figure

figure is a command for Claude Code from Abhinavbwj/AEC-Scholar. It costs 20 tokens per session (410 once invoked), scanned A, original, MIT.

A figure-designing command that helps create publication-ready charts and diagrams, along with code that can reproduce them. It supports data plots and diagrams such as workflows, architectures, and concept maps.

In plain words
What is it for?
Use it to plan chart types, choose accessible labels and colours, draft captions, and generate Python, R, Mermaid, TikZ, or Graphviz source for figures.
Why use it?
It helps turn an unclear message or dataset into an appropriate visual while avoiding misleading chart choices. It also records how the figure was made, so it can be regenerated and checked.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the aec-scholar plugin — 11 skills, 36 commands, 10 agents, 1 hook shipped together

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 commands/abhinavbwj/aec-scholar/figure
Clone the repo
git clone --depth 1 https://github.com/Abhinavbwj/AEC-Scholar

Made for: Claude Code.

Or install aec-scholar, the plugin that ships this one along with the rest of its 11 skills, 36 commands, 10 agents, 1 hook.

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 figure

README.md
[![agentmods](https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/figure.svg)](https://agentmods.dev/commands/abhinavbwj/aec-scholar/figure)
Your own site
<a href="https://agentmods.dev/commands/abhinavbwj/aec-scholar/figure"><img src="https://agentmods.dev/badge/commands/abhinavbwj/aec-scholar/figure.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 410 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00410
Opus 5 $0.00010 $0.00205
Sonnet 5 $0.00004 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 6d ago against content hash ba91d2a84305, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

figure 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 6d 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.

aec-scholar/commands/figure.md · 34 lines

What it actually says

Design a figure for: $ARGUMENTS

Use the figure-designer agent and the scientific-figures skill.

  1. Clarify the message & data. What is the single point this figure must make, and what data/structure underlies it (distribution, comparison, relationship, trend, composition, multi-objective trade-off, network, or a workflow/system diagram)?

  2. Recommend the chart/diagram type for that message + data, and say what to avoid (e.g. no pie, no dual axes, no truncated bars, no 3D).

  3. Specify honest, accessible encoding — zero-baseline bars, shown uncertainty (state what error bars mean), labelled axes with units, colour-blind-safe palette (Okabe–Ito/viridis) + redundant shape/ linestyle, vector output, legible fonts at print scale.

  4. Generate reproducible source:

    • Data plots → runnable matplotlib/seaborn or ggplot2 code (with accessible rcParams/theme and savefig/ggsave to PDF), using clearly marked placeholder data if the user hasn't supplied real data.
    • Diagrams (workflow, architecture, BIM/data pipeline, concept map) → Mermaid (renders inline) or TikZ/Graphviz source.
  5. Draft the caption (self-contained: what it shows, n, what error bars denote) and run a quick accessibility/print check.

Never invent or "beautify" data points or fabricate a plotted result; mark placeholders and tell the user exactly what to plug in.

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. 6d ago First seen · 34 lines · 20 tokens per session scan A ba91d2a84305

Subscribe to this mod's changes

figure is a command published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 410 once invoked, about $0.0001 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.