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.
npx skills add itallstartedwithaidea/agent-skills --skill composition-patternsgit clone --depth 1 https://github.com/itallstartedwithaidea/agent-skillsWrote 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.
[](https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/composition-patterns)<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/composition-patterns"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/composition-patterns/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.
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/composition-patterns"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/composition-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.01217 |
| Opus 5.5 | $0.00014 | $0.00487 |
| Sonnet 5.5 | $0.00007 | $0.00243 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
composition-patterns 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composition Patterns
Part of Agent Skills™ by googleadsagent.ai™
Description
Composition Patterns teaches agents to build flexible, maintainable React components using compound components, state lifting, internal composition, and the elimination of boolean prop proliferation. These patterns replace rigid, prop-heavy APIs with composable interfaces that scale gracefully as requirements evolve.
The most common agent mistake in React is building monolithic components with dozens of boolean props: showHeader, showFooter, isCompact, isLoading, hasSearch, enableDarkMode. Each boolean doubles the component's state space, creating an exponential testing surface and making the component impossible to extend without modifying its internals. Composition patterns replace these booleans with structural composition, where the consumer assembles the component from smaller pieces.
This skill addresses four complementary patterns: compound components for related UI families, state lifting for shared cross-component state, internal composition for encapsulated sub-rendering, and render delegation for maximum consumer flexibility. Applied together, these patterns produce components that are simple to use, powerful to customize, and trivial to test.
Use When
- A component has more than 3 boolean configuration props
- Related components need to share implicit state (tabs, accordions, selects)
- The consumer needs to control layout or ordering of sub-elements
- A component needs to support use cases not anticipated at design time
- Refactoring a "god component" into composable pieces
- Building a component library or design system
How It Works
graph TD
A[Component Design Request] --> B{Pattern Selection}
B --> C[Compound: Related UI Family]
B --> D[State Lifting: Shared State]
B --> E[Internal Composition: Sub-render]
B --> F[Render Delegation: Consumer Control]
C --> G[Parent provides context]
G --> H[Children consume context]
D --> I[State lives in nearest common ancestor]
E --> J[Component composes internally]
F --> K[Consumer passes render function]
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 First seen · 153 lines · 34 tokens per session scan A 5798c363e0f2
composition-patterns is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (44 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 1,217 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
widget-authoring
Author or edit ThinkEx widgets, which are self-contained interactive HTML blocks inside documents. Use when the user explicitly asks for a widget, asks for interaction or live computation, or wants a document visual that ordinary blocks cannot express.
front-vitest
Depth for Vitest tests of front- React 19 SPAs when DOM, RTL, TanStack Query hooks, or TanStack Router route-tree tests are needed. USE WHEN: adding jsdom or testing-library, writing tsx render or renderHook tests, testing createMemoryHistory plus RouterProvider, Suspense UI, or React 19 act fixtures. DO NOT USE WHEN…
multiworker-workflow
Repo-root commands, typegen and typecheck cadence, lint, deploy, adding packages with bun, and Alchemy app layout. Use at the start of a task, before PR, or when choosing turbo/typegen commands.
turborepo
Turborepo task configuration patterns for monorepo management. Use when configuring turbo.json tasks, setting up task dependencies, managing cache inputs/outputs, or working with cross-package dependencies in the monorepo.
workers-env-local
Alchemy + env files — repo-root .env.local (dev), .env.staging (staging / PR preview deploys), .env.production (prod / CI), optional per-package .env.local, and package-local Alchemy apps. Use when adding secrets or non-secret vars (must also update turbo.json globalEnv + deploy workflow env maps), or debugging…
creating-skills
Guide for creating new Agent Skills when patterns emerge or improvements are needed. Use when encountering repeated patterns, making the same mistakes, discovering better approaches, or receiving user corrections. Covers keeping each skill small (one topic), when to split SKILL.md or add references/, and line-count…