chart-maker

An agent that creates one styled chart from a data source and a chart specification. It accepts sources such as CSV files, SQL results, pandas DataFrames, and Parquet files.

In plain words
What is it for?
Use it to make bar, line, area, scatter, histogram, pie, heatmap, waterfall, funnel, table, and other supported charts with titles, subtitles, color grouping, and annotations.
Why use it?
It turns structured chart requirements into a consistent visualization and can apply a supplied fix report before creating the chart.

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/ai-analyst-lab/ai-analyst/chart-maker
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,427 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00000 $0.04427
Opus 5 $0.00000 $0.02214
Sonnet 5 $0.00000 $0.00885
Haiku 4.5 $0.00000 $0.00443

Measured 3d ago against content hash 68992c2aac99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

chart-maker scanned grade C with 1 finding 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 3d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- CONTRACT_START name: chart-maker description: Generate a single styled chart from data and a chart specification, applying SWD visualization standards for theme, color, typography, and annotation. inputs: - name: DA
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/chart-maker.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Chart Maker

Purpose

Generate a single styled chart from data and a chart specification, applying visualization skill standards for theme, color, typography, and annotation.

Inputs

  • {{DATA}}: Path to the data source — a CSV file, a SQL query result, a pandas DataFrame reference, or a path to a parquet file. The agent will load the data and use the columns specified in {{CHART_SPEC}}.
  • {{CHART_SPEC}}: A structured chart specification containing:
    • chart_type: The chart type — one of: bar, horizontal_bar, grouped_bar, stacked_bar, line, multi_line, area, scatter, histogram, pie, donut, heatmap, waterfall, funnel, table
    • x: Column name for the x-axis (or categorical axis for horizontal charts)
    • y: Column name(s) for the y-axis. For multi-series charts, provide a list: ["metric_a", "metric_b"]
    • title: Chart title — should state the insight, not describe the chart (GOOD: "Mobile conversion dropped 23% in Q3", BAD: "Conversion Rate by Platform")
    • subtitle: (optional) Additional context line below the title
    • color_by: (optional) Column name to use for color encoding (creates grouped/segmented visuals)
    • annotations: (optional) List of annotations to add — each with value, label, and position (e.g., [{"value": "2024-03", "label": "Redesign launched", "position": "top"}])
    • sort_by: (optional) How to sort the data — "value_asc", "value_desc", "label_asc", "label_desc", or "none". Defaults to the natural order of the data.
    • limit: (optional) Maximum number of data points to show. For bar charts with many categories, limits to top N and groups the rest as "Other".
    • format: (optional) Number format for labels — "percent", "currency", "integer", "decimal". Defaults to auto-detection from the data.
  • {{THEME}}: (optional) Named theme from the Visualization Patterns skill — "nyt", "economist", "minimal", "corporate". Defaults to "minimal" if not specified.
  • {{OUTPUT_NAME}}: (optional) Base filename for the output chart (without extension). Defaults to a slugified version of the chart title.

Read the full file on GitHub · 349 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. 3d ago First seen · 349 lines · 0 tokens per session scan C 68992c2aac99

Subscribe to this mod's changes

chart-maker is an agent published in the GitHub repository ai-analyst-lab/ai-analyst (296 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,427 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.