/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.

agentmods 80×15 button for preview-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/egregore-labs/egregore/preview-design"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/preview-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 10
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.00680
Opus 5 $0.00036 $0.00340
Sonnet 5 $0.00014 $0.00136
Haiku 4.5 $0.00007 $0.00068

Measured 10d ago against content hash e64dea355678, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

preview-design 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (render.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/preview-design/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Topic: $ARGUMENTS

Preview the Design Convention

Renders a real Egregore artifact through this branch's MERIDIAN render path (packages/egregore-artifacts local code) — deliberately not npx egregore-artifacts, which pulls the published npm 0.10.2 (the OLD design). This is the test vector for Design Convention Round 1: testers see the new design on real output before it merges.

Full protocol: memory/feedback/design-convention-r1/GUIDE.md.

When to invoke

User says: "/preview-design", "preview the design convention", "render with the new design", "let me test the new design on a document / handoff / board", or is running the design-convention round-1 test.

What it does

Run the bundled script — it handles dependency install and routes to the local CLI:

bash skills/preview-design/render.sh <surface> [file]
Surface Command Input
document render.sh document [file.md] any markdown — defaults to a bundled sample
handoff render.sh handoff [file.json] a handoff-v1 JSON — defaults to a bundled sample
platform render.sh platform reads memory/board/board.json (the board view)
emissary render.sh emissary harness-only this round — prints the harness URL and stops

The CLI opens the rendered HTML in the browser. After looking it over, the tester runs the Socratic feedback protocol ("Run the Design Convention feedback protocol").

Why it's built this way

  • Local, never npx. It runs node packages/egregore-artifacts/bin/cli.js, so you always get THIS branch's MERIDIAN design — npm's egregore-artifacts is the old look.
  • Lives in top-level skills/, not .claude/skills/. /update replaces .claude/skills/ wholesale from upstream (git checkout upstream -- .claude/skills/), which would delete an org-local preview command. Top-level skills/ survives.
  • Emissary is excluded on purpose. Its renderer (api/main.py) is server-side and not yet design-system-wired — wiring it is the #1 Round-2 task. For now it's reviewed via the published harness.

Read the full file on GitHub · 56 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 10d ago First seen · 56 lines · 71 tokens per session scan A e64dea355678

Subscribe to this mod's changes

preview-design is a skill published in the GitHub repository egregore-labs/egregore (289 stars, last pushed 6d ago), licensed MIT. It adds 71 tokens to every session and 680 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

diagrams

Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".

anton-abyzov/specweave · 0 tokens

atomic-visual-options

Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by…

damusix/atomic-claude · 150 tokens

ppt-orchestrator

A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.

huangrichao2020/pretty-skills · 160 tokens

zhongguose-html-skill

An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.

huangrichao2020/pretty-skills · 232 tokens

storyboard-generation

Rules and prompts for generating structured presentation slides and multi-panel storyboards.

alecs5am/ralphy · 18 tokens

ui-design

This skill should be used when the user asks to "design a component", "pick colors", "improve typography", "fix spacing", "choose a layout", or discusses visual design, CSS, styling decisions, or responsive interfaces. Provides patterns for typography scales, color systems, spacing, and production-grade UI design.

dean0x/devflow · 67 tokens