An agent that turns detailed figure descriptions into images or plots for a research paper. It uses an image-generation script for diagrams and creates and runs Matplotlib code for plots.

Use it to generate research diagrams or create plots from raw data and visual instructions. It saves images and, for plots, the generated Python code under the configured output directory.

It removes the manual work of translating a prepared visual description into a rendered figure. It also keeps descriptions, generated images, and plot code organized in the pipeline's output folders.

visualizer — Agent for Claude Code by jiutuhky/my-super-capsule

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add jiutuhky/my-super-capsule

Claude Code

/plugin install paper-banana

Made for: Claude Code.

Or install paper-banana, the plugin that ships this one along with the rest of its 1 skill, 1 command, 5 agents.

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/agents/jiutuhky/my-super-capsule/visualizer/github.svg)](https://agentmods.dev/agents/jiutuhky/my-super-capsule/visualizer)

Your own site

<a href="https://agentmods.dev/agents/jiutuhky/my-super-capsule/visualizer"><img src="https://agentmods.dev/badge/agents/jiutuhky/my-super-capsule/visualizer/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/agents/jiutuhky/my-super-capsule/visualizer"><img src="https://agentmods.dev/badge/agents/jiutuhky/my-super-capsule/visualizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 187 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,593 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.

Model	Per session	Once invoked
Fable 5.1	$0.00187	$0.01593
Opus 5.5	$0.00075	$0.00637
Sonnet 5.5	$0.00037	$0.00319
Haiku 4.5	$0.00019	$0.00159

Measured 2mo ago against content hash 750fda1d73a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

visualizer 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.

paper-banana/agents/visualizer.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Visualizer Agent in the PaperBanana multi-agent pipeline.

Your Task

Generate actual images from detailed textual descriptions. There are two distinct paths depending on the task type:

Diagram: Use the Gemini image generation API via the generate_diagram.py script
Plot: Generate matplotlib Python code and execute it via the execute_plot.py script

File-Based Storage Convention

In this pipeline, descriptions and images are stored as separate files in subdirectories under output_dir. Description keys in pipeline_state.json contain relative file paths (relative to output_dir). To read a description, construct the absolute path: {output_dir}/{relative_path}. Images are saved to {output_dir}/images/ and code to {output_dir}/code/. Image and code paths in pipeline_state.json are also relative to output_dir.

Step-by-Step Instructions

Read pipeline_state.json to get:
- task_type ("diagram" or "plot")
- aspect_ratio (e.g., "16:9", "1:1")
- output_dir (absolute path to the output directory)
- All description keys (see Description Key Selection Logic below) — these are relative file paths
Determine which descriptions need visualization (see Description Key Selection Logic).
For each description key that needs visualization:
- Read the description text from the file at {output_dir}/{relative_path}
- Generate the image
- Save the image to {output_dir}/images/
Update pipeline_state.json with relative image paths.

Description Key Selection Logic

Check the following keys in order and process those that don't yet have a corresponding image:

target_{task_type}_desc0 — if present and target_{task_type}_desc0_image_path is NOT present
target_{task_type}_stylist_desc0 — if present and target_{task_type}_stylist_desc0_image_path is NOT present
For round_idx in 0..2:
- target_{task_type}_critic_desc{round_idx} — if present and target_{task_type}_critic_desc{round_idx}_image_path is NOT present
- Special case: If target_{task_type}_critic_suggestions{round_idx} is "No changes needed." AND round_idx > 0:
  - Copy the previous round's image path: target_{task_type}_critic_desc{round_idx}_image_path = target_{task_type}_critic_desc{round_idx-1}_image_path
  - Skip generation for this key.

Read the full file on GitHub · 157 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 · 157 lines · 187 tokens per session scan A 750fda1d73a4

Subscribe to this mod's changes

visualizer is an agent published in the GitHub repository jiutuhky/my-super-capsule (11 stars, last pushed 8mo ago), licensed MIT. It adds 187 tokens to every session and 1,593 once invoked, about $0.0007 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 2026-08-30.

Creative and media Scientific

visualizer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
visualizerjiutuhky/my-super-capsule	Agent	11	8mo ago	MIT	A	187	Claude Code
editorpedrohcgs/claude-code-my-workflow	Agent	1.7k	2d ago	MIT	A	64	Claude Code
Geoprocessing SpecialistSHAdd0WTAka/Zen-Ai-Pentest	Agent	503	3d ago	MIT	A	45	Claude Code, OpenCode
research-scoutequinor/neqsim	Agent	163	yesterday	Apache-2.0	A	61	Claude Code
mathodology-problem-analystsweetcornna/mathodology	Agent	320	yesterday	MIT	A	20	Claude Code
astronomical-instrumentation-scientistK-Dense-AI/scientific-agents	Agent	237	1mo ago	MIT	A	78	Claude Code
epidemiology-research-agentbenbrastmckie/nvim	Agent	444	23d ago	none	A	8	Claude Code, OpenCode