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 lululu811/init-knowledge-base --skill json-canvasgit clone --depth 1 https://github.com/lululu811/init-knowledge-baseWrote 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/lululu811/init-knowledge-base/json-canvas)<a href="https://agentmods.dev/skills/lululu811/init-knowledge-base/json-canvas"><img src="https://agentmods.dev/badge/skills/lululu811/init-knowledge-base/json-canvas/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/lululu811/init-knowledge-base/json-canvas"><img src="https://agentmods.dev/badge/skills/lululu811/init-knowledge-base/json-canvas.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 | $0.00075 | $0.02451 |
| Opus 5.5 | $0.00030 | $0.00980 |
| Sonnet 5.5 | $0.00015 | $0.00490 |
| Haiku 4.5 | $0.00007 | $0.00245 |
Grade A, and why
json-canvas 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 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.
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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JSON Canvas 技能
本技能用于创建和编辑符合 JSON Canvas 1.0 规范的 .canvas 文件,实现知识网络的可视化呈现。
文件结构
Canvas 文件是标准 JSON,包含两个顶级数组:
{
"nodes": [],
"edges": []
}
nodes:节点数组(可选)edges:连接节点的边数组(可选)
节点(Nodes)
四种节点类型:text、file、link、group。
通用属性
| 属性 | 必需 | 类型 | 说明 |
|---|---|---|---|
id |
是 | string | 唯一标识符(16位小写十六进制) |
type |
是 | string | 节点类型 |
x |
是 | integer | X 坐标(像素) |
y |
是 | integer | Y 坐标(像素) |
width |
是 | integer | 宽度(像素) |
height |
是 | integer | 高度(像素) |
color |
否 | string | 颜色(预设 "1"-"6" 或 HEX) |
文本节点(text)
{
"id": "6f0ad84f44ce9c17",
"type": "text",
"x": 0,
"y": 0,
"width": 400,
"height": 200,
"text": "# 核心概念\n\n这是 **Markdown** 内容。"
}
换行转义:JSON 字符串中的换行必须写为
\n,不能写字面量\\n。
文件节点(file)
引用 Vault 内的文件:
{
"id": "a1b2c3d4e5f67890",
"type": "file",
"x": 500,
"y": 0,
"width": 400,
"height": 300,
"file": "assets/diagram.png"
}
引用笔记中的特定标题:
{
"id": "b2c3d4e5f6789012",
"type": "file",
"x": 500,
"y": 400,
"width": 400,
"height": 300,
"file": "wiki/concepts/Transformer.md",
"subpath": "#核心组件"
}
链接节点(link)
外部 URL:
{
"id": "c3d4e5f678901234",
"type": "link",
"x": 1000,
"y": 0,
"width": 400,
"height": 200,
"url": "https://obsidian.md"
}
分组节点(group)
视觉容器,用于组织其他节点:
{
"id": "d4e5f6789012345a",
"type": "group",
"x": -50,
"y": -50,
"width": 1000,
"height": 600,
"label": "项目概览",
"color": "4"
}
带背景图:
{
"id": "e5f67890123456ab",
"type": "group",
"x": 0,
"y": 700,
"width": 800,
"height": 500,
"label": "资源",
"background": "assets/background.png",
"backgroundStyle": "cover"
}
背景样式:cover(填充)、ratio(保持比例)、repeat(平铺)。
边(Edges)
连接节点的线条:
{
"id": "f67890123456789a",
"fromNode": "6f0ad84f44ce9c17",
"toNode": "a1b2c3d4e5f67890"
}
完整属性:
{
"id": "0123456789abcdef",
"fromNode": "节点A-ID",
"fromSide": "right",
"fromEnd": "none",
"toNode": "节点B-ID",
"toSide": "left",
"toEnd": "arrow",
"color": "1",
"label": "导致"
}
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 Changed d1baef6852fd
- 1mo ago First seen · 328 lines · 75 tokens per session scan A 840c1ed71ed6
json-canvas is a skill published in the GitHub repository lululu811/init-knowledge-base (23 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 2,451 once invoked, about $0.0003 per session on Opus 5.5. 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 $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.