agentmods.dev

open-carrusel: Instructions file for Claude Code

CLAUDE.md

open-carrusel CLAUDE.md is an instructions file for Claude Code from Hainrixz/open-carrusel. It costs 770 tokens per session, scanned A, original, MIT.

Repository instructions for Open Carrusel, an AI tool for building Instagram carousels. They describe its React and Next.js structure, chat-based agent, JSON storage, slide rendering, image export, and API routes.

In plain words
What is it for?
Use them when working on chat, carousel and slide editing, previews, PNG export, data storage, or API routes.
Why use it?
They show how the main parts fit together, so changes can preserve the shared rendering and storage behavior. This is useful when debugging or extending the application.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Hainrixz/open-carrusel's own configuration. It tells Claude Code how to work on open-carrusel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-carrusel configures →

not rated 446repo +2 4mo ago A scan 770 tokens original MIT
View source ↗ Hainrixz/open-carrusel
Reuse

Borrowing it

Nothing to install: this file belongs to Hainrixz/open-carrusel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Hainrixz/open-carrusel/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Hainrixz/open-carrusel

Made for: Claude Code.

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 open-carrusel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hainrixz/open-carrusel/claude-md/github.svg)](https://agentmods.dev/instructions/hainrixz/open-carrusel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hainrixz/open-carrusel/claude-md"><img src="https://agentmods.dev/badge/instructions/hainrixz/open-carrusel/claude-md/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.

agentmods 80×15 button for open-carrusel CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hainrixz/open-carrusel/claude-md"><img src="https://agentmods.dev/badge/instructions/hainrixz/open-carrusel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 770 This file is loaded in full into every session.
When invoked 770 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00770 $0.00770
Opus 5 $0.00385 $0.00385
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 10d ago against content hash 7d84a8637b5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

open-carrusel CLAUDE.md 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 10d 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.

- The Claude subprocess gets `--allowedTools Bash WebFetch` and uses curl to call local API routes
CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Carrusel

AI-powered Instagram carousel builder. Next.js 16 + React 19 + TypeScript + Tailwind v4.

Architecture

  • Frontend: React app at localhost:3000 with chat panel (left), carousel preview (center), slide filmstrip (bottom)
  • AI Agent: Claude CLI spawned as subprocess via /api/chat, communicates through SSE streaming
  • Storage: JSON files in /data/ with async-mutex locking and atomic writes
  • Export: Puppeteer screenshots HTML slides to PNG at exact Instagram dimensions
  • Slides: Full HTML documents rendered in sandboxed iframes. wrapSlideHtml() in src/lib/slide-html.ts is the shared rendering contract between preview and export.

Key Files

  • src/lib/chat-system-prompt.ts — Dynamic system prompt (injects brand config + carousel context)
  • src/lib/slide-html.ts — wrapSlideHtml() wraps slide body HTML into full documents
  • src/lib/data.ts — JSON storage with proper async-mutex and atomic writes
  • src/lib/carousels.ts — Carousel and slide CRUD with version history
  • src/lib/claude-path.ts — Portable Claude CLI discovery

API Routes

All at localhost:3000:

  • POST /api/chat — Claude CLI subprocess + SSE streaming
  • GET/POST /api/carousels — List/create carousels
  • GET/PUT/DELETE /api/carousels/[id] — Single carousel
  • POST /api/carousels/[id]/slides — Add slide
  • PUT/DELETE /api/carousels/[id]/slides/[slideId] — Update/delete slide
  • PUT /api/carousels/[id]/slides — Reorder slides (body: { slideIds: [...] })
  • POST /api/carousels/[id]/slides/[slideId]/undo — Undo slide change
  • POST /api/carousels/[id]/export — Export all slides to PNG ZIP
  • GET/PUT /api/brand — Brand configuration
  • GET/POST /api/templates — Templates
  • POST /api/upload — Image upload (PNG/JPG/WebP only, max 10MB)
  • GET /api/fonts — Google Fonts list

Conventions

  • Components max ~300 lines per file
  • Use cn() from src/lib/utils.ts for class merging
  • Types in src/types/, libs in src/lib/, components in src/components/
  • All data mutations go through src/lib/data.ts (never direct fs writes for JSON)
  • iframe slides always use sandbox="" attribute (no JavaScript execution)
  • The Claude subprocess gets --allowedTools Bash WebFetch and uses curl to call local API routes

Read the full file on GitHub · 63 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. 10d ago First seen · 63 lines · 770 tokens per session scan A 7d84a8637b5f

Subscribe to this mod's changes

open-carrusel CLAUDE.md is an instructions file published in the GitHub repository Hainrixz/open-carrusel (446 stars, last pushed 4mo ago), licensed MIT. It adds 770 tokens to every session, about $0.0038 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 2026-08-30.

Claude Codeaicarouselclaudeinstagramlocal-first
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens