Draw.io Scientific Illustrator is a Codex plugin that lets an AI agent create and edit scientific diagrams directly in the visible draw.io desktop canvas through a local MCP server. It is for users who want step-by-step agent-assisted scientific illustration and can also validate draw.io files or export them as images and PDFs. Its MCP servers and skill provide the catalogue add-ons for operating this workflow, although the repository is now legacy and development has moved elsewhere.
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 skills add icebird1998/drawio-scientific-illustrator --skill recreate-scientific-figure-in-drawiogit clone --depth 1 https://github.com/icebird1998/drawio-scientific-illustratorWrote 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/skills/icebird1998/drawio-scientific-illustrator/recreate-scientific-figure-in-drawio)<a href="https://agentmods.dev/skills/icebird1998/drawio-scientific-illustrator/recreate-scientific-figure-in-drawio"><img src="https://agentmods.dev/badge/skills/icebird1998/drawio-scientific-illustrator/recreate-scientific-figure-in-drawio/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.
<a href="https://agentmods.dev/skills/icebird1998/drawio-scientific-illustrator/recreate-scientific-figure-in-drawio"><img src="https://agentmods.dev/badge/skills/icebird1998/drawio-scientific-illustrator/recreate-scientific-figure-in-drawio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00118 | $0.00994 |
| Opus 5 | $0.00059 | $0.00497 |
| Sonnet 5 | $0.00024 | $0.00199 |
| Haiku 4.5 | $0.00012 | $0.00099 |
Grade A, and why
recreate-scientific-figure-in-drawio 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 13d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recreate Scientific Figures in draw.io
Use the plugin's live MCP tools whose names end in drawio_live_launch, drawio_live_status, drawio_live_screenshot, drawio_live_add_shape, drawio_live_add_edge, drawio_live_update_cell, drawio_live_draw_sequence, drawio_live_fit, drawio_live_inspect, and drawio_live_save_snapshot. Use file tools ending in drawio_validate and drawio_export only after the visible drawing has been saved.
Hard boundary
- Control only draw.io's internal graph/model API through the live MCP server.
- Never use operating-system mouse, keyboard, window, or full-screen automation for this workflow.
- Never pre-build XML and then open it as the drawing method. Serialize
.drawioonly after live shapes and edges already exist on the visible canvas. - Renderer screenshots are allowed only to inspect the draw.io canvas itself; they are not general computer-screen control.
Workflow
- Inspect every provided reference image with vision before creating XML. For a PDF, render the relevant page first. Do not merely embed the raster image and call it recreated.
- Decompose the figure into editable primitives: canvas/aspect ratio, panels, containers, nodes, text, arrows, legends, repeated motifs, colors, stroke widths, fonts, and z-order. Identify any portions that must remain raster because draw.io primitives cannot reproduce them faithfully.
- Call
drawio_live_launchwith a visible per-step delay, normally 400–1000 ms. Calldrawio_live_statusand requiregraph_ready=truebefore drawing. - Add geometry directly to the live canvas:
- Use
drawio_live_add_shapeanddrawio_live_add_edgefor one deliberate visible step at a time. - Use
drawio_live_draw_sequenceonly with a nonzerostep_delay_ms; each operation must remain a separate draw.io model update so the user can watch it appear. - Use stable semantic cell ids from the beginning so later edges and edits can target exact elements.
- Use
- Call
drawio_live_screenshotafter each logical section, not after every trivial cell. Inspect only the draw.io renderer and compare it with the reference. - Iterate directly in the live graph. Use
drawio_live_inspectfollowed bydrawio_live_update_cellfor labels, styles, position, and size. Usedrawio_live_fitto keep progress visible. - After the visible figure is complete, call
drawio_live_save_snapshot. This is the first point at which.drawioXML should be serialized. - Call
drawio_validate. Fix structural errors through the live graph when possible, then save again. - Export a review PNG with
embed=falseandwidth=2000. Check element count, wording, topology, alignment, overlap, clipping, arrow direction, color, whitespace, and correspondence to the reference. - After approval, export the requested deliverables. Default to an editable
.drawioplus PNG. Useembed=truefor final PNG/SVG/PDF so draw.io XML remains embedded where supported.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 46 lines · 118 tokens per session scan A ffedd1bc94b4
recreate-scientific-figure-in-drawio is a skill published in the GitHub repository icebird1998/drawio-scientific-illustrator (1,413 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 994 once invoked, about $0.0006 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 skills, from other repositories
audit-scientific-figure
Review and score an existing scientific illustration in visible draw.io, Microsoft PowerPoint, or WPS Presentation without hiding defects through flattening. Use for reference-fidelity checks, layout cleanup, connector review, text-fit checks, deep editability and raster-atomicity inspection, local-region gates, or…
correct-scientific-figure
Convert Reviewer findings for a scientific illustration into minimal, ordered, object-level correction instructions for visible draw.io, Microsoft PowerPoint, or WPS Presentation. Use when layout, text, connector, z-order, reference-fidelity, or raster editability defects must be translated into exact backend…
recreate-scientific-figure
Recreate a supplied scientific figure, graphical abstract, workflow, model diagram, or multi-panel schematic as a maximally editable illustration in visible draw.io, Microsoft PowerPoint, or WPS Presentation. Use when a PNG/JPEG/SVG/PDF reference must be rebuilt panel by panel through a Designer, Drawer, Reviewer, and…
recreate-scientific-figure-in-drawio
Recreate, design, inspect, refine, or export scientific figures live in the visible draw.io desktop canvas through draw.io's graph API. Use as the draw.io Drawer for step-by-step editable reconstruction or clean no-reference design with text/shapes/lines, composite tables/charts, atomic images, exact layout…
design-scientific-figure
Design a new scientific illustration, graphical abstract, workflow, architecture figure, or mechanism diagram from a brief without a reference image, for visible draw.io, Microsoft PowerPoint, or WPS Presentation. Use when a clean editable layout, planned connector lanes, consistent visual grammar, and…
diagram-design
Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, treemap, bar, waterfall, line, Gantt and scatter charts…