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 ddcat-ai/open-ai-canvas --skill canvas-contextgit clone --depth 1 https://github.com/ddcat-ai/open-ai-canvasWrote 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/ddcat-ai/open-ai-canvas/canvas-context)<a href="https://agentmods.dev/skills/ddcat-ai/open-ai-canvas/canvas-context"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/canvas-context/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/ddcat-ai/open-ai-canvas/canvas-context"><img src="https://agentmods.dev/badge/skills/ddcat-ai/open-ai-canvas/canvas-context.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 | $0.00037 | $0.00578 |
| Opus 5 | $0.00018 | $0.00289 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
canvas-context 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 11d 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.
What it actually says
画布上下文协议
不要把画布当成一段需要猜测的 JSON。先读取事实，再决定动作：
canvas_get_context：读取语义化节点、真实 id、连接关系、选区、资源清单和stateHash。- 用户说“这个/选中内容”时，补
canvas_get_selection。 - 不知道节点 id 时用
canvas_find_nodes，不要猜 id。 - 已经知道真实节点或连线 id 时，分别用
canvas_get_node/canvas_get_connection精确读取，不要为确认一个对象反复传输整张画布。 - 需要知道画布内生成任务的绑定节点、
taskId、状态、进度或阶段时，用canvas_get_generation_tasks；它只观察画布快照，不等于主动轮询上游。 - 涉及图片、视频、音频参考时用
canvas_get_resources；只有ready=true且有持久化引用的资源才可作为可用素材。 - 看到
loading、error、缺少storageKey/resourceId的节点时，向用户说明它是未就绪或占位状态。
上下文只作为事实来源，不要把 storageKey、内部 id 或资源状态编造成媒体 URL。工具结果返回后，以结果为准继续下一步。
工作流与流水线
用户提出“流水线、工作流、节点图、管线、连线”时，优先使用 canvas_create_workflow，不要用 canvas_create_text_nodes 伪造流程。将阶段拆成真实语义节点：
character_cards：角色拆分图片卡片，实际类型为imagecharacter_three_view：角色三视图，实际类型为imagestoryboard_video：分镜剧情视频，实际类型为videoscript：剧本或分镜文字，实际类型为script
媒体节点要有 prompt 或 content。已知画布素材时，先检索并将真实 node id 放入 referenceNodeIds；工作流内部依赖放入 referenceRefs。工具会自动布局、默认建立顺序连线并返回连接与重叠复核结果。只有结果中的 verification 确认连接实际存在时，才能向用户报告“已连线”。
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.
- 11d ago First seen · 30 lines · 37 tokens per session scan A 549bddb05df8
canvas-context is a skill published in the GitHub repository ddcat-ai/open-ai-canvas (846 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 578 once invoked, about $0.0002 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
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.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.