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 SPYfighting/my-academic-skills --skill scientific-illustrator-localgit clone --depth 1 https://github.com/SPYfighting/my-academic-skillsWrote 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/spyfighting/my-academic-skills/scientific-illustrator-local)<a href="https://agentmods.dev/skills/spyfighting/my-academic-skills/scientific-illustrator-local"><img src="https://agentmods.dev/badge/skills/spyfighting/my-academic-skills/scientific-illustrator-local/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/spyfighting/my-academic-skills/scientific-illustrator-local"><img src="https://agentmods.dev/badge/skills/spyfighting/my-academic-skills/scientific-illustrator-local.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00082 | $0.01550 |
| Opus 5 | $0.00041 | $0.00775 |
| Sonnet 5 | $0.00016 | $0.00310 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
scientific-illustrator-local 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 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.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Illustrator Local
Version 0.2.1. Produce editable paths and live text through a local workflow shared by Codex, Claude Code, and OpenCode. Instructions are in English; preserve the original language and content of figure labels.
Start
Resolve skill_dir from this file's actual location. Use its scripts directly for project-local work; registering a global skill is unnecessary. For setup or a different machine, read installation and compatibility.
In the commands below, <python> is the skill's .venv/Scripts/python.exe on Windows or .venv/bin/python on macOS, or an explicitly verified CPython 3.11-3.13 environment. <cli> means skill_dir/scripts/figure_cli.py. Quote full paths; PowerShell needs & before a quoted executable path.
<python> -X utf8 <cli> doctor
<python> -X utf8 <cli> illustrator-doctor
The native adapter attaches to an already-running Illustrator instance: Windows uses PowerShell 5.1 and COM; macOS uses the actual running application bundle and AppleScript. The Python scheduler and JSX renderer are shared. Windows with Illustrator 27.2.0 has been tested on hardware; macOS and other versions still require native validation.
Choose the input route
- New schematic: write structured SVG with paths, basic shapes, and real
<text>. Use polygons for arrowheads. Data plots require the user's actual data or original vector output. - Existing vector SVG: validate and prepare it directly, preserving its vector structure.
- Raster reconstruction: read the workflow and input specification. Transcribe and review every label first, remove only the text from a copy, trace the remaining artwork, then add real text at the original baselines. Do not trace letters and hide their outlines beneath white overlays.
- Use
--text-mode noneonly for genuinely text-free input. Use--text-mode outlinesonly when the user explicitly accepts non-editable lettering.
What ships with it
22 files 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.
- .gitignore 71 B
- examples/editable-workflow.svg 1.6 KB
- LICENSE 1.1 KB
- NOTICE.md 1.4 KB
- references/input-and-validation.md 3.2 KB
- references/installation-and-compatibility.md 5.1 KB
- references/workflow.md 4.9 KB
- requirements.lock 311 B
- scripts/bridge-windows.ps1 2.0 KB runs code
- scripts/figure_cli.py 7.1 KB runs code
- scripts/figurelib/__init__.py 108 B runs code
- scripts/figurelib/common.py 2.1 KB runs code
- scripts/figurelib/illustrator.py 19 KB runs code
- scripts/figurelib/jobs.py 8.7 KB runs code
- scripts/figurelib/preview.py 5.1 KB runs code
- scripts/figurelib/svg.py 17 KB runs code
- scripts/figurelib/text.py 8.6 KB runs code
- scripts/figurelib/trace.py 11 KB runs code
- scripts/illustrator_runtime.jsx 15 KB
- scripts/install_vtracer.py 3.8 KB runs code
- scripts/selfcheck.py 7.6 KB runs code
- scripts/setup_environment.py 2.0 KB runs code
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.
- 3d ago First seen · 81 lines · 82 tokens per session scan A d2e3579f61e0
scientific-illustrator-local is a skill published in the GitHub repository SPYfighting/my-academic-skills (14 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 1,550 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 2026-09-09.
Other skills, from other repositories
figure-design
Use when creating, updating, or reviewing a research figure (plot, chart, brain map, heatmap, schematic) — guides chart-type selection, typography, colorblind-safe palette, layout, and journal-specific export specs. Dispatches a figure-reviewer subagent after rendering. Complements claims-audit (which checks figure…
hypothesis-first
Use when running any experiment or analysis — hypothesis and analysis plan must be registered before seeing results, the scientific equivalent of test-driven development.
manuscript-writing
Use when writing a research manuscript — guides section-by-section writing with prerequisite gates, citation discipline, number traceability, and per-section subagent review. Activated after experiment results are reviewed and before claims-audit.
claims-audit
Use during or after manuscript writing to verify every quantitative claim traces to actual data, every figure is script-generated, and all results including negative ones are reported.
experiment-design
Use when a research design has been approved and needs to be broken into executable experiment steps — the research equivalent of an implementation plan.
research-brainstorming
You MUST use this before any experiment, analysis, or scientific claim — when a research question, hypothesis, study design, or scientific approach needs to be defined or refined.