mandu-composition

mandu-composition is a skill for Claude Code, Codex from konamgil/mandu. It costs 48 tokens per session (1,061 once invoked), scanned A, original, MPL-2.0.

A guide to arranging React components in Mandu applications. It covers reusable component parts, shared state, providers, and the boundary between server and browser code.

In plain words
What is it for?
Use it when planning or changing Mandu islands, compound components, shared state, providers, slots, or hydration.
Why use it?
It reduces confusing component structure and helps prevent state or browser-only code from spreading beyond the feature that needs it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/konamgil/mandu/mandu-composition
Any agent
npx skills add konamgil/mandu --skill mandu-composition
Clone the repo
git clone --depth 1 https://github.com/konamgil/mandu

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.

agentmods badge for mandu-composition

README.md
[![agentmods](https://agentmods.dev/badge/skills/konamgil/mandu/mandu-composition.svg)](https://agentmods.dev/skills/konamgil/mandu/mandu-composition)
Your own site
<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-composition"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-composition.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,061 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01061
Opus 5 $0.00024 $0.00531
Sonnet 5 $0.00010 $0.00212
Haiku 4.5 $0.00005 $0.00106

Measured 6d ago against content hash 307b687bb54f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mandu-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 6d 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.

docs/archive/skills/mcp-v0/mandu-composition/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mandu Composition

Mandu 애플리케이션을 위한 React 컴포지션 패턴 가이드. Island 컴파운드 컴포넌트, 상태 관리 인터페이스, Provider 패턴, slot-client 분리를 다룹니다. Vercel의 Composition Patterns를 Mandu 컨텍스트로 변환하여 적용합니다.

Agent Workflow Contract

This skill is a Domain addendum. It must not replace mandu-agent-workflow. Use it only after mandu.agent.plan selects composition, UI, hydration, slot, or component domains.

Canonical workflow step: plan -> apply -> verify.

Preferred MCP tools:

Step Tools
plan mandu.agent.plan, mandu.design.get, mandu.island.list
apply mandu.agent.apply
verify mandu.agent.verify, mandu.design.check, mandu.slot.validate
repair mandu.agent.repair

Allowed file edits:

  • Island/client component files named in the plan
  • Provider/state modules scoped to the target feature
  • Slot-client boundaries only when the plan includes slot or hydration domains

Verification command:

mandu agent verify --changed --json --write

Common failures:

  • Refactoring component APIs without checking island/client boundaries
  • Adding shared state providers broader than the planned feature
  • Mixing slot server logic into client composition files

Repair path:

mandu agent repair --from .mandu/agent-verify.json --json

When to Apply

Reference these guidelines when:

  • Designing Island component architecture
  • Managing shared state between Islands
  • Building reusable component APIs
  • Refactoring components with boolean prop proliferation
  • Working with compound components or context providers

Rule Categories by Priority

Priority Category Impact Prefix
1 Component Architecture HIGH comp-arch-
2 State Management HIGH comp-state-
3 Island Patterns MEDIUM comp-island-
4 Implementation Patterns MEDIUM comp-pattern-

Quick Reference

1. Component Architecture (HIGH)

  • comp-arch-avoid-boolean-props - Use composition instead of boolean customization
  • comp-arch-compound-components - Structure Islands as compound components
  • comp-arch-explicit-variants - Create explicit variant components

Read the full file on GitHub · 132 lines

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. 6d ago First seen · 132 lines · 48 tokens per session scan A 307b687bb54f

Subscribe to this mod's changes

mandu-composition is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 9d ago), licensed MPL-2.0. It adds 48 tokens to every session and 1,061 once invoked, about $0.0002 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

opengeni-sites

Build, inspect, edit, validate, and publish OpenGeni Sites as ordinary Bun + React source projects compiled to one self-contained HTML artifact. Use for interactive pages, dashboards, visualizations, workflows, and focused apps that may call workspace tools through the typed Site bridge.

Cloudgeni-ai/opengeni · 60 tokens

tauri-django-react

Agents should invoke this skill for Tauri + Django + React desktop apps, especially backend lifecycle, CORS/auth, frontend integration, mandatory light/dark theming, German/English i18n, build packaging, dual desktop/web deployment, Rust commands, and platform-specific gotchas.

Firstp1ck/pi-coding-agent-forge · 63 tokens

diceui

Build complex, accessible UI components using DiceUI — combobox, tags-input, sortable, kanban, data-table, file-upload, color-picker, and 40+ more. Use when the user wants to add any DiceUI component, mentions @diceui packages, asks for complex interactive components like combobox, sortable lists, kanban boards…

vobase/vobase · 116 tokens

veryfront

Build Veryfront apps. Use for real-time errors, route preview, HMR control, and scaffolding pages/APIs/components/AI tools.

veryfront/veryfront-code · 32 tokens

next-application-structure

Establishes or reviews directory layout, server/client boundaries, routing, data-fetching strategy, and testing structure for Next.js 14+ App Router TypeScript applications. Invoked when the user asks to structure a Next app, set App Router conventions, or review architecture for React parity.

soulcodex/agentic · 64 tokens

react-application-structure

Establishes or reviews the directory layout, feature boundaries, state design, routing approach, and data-fetching conventions for a React 18+ TypeScript application. Invoked when the user asks to structure a React app, set up a scalable architecture, or review React project organization.

soulcodex/agentic · 63 tokens