What is VibePoster CLAUDE.md?

Project instructions for VibePoster, an AI-based poster design system with a web editor, image tools, brand information retrieval, and separate frontend, backend, and image-export services.

Use them to install dependencies, configure API keys, run the services with Docker or local development, and understand where the frontend, AI engine, export service, and documentation live.

They give an unfamiliar developer the project layout, setup choices, required environment values, and commands needed to start the system.

How l1anch1/VibePoster configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to l1anch1/VibePoster. 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/l1anch1/VibePoster/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/l1anch1/VibePoster

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/l1anch1/vibeposter/claude-md/github.svg)](https://agentmods.dev/instructions/l1anch1/vibeposter/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/l1anch1/vibeposter/claude-md"><img src="https://agentmods.dev/badge/instructions/l1anch1/vibeposter/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/l1anch1/vibeposter/claude-md"><img src="https://agentmods.dev/badge/instructions/l1anch1/vibeposter/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,900 This file is loaded in full into every session.

When invoked 1,900 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01900	$0.01900
Opus 5.5	$0.00760	$0.00760
Sonnet 5.5	$0.00380	$0.00380
Haiku 4.5	$0.00190	$0.00190

Measured 2mo ago against content hash 972ee221bdf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

VibePoster 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 2mo 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.

CLAUDE.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibePoster

AI-powered poster design system. Multi-agent orchestration + Knowledge Graph (KG) + RAG brand knowledge + image understanding/generation + online editor.

Project Structure

VibePoster/
├── frontend/          # React 19 + TypeScript + Vite 7 + Tailwind CSS 4
├── backend/
│   ├── engine/        # Python FastAPI — AI Agent engine (LangGraph orchestration)
│   └── render/        # Node.js Express — PNG/JPG/PSD export service
└── docs/              # Architecture docs

Quick Start

Docker (recommended)

cp backend/engine/env.template backend/engine/.env
# Edit .env with your API keys
docker-compose up -d --build                                          # production
docker-compose -f docker-compose.yml -f docker-compose.dev.yml up     # dev (hot reload)

Local Development (3 terminals)

# Terminal 1: Engine
cd backend/engine && uv sync
uv run uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

# Terminal 2: Render
cd backend/render && npm install && node src/server.js

# Terminal 3: Frontend
cd frontend && npm install && npm run dev

Service	Dev Port	Prod Port
Frontend (Vite)	5173	80 (Nginx)
Engine (FastAPI)	8000	8000
Render (Express)	3000	3000

Environment Variables

Single config file: backend/engine/.env (template: backend/engine/env.template)

Required API keys: PLANNER_API_KEY, VISUAL_API_KEY, LAYOUT_API_KEY, CRITIC_API_KEY, plus at least one of VISUAL_FLUX_API_KEY or VISUAL_PEXELS_API_KEY.

Each agent supports independent config: {AGENT}_PROVIDER, {AGENT}_API_KEY, {AGENT}_BASE_URL, {AGENT}_MODEL, {AGENT}_TEMPERATURE.

Frontend env vars injected via Vite: VITE_API_URL (default http://localhost:8000), VITE_RENDER_URL (default http://localhost:3000).

Agent Architecture

Planner → Visual → Layout → Critic → [retry Layout or END]

Planner: 4-Skill pipeline (IntentParse → DesignRule/KG → BrandContext/RAG → DesignBrief/LLM)
Visual: Image understanding + asset search/generation (Pexels/Flux)
Layout: Semantic DSL generation + OOP layout engine (7 strategies, dynamic coordinate computation)
Critic: Dual-path review (JSON structure + visual rendering), retries Layout on failure (up to 2x)

Read the full file on GitHub · 185 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.

2mo ago First seen · 185 lines · 1,900 tokens per session scan A 972ee221bdf2

Subscribe to this mod's changes

VibePoster CLAUDE.md is an instructions file published in the GitHub repository l1anch1/VibePoster (3 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,900 tokens to every session, about $0.0076 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 2026-08-31.

Creative and media Design and UX ai-art computer-vision fastapi knowledge-graph langgraph llms

VibePoster CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
VibePoster CLAUDE.mdl1anch1/VibePoster	Instructions file	3	6mo ago	Apache-2.0	A	1,900	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

VibePoster: Instructions file for Claude Code