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.
npx agentmods add agents/jiutuhky/my-super-capsule/visualizergit clone --depth 1 https://github.com/jiutuhky/my-super-capsuleWrote 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.
[](https://agentmods.dev/agents/jiutuhky/my-super-capsule/visualizer)<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="Measured on agentmods" height="20"></a>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 | $0.00187 | $0.01593 |
| Opus 5 | $0.00093 | $0.00796 |
| Sonnet 5 | $0.00037 | $0.00319 |
| Haiku 4.5 | $0.00019 | $0.00159 |
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 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.
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.pyscript - Plot: Generate matplotlib Python code and execute it via the
execute_plot.pyscript
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.jsonto 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/
- Read the description text from the file at
-
Update
pipeline_state.jsonwith 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 andtarget_{task_type}_desc0_image_pathis NOT presenttarget_{task_type}_stylist_desc0— if present andtarget_{task_type}_stylist_desc0_image_pathis NOT present- For round_idx in 0..2:
target_{task_type}_critic_desc{round_idx}— if present andtarget_{task_type}_critic_desc{round_idx}_image_pathis 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.
- Copy the previous round's image path:
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 · 157 lines · 187 tokens per session scan A 750fda1d73a4
visualizer is an agent published in the GitHub repository jiutuhky/my-super-capsule (11 stars, last pushed 6mo ago), licensed MIT. It adds 187 tokens to every session and 1,593 once invoked, about $0.0009 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.
Other agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…