chart-creator

chart-creator is a skill for Claude Code, Codex from joe-broadhead/open-cowork. It costs 40 tokens per session (921 once invoked), scanned A, original, MIT.

A guide for creating truthful, readable charts from structured data, including choosing a suitable chart type, ordering dates correctly, and labeling values clearly.

In plain words
What is it for?
Use it when creating line, bar, area, or other charts from data, or when redesigning data for charting.
Why use it?
It helps avoid charts that use the wrong visual form, misleading order, unclear labels, or unsupported interpretations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when creating line, bar, area, or other charts from data, or when redesigning data for charting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joe-broadhead/open-cowork/chart-creator
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.

Any agent
npx skills add joe-broadhead/open-cowork --skill chart-creator
Clone the repo
git clone --depth 1 https://github.com/joe-broadhead/open-cowork

Made for: Claude Code, Codex.

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 chart-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/chart-creator/github.svg)](https://agentmods.dev/skills/joe-broadhead/open-cowork/chart-creator)
Your own site
<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/chart-creator"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/chart-creator/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.

agentmods 80×15 button for chart-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/chart-creator"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/chart-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 921 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00921
Opus 5 $0.00020 $0.00461
Sonnet 5 $0.00008 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured 9d ago against content hash ae370fddca92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

chart-creator 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 9d 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.

skills/chart-creator/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chart Creator

Use this skill when the user asks for a chart, diagram, visual explanation, or chart-ready redesign.

Core Rule

When the charts MCP is available, call the appropriate charts_* tool. Do not merely print a Vega-Lite spec or Mermaid source unless the user explicitly asks for raw source only.

Workflow

  1. Identify the question the chart must answer.
  2. Reduce the data to a flat array of objects with clear field names and one row per plotted mark.
  3. Validate the grain, units, ordering, and category count before plotting.
  4. Choose the simplest chart that shows the signal without distorting it.
  5. Call the matching charts MCP tool with complete inline data.
  6. Explain briefly what the chart shows and any caveat needed to read it correctly.

Tool Choice

  • charts_line_chart: default for ordered trends over dates, times, weeks, months, versions, or ranks.
  • charts_bar_chart: category comparison or ranking. Use bars for dates only when discrete daily/weekly/monthly magnitudes are the point; keep dates chronological, not value-sorted. For horizontal bars, use x for the numeric value and y for the category.
  • charts_area_chart: magnitude or composition over an ordered sequence; use only when filled area helps, not for ordinary single-series trends.
  • charts_scatter_plot: relationship between two numeric measures.
  • charts_pie_chart: simple part-to-whole with a small category count; use donut for a cleaner share view.
  • charts_heatmap: intensity by two dimensions.
  • charts_map: geographic points with latitude and longitude fields; use only when location is the primary dimension.
  • charts_histogram or charts_boxplot: distributions.
  • charts_funnel_chart: ordered stage dropoff.
  • charts_waterfall_chart: additive positive/negative contributions.
  • charts_bump_chart: rank changes over time.
  • charts_streamgraph: centered stacked areas for composition changing over time; avoid when ordinary stacked areas are clearer.
  • charts_calendar_heatmap: daily intensity across weeks/months/years when the calendar pattern matters.
  • charts_bullet_chart: actual vs target with optional qualitative ranges.
  • charts_candlestick_chart: open, high, low, close values across a time axis.
  • charts_sankey: weighted flows between stages or categories.
  • charts_mermaid: process, flow, sequence, or architecture diagrams rather than quantitative charts.
  • charts_custom_spec: only when the standard tools cannot express the needed visual.

Read the full file on GitHub · 65 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. 9d ago First seen · 65 lines · 40 tokens per session scan A ae370fddca92

Subscribe to this mod's changes

chart-creator is a skill published in the GitHub repository joe-broadhead/open-cowork (11 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 921 once invoked, about $0.0002 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.