canvas

canvas is a command for Claude Code from tboome33/obsidian-mcp-router. It costs 38 tokens per session (281 once invoked), scanned A, original, Apache-2.0.

A command set for creating and editing Obsidian Canvas files, which are visual layouts containing notes, images, links, and grouped areas. It can create cards, zones, file nodes, and external-link nodes.

In plain words
What is it for?
Use it to create a canvas, add text or files, link web pages, organize nodes into labeled zones, inspect a canvas, or add recent images.
Why use it?
It avoids manually editing the Canvas JSON format and places new items automatically. It also supports read-only inspection and adding recently modified images from a vault folder.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the obsidian-router plugin — 49 skills, 54 commands, 2 agents, 3 hooks, 1 MCP server shipped together

Good fit Use it to create a canvas, add text or files, link web pages, organize nodes into labeled zones, inspect a canvas, or add recent images.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/tboome33/obsidian-mcp-router/canvas
Install

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.

Clone the repo
git clone --depth 1 https://github.com/tboome33/obsidian-mcp-router

Made for: Claude Code.

Or install obsidian-router, the plugin that ships this one along with the rest of its 49 skills, 54 commands, 2 agents, 3 hooks, 1 MCP server.

Wrote 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.

agentmods badge for canvas

README.md
[![agentmods](https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/canvas/github.svg)](https://agentmods.dev/commands/tboome33/obsidian-mcp-router/canvas)
Your own site
<a href="https://agentmods.dev/commands/tboome33/obsidian-mcp-router/canvas"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/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.

agentmods 80×15 button for canvas

Your own site · 80×15
<a href="https://agentmods.dev/commands/tboome33/obsidian-mcp-router/canvas"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/canvas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 281 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00281
Opus 5 $0.00019 $0.00140
Sonnet 5 $0.00008 $0.00056
Haiku 4.5 $0.00004 $0.00028

Measured 12d ago against content hash f815a426abf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 12d 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.

commands/canvas.md · 20 lines

What it actually says

Invoke the canvas skill.

Sub-operations:

  • /canvas new <name> → create at wiki/canvases/<slug>.canvas
  • /canvas add text <canvas> <text> → append a text card
  • /canvas add file <canvas> <vault-relative-path> → append a file/note/image/PDF node
  • /canvas add link <canvas> <url> → append an external link card
  • /canvas zone <canvas> <label> → add a labeled group region
  • /canvas add to zone <canvas> <zone-label> <node> → place inside a zone
  • /canvas list <canvas> → read-only inspection of the canvas
  • /canvas capture recent images <canvas> [folder] → add the most recently modified image files from a vault folder (default _attachments/) as file nodes to the canvas

Canvas file format is JSON; the skill always read-modify-writes the entire file (atomic) since JSON is brittle to patch.

Auto-layout: rightmost+50px for new sibling nodes, wrap rows at 4-wide. Zones go below or right of existing zones.

Changes

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.

  1. 12d ago First seen · 20 lines · 38 tokens per session scan A f815a426abf2

Subscribe to this mod's changes

canvas is a command published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 281 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 2026-08-31.