A tool for creating visual or interactive artifacts with code, such as charts, dashboards, diagrams, planners, simulations, small games, and polished web pages.

It is for building browser-based visual explanations, interactive calculators, trackers, maps, and other compositions when a visual communicates better than text or a table.

It helps present relationships, processes, comparisons, or calculations in a form that can be inspected or manipulated more easily than prose.

composition — Skill for Claude Code and Codex by lvndry/jazz

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 lvndry/jazz --skill composition

Clone the repo

git clone --depth 1 https://github.com/lvndry/jazz

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lvndry/jazz/composition/github.svg)](https://agentmods.dev/skills/lvndry/jazz/composition)

Your own site

<a href="https://agentmods.dev/skills/lvndry/jazz/composition"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/composition/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lvndry/jazz/composition"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/composition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,112 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.

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 5.1	$0.00051	$0.02112
Opus 5.5	$0.00020	$0.00845
Sonnet 5.5	$0.00010	$0.00422
Haiku 4.5	$0.00005	$0.00211

Measured 1mo ago against content hash 26200836343d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

composition 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 1mo 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.

skills/composition/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Composition

Create a useful, distinctive visual artifact with create_composition. The agent writes the complete HTML; the tool saves it and optionally renders a PNG. Local interactive sessions open the result in the browser; chat surfaces deliver an image or a link when supported.

Design the artifact

Start with what the person should understand or do, and choose the visual form that serves it. A chart, diagram, calculator, editorial page, or deck may be better than a dashboard. Make the primary insight or action easy to find. For a single fact or a short list, use prose or a table when that is clearer.

Compositions have no house style. Choose typography, palette, layout, density, shape, imagery, and motion for this artifact and its audience. Honor the user's references and any existing product design. Use a consistent visual system throughout the result, with tokens defined for the design you actually chose.

UI resources

Use real design references to inform the work. These are starting points, not a required sequence; browse what helps the task and follow useful links to other resources. Don't load every source or combine incompatible visual treatments.

Refero Styles — product design references with screenshots and AI-readable DESIGN.md material. Study a relevant style's layout, type, spacing, surfaces, and components, rather than borrowing only its accent color.
21st.dev — community components and page sections for implementation ideas and visual detail. Inspect a relevant component's structure, interactions, and dependencies before adapting it to the composition.
Component Gallery — component examples from established design systems. Use it to compare how a control works, including its states and information hierarchy.
Kinetics — motion examples and recipes when animation helps feedback, navigation, or the experience.
Impeccable — design guidance and critique for improving hierarchy, typography, color, layout, and finishing details.

Read the full file on GitHub · 164 lines

Files

What ships with it

4 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.

1mo ago Changed · -46 lines · -37 tokens per session 26200836343d
1mo ago Changed · +92 lines ad94ccaf7306
1mo ago First seen · 118 lines · 88 tokens per session scan A 57bc54a2b2e9

Subscribe to this mod's changes

composition is a skill published in the GitHub repository lvndry/jazz (55 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 2,112 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-22.

CSS and styling Design and UX Frontend LLM agent ai automation cli effect-ts

composition next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
compositionlvndry/jazz	Skill	55	today	MIT	A	51	Claude Code, Codex
web-designPrism-Shadow/penguin-harness	Skill	3.2k	today	Apache-2.0	A	51	Claude Code, Codex
schematicssynthetic-sciences/openscience	Skill	4.4k	yesterday	Apache-2.0	A	134	Claude Code
ui-craftMemTensor/memmy-agent	Skill	2.2k	yesterday	MIT	A	86	Claude Code, Codex
proceed-videoniki914/zafiro	Skill	364	3d ago	MIT	A	78	Claude Code, Codex
vibe-ui-methodologyhuangrichao2020/pretty-skills	Skill	55	yesterday	MIT	A	401	Claude Code, Codex
design-skillOverbrilliant/ob-1	Skill	30	18d ago	Apache-2.0	A	82	Claude Code, Codex