What is Claude-Visual-Communications-Plugin CLAUDE.md?

Instructions for a visual-communications plugin that plans images, diagrams, and videos for long-form content. It organizes source files, ideas, prompts, and generated assets by project.

Use it to set up projects for whitepapers, blog posts, technical documents, magazine articles, or presentations, then prepare and manage their visuals.

It gives visual work a repeatable place and process instead of leaving ideas and generated files scattered.

Claude-Visual-Communications-Plugin CLAUDE.md — Instructions file for coding agents by danielrosehill: Instructions for a visual-communicati

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/danielrosehill/claude-visual-communications-plugin/claude-md

Clone the repo

git clone --depth 1 https://github.com/danielrosehill/Claude-Visual-Communications-Plugin

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/danielrosehill/claude-visual-communications-plugin/claude-md.svg)](https://agentmods.dev/instructions/danielrosehill/claude-visual-communications-plugin/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/danielrosehill/claude-visual-communications-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/danielrosehill/claude-visual-communications-plugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,133 This file is loaded in full into every session.

When invoked 1,133 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.

Model	Per session	Once invoked
Fable 5	$0.01133	$0.01133
Opus 5	$0.00566	$0.00566
Sonnet 5	$0.00227	$0.00227
Haiku 4.5	$0.00113	$0.00113

Measured 5d ago against content hash 3516a7e6c6c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Claude-Visual-Communications-Plugin 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 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.

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 · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual-Communications Plugin

A Claude Code plugin for planning and prompt-engineering AI-generated visuals (images, diagrams, video) for long-form content projects such as whitepapers, blogs, technical documents, and presentations.

Overview

The plugin guides users through two phases of visual enhancement:

Project onboarding — Set up a project, gather source material, and define target platform and style
Ideation & prompt generation — Brainstorm visual concepts and convert them into optimized generation prompts
Generation & management — Execute prompts via the fal-ai MCP and manage visual assets

Data Storage

All project data is stored in the plugin data directory:

${CLAUDE_PLUGIN_DATA:-$HOME/.local/share/claude-plugins}/visual-communications/
  projects/
    <project-name>/
      source/            # Original content (markdown, PDFs, etc.)
      visuals/           # Generated images and videos
      prompts/           # Saved prompts (YAML format)
      project.yaml       # Project configuration
      ideation.md        # Brainstormed visual concepts

Each project's project.yaml defines:

Project name, type (whitepaper | blog | technical-doc | magazine | presentation), and goal
Target platform (web | print | social | presentation | pdf)
Target audience and visual style preferences
Resolution specifications per platform
References to source material

Skills

onboard-visual-project

Set up a new project. Collects project name, type, purpose, platform, source material, audience, and style preferences. Scaffolds the project directory and writes project.yaml.

ideate-visuals

Analyze source content and brainstorm 5–8 visual concepts across categories:

Hero/header images
Explanatory visuals (flowcharts, diagrams, infographics)
Conceptual illustrations
Data visualizations
Spot illustrations and icons
Interactive/animated content
Video content

Saves ideation notes to ideation.md for later reference.

Read the full file on GitHub · 117 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.

5d ago First seen · 117 lines · 1,133 tokens per session scan A 3516a7e6c6c2

Subscribe to this mod's changes

Claude-Visual-Communications-Plugin CLAUDE.md is an instructions file published in the GitHub repository danielrosehill/Claude-Visual-Communications-Plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,133 tokens to every session, about $0.0057 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.

Creative and media

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 · 5,182 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

Claude-Visual-Communications-Plugin CLAUDE.md