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 agentmods add skills/stencila/stencila/figure-creationnpx skills add stencila/stencila --skill figure-creationgit clone --depth 1 https://github.com/stencila/stencilaWhat 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 | $0.00092 | $0.05508 |
| Opus 5 | $0.00046 | $0.02754 |
| Sonnet 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 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.
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.
- 3d ago First seen · 453 lines · 92 tokens per session scan C 7f1b6cc81c31
figure-creation is a skill published in the GitHub repository stencila/stencila (900 stars, last pushed 3d ago), licensed Apache-2.0. It adds 92 tokens to every session and 5,508 once invoked, about $0.0005 per session on Opus 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
Skill "fin-viz-launch" from csmar432/finai-research, covering fin-viz-launch, 触发条件, 三种工作模式, 模式一：快速模式 (quick mode) and 关键词 → 预设映射.
protein-function-prediction
Predict protein function and properties from amino acid sequence using BioT5. Use this skill when: (1) You have a protein sequence and want to understand its biological function, (2) You need to identify enzyme activity, pathway involvement, or molecular interactions, (3) You want a concise description of protein…
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.
bulkrna-geneid-mapping
Load when converting gene identifiers between Ensembl, Entrez, and HGNC symbol in a bulk RNA-seq count matrix. Skip when the input is already in the desired identifier system; organisms outside human/mouse; non-bulk-counts inputs.
genomics-variant-annotation
Load when summarising functional impact of an annotated variant CSV — per-IMPACT counts (HIGH / MODERATE / LOW / MODIFIER), top consequences, gene-affected count. Skip when input is a raw VCF (convert with bcftools +split-vep first); calling raw variants (use genomics-variant-calling); filtering VCFs (use…