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 stencila/stencila --skill figure-creationgit clone --depth 1 https://github.com/stencila/stencilaWrote 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/stencila/stencila/figure-creation)<a href="https://agentmods.dev/skills/stencila/stencila/figure-creation"><img src="https://agentmods.dev/badge/skills/stencila/stencila/figure-creation/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/stencila/stencila/figure-creation"><img src="https://agentmods.dev/badge/skills/stencila/stencila/figure-creation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 243 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00092 | $0.05508 |
| Opus 5.5 | $0.00037 | $0.02203 |
| Sonnet 5.5 | $0.00018 | $0.01102 |
| Haiku 4.5 | $0.00009 | $0.00551 |
Grade C, and why
figure-creation 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 1mo 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.
Fix any errors and warnings before proceeding to visual verification with `snap`. To suppress a collision warning for an intentional overlap, place `<!-- lint-ignore collision -->` before the component. How it starts
The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Create, edit, or plan figures in Stencila Markdown (.smd) documents. Figures wrap images or executable output with captions, auto-numbered labels, cross-references, multi-panel grid layouts, and SVG annotation overlays.
If the user asks for strategy, options, or a figure specification rather than immediate file edits, provide a plan that covers the recommended figure structure, layout, caption approach, overlay strategy, and any missing inputs. Do not imply that implementation has already happened.
References
Condensed references for quick lookup (try these first):
references/figure-syntax-cheatsheet.md— figure syntax, labels, layouts, padding, and overlay block structurereferences/layout-cookbook.md— copy-paste multi-panel layout patternsreferences/overlay-patterns.md— common overlay annotation recipes and anchor patternsreferences/overlay-components-quick-ref.md— condensed attribute tables for all<s:*>components
Full documentation (large — load only when the condensed references are insufficient):
references/figures.smd— complete figures documentation (763 lines)references/figure-overlay-components.smd— full overlay component reference with demos (980 lines)references/inspect-image-tool.md— fullinspect_imagetool reference for coordinate inspectionreferences/lint-svg-tool.md— fulllint_svgtool reference for overlay static analysisreferences/snap-tool.md— fullsnaptool reference for visual verification
Required Inputs
| Input | Required | Description |
|---|---|---|
Target .smd file or figure location |
Required | Which document and where in it the figure should go, or which existing figure should be revised |
| Source images, existing figure content, or executable code/data | Required | The content the figure will display or the current figure material to revise |
| Caption text or intent | Required | What the caption should say or convey |
| Annotation/overlay intent | Optional | What to annotate, highlight, or label |
| Panel order and layout preference | Optional | How subfigures should be arranged |
| Calibration or scale info | Optional | Known scale for scale bars (e.g., "130px = 20 μm") |
| Orientation semantics | Optional | Axis meanings for compass indicators (e.g., N/S, A/P D/V) |
| Image dimensions | Optional | Pixel dimensions if precise overlay coordinates matter |
| Delivery mode | Optional | Whether the user wants design/specification guidance or an actual .smd edit |
What ships with it
9 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.
- references/figure-overlay-components.smd 61 B
- references/figure-syntax-cheatsheet.md 3.9 KB
- references/figures.smd 43 B
- references/inspect-image-tool.md 58 B
- references/layout-cookbook.md 2.8 KB
- references/lint-svg-tool.md 53 B
- references/overlay-components-quick-ref.md 8.0 KB
- references/overlay-patterns.md 6.4 KB
- references/snap-tool.md 42 B
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.
- 1mo ago First seen · 453 lines · 92 tokens per session scan C 7f1b6cc81c31
figure-creation is a skill published in the GitHub repository stencila/stencila (913 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 5,508 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
fin-viz-launch
A tool for turning research data and a written description into academic charts. It can choose a suitable chart type, create plotting code with matplotlib or seaborn, and save the result as a high-resolution PDF, SVG, or PNG.
data-science-visualization
A workflow for choosing and producing data visualisations from supplied data. It focuses on selecting a chart that answers the stated question, preserving units and limits, and delivering a viewable HTML file with the chart.
Bio Image Processing Skills Index
Skills for biological image analysis: cell/nucleus segmentation, image restoration, and spatial data processing.
Single-Cell Analysis Skills Index
Core skills for single-cell RNA-seq analysis: quality control, cell type annotation, and trajectory inference. These are high-priority actionable workflows — load them first for common single-cell tasks.
tao-generate-video-reasoning-annotations
Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets"…
sc-markers
Load when ranking cluster-level marker genes from a clustered single-cell AnnData via Scanpy Wilcoxon / t-test / logreg or COSG specificity. Skip when comparing condition-vs-control with replicates (use sc-de); assigning cell-type labels (use sc-cell-annotation).