marco-code-style

marco-code-style is a skill for Claude Code, Codex from tonyghiani/ai-essentials. It costs 86 tokens per session (3,690 once invoked), scanned A, original, MIT.

A written set of TypeScript and React coding rules based on one developer’s code and stated preferences. It covers code structure, components, hooks, types, server code, and tests.

In plain words
What is it for?
Use it before writing or reviewing substantial TypeScript or React code, creating modules, writing tests, or resolving style disagreements.
Why use it?
It gives an agent consistent guidance for matching that developer’s style, while noting that existing project rules and nearby code take priority.

Skill for Claude CodeCodex

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/tonyghiani/ai-essentials/marco-code-style
Any agent
npx skills add tonyghiani/ai-essentials --skill marco-code-style
Clone the repo
git clone --depth 1 https://github.com/tonyghiani/ai-essentials

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 marco-code-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/tonyghiani/ai-essentials/marco-code-style.svg)](https://agentmods.dev/skills/tonyghiani/ai-essentials/marco-code-style)
Your own site
<a href="https://agentmods.dev/skills/tonyghiani/ai-essentials/marco-code-style"><img src="https://agentmods.dev/badge/skills/tonyghiani/ai-essentials/marco-code-style.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,690 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00086 $0.03690
Opus 5 $0.00043 $0.01845
Sonnet 5 $0.00017 $0.00738
Haiku 4.5 $0.00009 $0.00369

Measured 5d ago against content hash 41cab1aecb85, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

marco-code-style scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`queryFn: ({ signal }: QueryFunctionContext) => client.fetch(endpoint, { signal: signal ?? null })`.
skills/marco-code-style/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Marco's code style

Observed conventions, then confirmed. Every rule below came from reading 748 commits Marco authored, cross-checked by author-frequency per file, and then put to him directly in a 69-question interview covering naming, control flow, typing, React, state, server patterns, structure, comments, and tests.

Precedence. Project conventions win when they conflict with this file. Read the neighbouring files first. Where project documentation states a rule Marco's own code contradicts, follow the surrounding file, and follow this file for new modules he owns.

Scope. Mechanical rules (formatting, import order, casing, banned syntax) are lint config, not guidance; they live in eslint-recommendations.md in the ai-essentials repo. Cursor consumes the same material as file-scoped rules in rules/typescript-style.mdc, rules/react-components.mdc, rules/node-api-patterns.mdc, rules/testing-style.mdc, and rules/project-structure.mdc.

Where his stated preference overrides his existing code

Read these first. Following the code instead of the preference is the most likely way to get it wrong.

Rule His code His answer
Type name prefixes no prefixes in Kibana (58 declarations) I on interfaces, T on type aliases
Props interface inline object type under ~4 props always a named interface IXProps
Guard braces 12 brace-less single-line guards always braces
Imperative loops 24 for…of for sequencing declarative by default; imperative is a performance escape hatch
Abort signals threaded through every call only long-running or user-cancellable requests
Destructured params past ~2 arguments past 1 argument, and always once one is optional

Components

// Default form.
export function SignificantEventsPage({ tab, onTabChange }: ISignificantEventsPageProps) {
  // ...
}

// Arrow-const only for a one-expression wrapper.
export const AppHeader = (props: IAppHeaderProps) => <PageHeader {...props} />;

Read the full file on GitHub · 237 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. 5d ago First seen · 237 lines · 86 tokens per session scan A 41cab1aecb85

Subscribe to this mod's changes

marco-code-style is a skill published in the GitHub repository tonyghiani/ai-essentials (6 stars, last pushed 27d ago), licensed MIT. It adds 86 tokens to every session and 3,690 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

client-setup

Create a vanilla tRPC client with createTRPCClient (), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.

trpc/trpc · 63 tokens

adapter-express

Mount tRPC as Express middleware with createExpressMiddleware() from @trpc/server/adapters/express. Access Express req/res in createContext via CreateExpressContextOptions. Mount at a path prefix like app.use('/trpc', ...). Avoid global express.json() conflicting with tRPC body parsing for FormData.

trpc/trpc · 67 tokens

trpc-router

Entry point for all tRPC skills. Decision tree routing by task: initTRPC.create(), t.router(), t.procedure, createTRPCClient, adapters, subscriptions, React Query, Next.js, links, middleware, validators, error handling, caching, FormData.

trpc/trpc · 59 tokens

frontend-conventions

Coding conventions, architecture patterns, and testing rules for the SkillHub React frontend. Ensures agents follow Feature-Sliced Design and use the generated OpenAPI types.

iflytek/skillhub · 36 tokens

frontend-dev-guidelines

Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features…

diet103/claude-code-infrastructure-showcase · 76 tokens

fast-typescript-check

Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…

internet-development/www-sacred · 84 tokens