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 kamiazya/whiteboard --skill drawing-visualsgit clone --depth 1 https://github.com/kamiazya/whiteboardWrote 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/kamiazya/whiteboard/drawing-visuals)<a href="https://agentmods.dev/skills/kamiazya/whiteboard/drawing-visuals"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/drawing-visuals/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/kamiazya/whiteboard/drawing-visuals"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/drawing-visuals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 257 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00058 | $0.03893 |
| Opus 5 | $0.00029 | $0.01946 |
| Sonnet 5 | $0.00012 | $0.00779 |
| Haiku 4.5 | $0.00006 | $0.00389 |
Grade A, and why
drawing-visuals 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 2d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
drawing-visuals
Like a whiteboard on the wall of a meeting room, this is a tool for AI and humans to align by drawing on the same workspace. Use it when drawing and pointing is faster than iterating in prose. What you draw stays on the document and can be revisited and refined later.
Coverage note. The whiteboard MCP surface is deliberately small: edit nodes and edges, tidy the layout, render SVG, save/restore versions. There is no icon or template library, no align/distribute, and no viewport control. Plan the diagram with that ceiling in mind rather than assuming a full-featured drawing-app tool set.
Use these tools:
wb_document_create/wb_document_list/wb_document_resolve/wb_document_delete— create, find, and remove documentswb_canvas_edit— the whole spatial-editing surface. One call takes a list of ops (add, patch, remove, lock, tidy) and applies them as a single transaction. Passmode: "apply": the default proposes content changes for a person to adopt, because nobody watches an agent type — but somebody just asked you to draw this, and they are looking at itwb_canvas_snapshot— read a canvas: node types, text, geometry and lock state, plus every edge. Passlayout: trueto also get the laid-out analysis (overlaps, clusters, free regions) for judging whether the board is tidywb_scene_render— render the laid-out scene as SVG (the only export format)wb_version_save/wb_version_list/wb_version_restore— checkpoint and roll back
Open references/reading-map.md first and read only the note you need.
references/reading-map.md: the routing note that tells you which guidance to open for which kind of diagramstyle-reference.md: the deep reference for coordinates, color, and layout recipes; open only when neededvisual-vocabulary.md: the deep reference for labeling, diagram choice, and anti-patterns; open only when needed
Do not read style-reference.md and visual-vocabulary.md end-to-end every time.
Choose the diagram type through the reading map, then open only 1-2 relevant notes.
If you need the collaborative workflow for tightening the visual together while talking with the user, also open ../coauthoring-visuals/SKILL.md.
This drawing-visuals skill covers canvas operations, diagram vocabulary, and drawing mechanics.
coauthoring-visuals covers context gathering, iterative refinement, and fresh-viewer testing.
What ships with it
15 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/cloud-and-network-zones.md 2.6 KB
- references/comparison-splits.md 2.0 KB
- references/dark-mode-techniques.md 2.7 KB
- references/decomposition-and-trees.md 1.9 KB
- references/flow-and-architecture.md 2.5 KB
- references/infrastructure-diagrams.md 4.0 KB
- references/layered-architectures.md 1.9 KB
- references/pipelines-and-roadmaps.md 1.7 KB
- references/reading-map.md 3.3 KB
- references/review-and-comparison.md 1.6 KB
- references/sequence-and-decisions.md 1.6 KB
- references/trust-boundary-and-security.md 2.1 KB
- references/workflows-and-swimlanes.md 1.8 KB
- style-reference.md 12 KB
- visual-vocabulary.md 13 KB
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.
- 2d ago Changed · +13 lines cd2329ff0083
- 5d ago Changed · +3 lines b399eb63e565
- 9d ago First seen · 272 lines · 58 tokens per session scan A adebf8397a4f
drawing-visuals is a skill published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 3,893 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
html-ppt-zhangzara-studio
A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…