What is visualize CLAUDE.md?

A project guide for Visualize, a Claude Code plugin that turns ideas, data, or other content into self-contained HTML visualizations. Claude Code is a coding assistant that can load project-specific instructions and skills.

Use it when installing or maintaining the Visualize plugin, creating HTML visualizations, consulting its design references, or working with its examples and evaluation files.

It tells the coding agent how the plugin is organized, installed, and used, so work follows the repository’s structure and design rules.

visualize CLAUDE.md — Instructions file by careerhackeralex

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/careerhackeralex/visualize/claude-md

Clone the repo

git clone --depth 1 https://github.com/careerhackeralex/visualize

Per session 1,155 This file is loaded in full into every session.

When invoked 1,155 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	$0.01155	$0.01155
Opus 5	$0.00577	$0.00577
Sonnet 5	$0.00231	$0.00231
Haiku 4.5	$0.00115	$0.00115

Measured 3d ago against content hash 662a21cf9f77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visualize 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.

CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This is the Visualize plugin — an open-source Claude Code plugin that turns any idea, data, or content into beautiful, self-contained HTML visualizations.

Repo Structure

visualize/
├── .claude-plugin/
│   └── plugin.json           # Plugin manifest (name, version, author)
├── skills/
│   └── visualize/
│       ├── SKILL.md           # Main skill file (loaded by Claude Code)
│       └── references/        # Detailed specs (progressive disclosure Level 3)
│           ├── design-system.md
│           ├── skeleton.md
│           ├── types.md
│           ├── libraries.md
│           ├── menu.md
│           ├── css-techniques.md
│           ├── animations.md
│           └── eval.md
├── examples/                  # 15 example HTML files
├── eval/                      # Eval infrastructure
│   ├── EVAL.md               # 3-layer scoring specification
│   ├── LOOP.md               # Self-improvement loop methodology (v6)
│   ├── SKILL.md              # Evaluator skill
│   ├── loop-state.json       # Current round + score history
│   ├── stress-tests.md       # 40 test cases
│   ├── OPENCLAW-SETUP.md     # Prompt to set up automated cron job on OpenClaw
│   ├── pipeline/             # Automated eval pipeline (Node.js)
│   │   ├── run.js            # Orchestrator: node run.js --dir examples/
│   │   ├── format-detect.js  # Layer 1: auto-detect visualization format
│   │   ├── vision-eval.js    # Layer 3: vision eval helper (agent scores, not API)
│   │   ├── checks/           # Layer 2: 45 deterministic DOM checks
│   │   ├── calibration/      # Anchor screenshots for vision eval
│   │   └── LOOP-PROMPT.md    # Self-improvement loop agent prompt
│   ├── rounds/               # Per-round results
│   └── archive/              # Rounds 1-38 (historical)
├── docs/plans/               # Design & implementation docs
├── CLAUDE.md                  # This file
├── README.md                  # GitHub-facing docs
└── LICENSE                    # MIT

Installation

Read the full file on GitHub · 96 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.

3d ago First seen · 96 lines · 1,155 tokens per session scan A 662a21cf9f77

Subscribe to this mod's changes

visualize CLAUDE.md is an instructions file published in the GitHub repository careerhackeralex/visualize (218 stars, last pushed 6mo ago), licensed MIT. It adds 1,155 tokens to every session, about $0.0058 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 2026-08-30.

ai claude-code dashboards html infographics open-source

visualize CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Repo Structure

Installation

What this file has done since we first saw it

Other instructions, from other repositories

hyperframes AGENTS.md

open-pencil copilot-instructions.md

openscreen AGENTS.md

Claw3D AGENTS.md

openstatus AGENTS.md

openstatus CLAUDE.md