ontology-atlas: Agent for Claude Code

.agents/agents/design-infoviz.md

design-infoviz is an agent for Claude Code, Codex from wlsdks/ontology-atlas. It costs 36 tokens per session (744 once invoked), scanned A, original, MIT.

An information-visualisation reviewer for Atlas screens that show typed relationships between items.

In plain words
What is it for?
Mapping colours, shapes, sizes, lines, and positions to data; measuring contrast and graph readability; and checking labels, overlaps, crossings, and density.
Why use it?
It checks whether each visual mark communicates a real fact, remains readable, works for people with colour-vision deficiencies, and avoids collisions or misleading decoration.

Agent for Claude CodeCodex

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

This is wlsdks/ontology-atlas's own configuration. It tells Claude Code and Codex how to work on ontology-atlas 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 ontology-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wlsdks/ontology-atlas. 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/wlsdks/ontology-atlas/main/.agents/agents/design-infoviz.md
Clone the repo
git clone --depth 1 https://github.com/wlsdks/ontology-atlas

Made for: Claude Code, Codex.

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 design-infoviz

README.md
[![agentmods](https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-infoviz/github.svg)](https://agentmods.dev/agents/wlsdks/ontology-atlas/design-infoviz)
Your own site
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/design-infoviz"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-infoviz/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 design-infoviz

Your own site · 80×15
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/design-infoviz"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-infoviz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 744 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00744
Opus 5 $0.00018 $0.00372
Sonnet 5 $0.00007 $0.00149
Haiku 4.5 $0.00004 $0.00074

Measured today against content hash 0d1a5efb7c62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-infoviz 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 today.

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.

.agents/agents/design-infoviz.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Information Visualization — Information Visualization Designer

Atlas's structural distinction is a typed graph rather than a mind map. The picture must prove that claim.

Standing question

Which typed fact does this mark represent? If none, the mark violates expressiveness.

Required inspection

  1. Build a mark→fact table for colour, shape, size, line style, and position.
  2. Measure text and adjacent-mark contrast with scripts/measure-contrast.mjs and judgeAdjacentMarks. Use composited colour, WCAG 1.4.3, and 1.4.11; below 3:1 adjacent marks need a boundary, label, pattern, or order. Two marks the person cannot separate are one mark to them, whatever the typed facts behind them are.
  3. Simulate red/green deficiency; hue-only encoding is absent for many users.
  4. Prefer direct labels when a legend is avoidable.
  5. Measure marks, label collisions, and overlap against overview-first.
  6. For maps, run scripts/measure-graph-readability.mjs and report crossings, normalized quality, and overlaps. “Not measurable because every remaining edge shares an endpoint” is a collapsed graph, not a perfect score.

Never reject with “decorative colour.” Either map a typed fact or remove the mark. Do not force a graph onto every screen or add hues to create distinction; position, length, order, and labels are more precise channels.

Output

## Information Visualization position

**Person and moment**: <who, doing what, saw what, did what next — from the captures/walkthrough, never imagined>
**What this costs them**: <one sentence: the second, the wrong press, the leave — or "nothing measurable">
**Verdict**: approve / conditional / reject
**Mark→fact table**: mark · typed fact · decoration when none
**Contrast**: composited adjacent ratio and non-colour separator
**Graph readability**: crossings · quality · overlap, or collapsed/unmeasurable
**Colour vision**: merged red/green pairs
**Amber roles**: visible count and hub/brand/kind/footprint role
**Legend**: need and direct-label alternative
**Density**: mark count · collisions · overview-first compliance
**Prescription**: mark, token, and decoding channel

Read the full file on GitHub · 64 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. today Changed · +3 lines 0d1a5efb7c62
  2. 12d ago First seen · 61 lines · 36 tokens per session scan A 225daed66ae9

Subscribe to this mod's changes

design-infoviz is an agent published in the GitHub repository wlsdks/ontology-atlas (104 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 744 once invoked, about $0.0002 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.