claude-react-kit CLAUDE.md

claude-react-kit CLAUDE.md is an instructions file for coding agents from wahmoh/claude-react-kit. It costs 575 tokens per session, scanned A, original, MIT.

Development rules for a React and TypeScript application organized into layers, such as pages, features, shared code, interface components, and core infrastructure. They also list commands for checking types, style, tests, and production builds.

In plain words
What is it for?
Use them when adding or changing React components, deciding where code belongs, enforcing import boundaries, and running the project’s type checks, linting, tests, and build.
Why use it?
They keep responsibilities separated: for example, pages fetch data, components display it, and features do not depend directly on one another. This makes changes easier to check and reduces accidental coupling.

Instructions file

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 instructions/wahmoh/claude-react-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/wahmoh/claude-react-kit

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 claude-react-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wahmoh/claude-react-kit/claude-md.svg)](https://agentmods.dev/instructions/wahmoh/claude-react-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wahmoh/claude-react-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/wahmoh/claude-react-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 575 This file is loaded in full into every session.
When invoked 575 The same file — it is already loaded in full.
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 $0.00575 $0.00575
Opus 5 $0.00287 $0.00287
Sonnet 5 $0.00115 $0.00115
Haiku 4.5 $0.00057 $0.00057

Measured 3d ago against content hash a1f67dd0b4eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-react-kit CLAUDE.md 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Commands

# Replace these with your project's actual commands
npm run type-check     # TypeScript verification
npm run lint           # Linting (zero warnings allowed)
npm run test           # Run tests
npm run build          # Production build

Architecture — MANDATORY

This project follows a layered architecture with strict import boundaries:

app/pages/routes/  →  src/features/  →  src/shared/  →  src/design-system/  →  src/core/
      ↓                    ↓                 ↓                  ↓                   ↓
  Data fetching      Feature UI +      Cross-feature       UI primitives      App infra
  Route handling     domain logic      reusables           (tokens, atoms)    (auth, net, i18n)

Import rules (NEVER violate):

  • Features NEVER import from other features
  • core/ has ZERO business domain awareness
  • Components NEVER fetch data — they receive it via props
  • Pages/routes are the ONLY place for data fetching

See @.claude/rules/architecture.md for full layer definitions.

Component Rules

  • Single responsibility: one component = one job
  • Target < 100 lines, hard max 200 lines (split into subfolder)
  • Functions: max 20 lines, max 3 parameters
  • Use guard clauses (early returns) over nested conditionals

Naming Conventions

Item Convention Example
Component folders PascalCase UserProfile/
Infrastructure folders lowercase/kebab-case hooks/, shared/services/
Component files PascalCase.tsx UserCard.tsx
Hook files camelCase.ts useUserData.ts
Type/const files camelCase.ts userTypes.ts
Booleans is/has/can/should prefix isLoading, hasError
Handlers handle + Subject + Action handleFormSubmit

TypeScript

  • NEVER use any — use proper types or unknown
  • Use interface for objects, type for unions/primitives
  • Always handle null/undefined explicitly

Before Finishing Any Task

  1. Run type-check: npm run type-check
  2. Verify zero new errors introduced
  3. Confirm no cross-feature imports were added

Read the full file on GitHub · 70 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. 3d ago First seen · 70 lines · 575 tokens per session scan A a1f67dd0b4eb

Subscribe to this mod's changes

claude-react-kit CLAUDE.md is an instructions file published in the GitHub repository wahmoh/claude-react-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 575 tokens to every session, about $0.0029 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 2026-08-31.

Related

Other instructions, from other repositories