vedix-plotter

A figure-making agent that turns experiment data into charts for research papers, using either Python plotting code or LaTeX drawing code. It works through three drafts and applies styles for journals such as Nature, Cell, IEEE, and Springer.

In plain words
What is it for?
Use it to create figures from results.csv and NumPy data, including timelines, taxonomies, heatmaps, and other plots. It can produce draft and final PNG files with records of the refinement process.
Why use it?
It reduces the manual work of checking data, choosing suitable chart types, and adjusting figures for publication. Drafts and critiques help catch readability problems before the final figure.

Agent

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 agents/danilkotelnikov/vedix/plotter
Clone the repo
git clone --depth 1 https://github.com/danilkotelnikov/vedix
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,446 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 $0.00085 $0.01446
Opus 5 $0.00043 $0.00723
Sonnet 5 $0.00017 $0.00289
Haiku 4.5 $0.00009 $0.00145

Measured yesterday against content hash f6adec8b3a7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vedix-plotter 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 yesterday.

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.

plugins/vedix/agents/plotter.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plotter

Iterative publication-grade figure generation. Three cycles, each independently re-runnable.

Inputs

  • <input name="output_dir"> — job output directory containing results.csv and any *.npy files
  • <input name="article_type">experimental | review | benchmark
  • <input name="journal_style">nature | cell | ieee | springer | auto
  • <input name="mode">scripting (matplotlib) | latex_native (TikZ/pgfplots) | both
  • <input name="cycle">1 | 2 | 3 | all
  • <input name="figure_specs"> — JSON list of {figure_id, kind, x, y, title, facets}

Cycle 1 — Inspect & Draft

For each spec:

  1. Sniff the schema of results.csv — column dtypes, row count, missing %, ranges.
  2. Justify the chosen plot kind in one sentence (e.g. "violin over bar because n=847 and Shapiro-Wilk rejects normality at p<0.001").
  3. Render a draft PNG at 2× target DPI (high enough to evaluate legibility, not final).
  4. Write figures_draft1/<id>.png and figures_draft1/manifest.json.

Article-type defaults:

  • review → bibliometric figures: timeline, taxonomy tree, co-citation cluster heatmap, journal/year heatmap. Booktabs summary tables in LaTeX. Prefer latex_native mode for font consistency with manuscript.
  • experimental → headline result with paired comparison + 95 % bootstrap CI; ablation table; Pareto front.
  • benchmark → score-vs-method bars (sorted by median, not alphabetically), per-task heatmap, compute-vs-quality scatter, Bradley-Terry Elo bars with symmetric CI.

Mandatory: every figure has axis labels with units, error bars (with description in caption), and a one-sentence rationale logged in manifest.json.

Cycle 2 — VLM Critique

For each figure, ask the VLM (per host: GPT-4o / Claude w/ vision / Gemini) the 10-point rubric:

  1. Is the primary message legible at thumbnail size?
  2. Is the color palette colorblind-safe (Okabe-Ito or Wong)?
  3. Are all axes labeled with units?
  4. Are error bars present and described in the caption?
  5. Is the legend placement optimal (inside or direct labels)?
  6. Is the font size legible at journal column width?
  7. Is the figure free of chartjunk (3D/gradient/shadow)?
  8. Are statistical annotations (p-values, n, CI) complete?
  9. Does the figure match the caption claim?
  10. Is the data-ink ratio maximized?

Read the full file on GitHub · 104 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. yesterday First seen · 104 lines · 85 tokens per session scan A f6adec8b3a7d

Subscribe to this mod's changes

vedix-plotter is an agent published in the GitHub repository danilkotelnikov/vedix (3 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 1,446 once invoked, about $0.0004 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 2026-08-31.

Related

Other agents, from other repositories

hlasm-assembler-specialist

IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…

josstei/maestro-orchestrate · 306 tokens

cloud_architect

Cloud architecture specialist for AWS, GCP, and Azure topology design, IaC patterns, multi-region resilience, and cost/security trade-offs. Use when the task requires designing a cloud deployment, reviewing IaC for best practices, or evaluating multi-region/DR strategies. For example: choosing between ECS and EKS…

josstei/maestro-orchestrate · 83 tokens

wtfp-research-synthesizer

Investigate the literature needed to plan and write a specific section well. The output is an evidence-traceable synthesis of foundational and recent work, standard approaches, genuine gaps, positioning options, and concrete writing guidance—not a search-result dump.

akougkas/wtf-p · 57 tokens

continuity-checker

Verifies logical, chronological, and factual consistency across drafted units. Flags contradictions, timeline issues, and character state drift.

hannsxpeter/scriveno · 29 tokens

AGENTS

Each file implements an AgentAdapter that reads local AI coding agent data.

eat-pray-ai/wingman · 0 tokens

java-reviewer

Expert Java and Spring Boot code reviewer specializing in layered architecture, JPA patterns, security, and concurrency. Use for all Java code changes. MUST BE USED for Spring Boot projects.

Jamkris/everything-gemini-code · 40 tokens