A tool and file format for creating editable visual designs such as posters, slides, flyers, books, diagrams, charts, and ads from plain-text .zen documents. The Zenith command-line tool validates the document and renders it to PNG or PDF.

Use it to author deterministic designs, inspect their geometry and styles, validate documents, manage design tokens and fonts, and create image or print outputs.

It keeps the design as structured source code that can be edited, reviewed, compared, and rendered again instead of being only a flat image.

zenith — Skill by zenitheditor

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.

agentmods

npx agentmods add skills/zenitheditor/zenith/skill

Any agent

npx skills add zenitheditor/zenith --skill skill

Clone the repo

git clone --depth 1 https://github.com/zenitheditor/zenith

Made for: Claude Code, Codex.

Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,202 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00197	$0.03202
Opus 5	$0.00098	$0.01601
Sonnet 5	$0.00039	$0.00640
Haiku 4.5	$0.00020	$0.00320

Measured 2d ago against content hash 275d3913703d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

zenith 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.

zenith-cli/assets/skill/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zenith

Plain-text .zen source (KDL) → validate → render to pixel-exact PNG or print PDF. Editable, addressable, deterministic. Drive it with the zenith CLI — not an image model.

Use for posters, decks, social, flyers, diagrams, charts, ads, variants — source you can diff and re-render. Don't use for photographic pictures (generate elsewhere, place as image), pure code tasks, or in-place raster editing.

CLI is the source of truth

Do not invent attribute names or op fields:

zenith --version                  # missing? https://github.com/zenitheditor/zenith#install
zenith --help · zenith <cmd> --help
zenith schema nodes | ops | tokens
zenith schema node <kind> · zenith schema op <name> · zenith schema token <type>
zenith validate <file> --json
zenith inspect <file> --json      # geometry + role facts for critique
zenith inspect path <file> <id> --json   # path topology + extrema bounds (+ --craft)
zenith tokens <file>              # palette/type already on the document
zenith library list               # every embedded + project pack
zenith fonts                      # Bundled (portable) vs Local
zenith fonts features "Noto Sans" --json # OT feature tags for a face
zenith fonts alternates "Noto Sans" --char A --json

If zenith is missing, give the one-line installer from the repo README — do not fake a workflow. This skill is judgment + routing. Syntax lives in zenith schema.

Core loop

Match the brief → canvas + primitives (By brief below; details in references/by-kind.md).
Tokens first. Project brand (.zenith/brand.md / libraries/*.zen) → else zenith new <path> --theme <name>. Only invent a palette when neither fits.
Author. Scaffold with zenith new (don't hand-write the outer skeleton). Prefer zenith tx for later edits (dry-run by default). KDL: one node per line (or \); booleans #true / #false.
Validate. zenith validate <file> --json after every change. Never finalize with Errors.
Render and look. zenith render <file> --png out.png (or --all-pages / --pdf), then open the PNG. Clean validate ≠ good design. Critique: references/design-critique.md + inspect --json.
Report briefly: ids/tokens changed, validate result, output path.

Read the full file on GitHub · 180 lines

Files

What ships with it

25 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.

2d ago First seen · 180 lines · 197 tokens per session scan A 275d3913703d

Subscribe to this mod's changes

zenith is a skill published in the GitHub repository zenitheditor/zenith (22 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 197 tokens to every session and 3,202 once invoked, about $0.0010 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.

Data and AI Documents Planning cli design kdl mcp mcp-server model-context-protocol

ship-quality-gate

Run the deterministic auditors over a real project before it ships — design drift, security headers, generated-default tells, SEO/GEO signals, delivery signals, Apple project configuration — and read the results correctly, disclosure list included. Use when someone asks "audit this", "is this ready to ship", "check…

HalidSaglam/saglitzdesign-mcp · 84 tokens

apple-platform-design

Design iOS, iPadOS, and macOS apps that feel native, in the Liquid Glass era. Use when building or reviewing Apple-platform UI — navigation, controls, sheets, materials, typography, haptics — or deciding what must change when porting from web/Android. Covers Apple's HIG, the Liquid Glass design language (iOS 26 /…

HalidSaglam/saglitzdesign-mcp · 95 tokens

clean-interface-design

Design clean, calm, uncluttered interfaces that don't read as templated AI output. Use when building or restyling any UI (web, iOS, Android, macOS) and it needs visual hierarchy, restraint, spacing discipline, one clear primary action, and a cohesive look. Covers accent color, whitespace, corner radius, type scale…

HalidSaglam/saglitzdesign-mcp · 95 tokens

design-review

Critique a UI (screenshot, live page, or code) like a rigorous senior designer — grounded, reproducible, element-citing, and ranked by severity. Use when someone asks "review this design", "what's wrong with this screen", or wants feedback on a mockup/site/app. Avoids the failure modes of typical AI critique…

HalidSaglam/saglitzdesign-mcp · 92 tokens

design-system-audit

Find out whether a codebase actually has a design system or is re-deciding the basics on every screen — count the distinct colors, sizes, radii, shadows and spacings, collapse the near-duplicates, and migrate onto tokens. Use when inheriting a codebase, before a redesign, when a UI "feels inconsistent but I can't say…

HalidSaglam/saglitzdesign-mcp · 93 tokens

landing-page-conversion

Build or improve landing pages and marketing sites that convert, not just look good. Use when writing a hero, structuring a page, choosing a CTA, adding social proof, or diagnosing why a page isn't converting. Covers positioning, copy-first workflow, the above-the-fold contract, page narrative, CTAs, trust, and…

HalidSaglam/saglitzdesign-mcp · 86 tokens