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 allenhutchison/obsidian-gemini --skill json-canvasgit clone --depth 1 https://github.com/allenhutchison/obsidian-geminiWrote 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/allenhutchison/obsidian-gemini/json-canvas)<a href="https://agentmods.dev/skills/allenhutchison/obsidian-gemini/json-canvas"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/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/allenhutchison/obsidian-gemini/json-canvas"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/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 | $0.00056 | $0.01555 |
| Opus 5 | $0.00028 | $0.00777 |
| Sonnet 5 | $0.00011 | $0.00311 |
| Haiku 4.5 | $0.00006 | $0.00155 |
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 10d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JSON Canvas
Obsidian Canvas files use the open JSON Canvas format: a .canvas file is plain JSON describing nodes (cards) laid out on an infinite spatial board and edges (connections) between them.
Write canvas files with the write_file tool — pass the full JSON as the file content with a .canvas extension. The plugin classifies .canvas as a text file, so read_file returns its JSON for editing. After writing, the user opens the file in Obsidian to see it rendered; remind them a .canvas file shows as raw JSON in a text editor but renders as a board in Canvas view.
Top-Level Structure
{
"nodes": [],
"edges": []
}
Both arrays are optional. nodes holds the cards; edges holds the connections.
Coordinates
The canvas is an infinite 2D plane. Each node has a top-left origin (x, y) and a width/height in pixels. x increases rightward, y increases downward. Lay nodes out with enough spacing that they don't overlap (e.g. step x by width + 100).
Nodes
Every node requires: id, type, x, y, width, height.
id— a unique string. Use a 16-character lowercase hex string (e.g."a1b2c3d4e5f60718"); each id must be unique within the file.color(optional, any node) — a preset"1"–"6"or a hex string like"#FF0000".
Preset colors: "1" red, "2" orange, "3" yellow, "4" green, "5" cyan, "6" purple.
Text node
Holds Markdown content (Obsidian Flavored Markdown is supported, including wikilinks):
{
"id": "6f0ad84f44ce9c17",
"type": "text",
"x": 0,
"y": 0,
"width": 400,
"height": 200,
"text": "# Hello\n\n**Bold** text and a [[Linked Note]]."
}
File node
References a vault file (note, image, PDF, etc.) by path. Optional subpath targets a heading (#Heading) or block (#^block-id):
{
"id": "a1b2c3d4e5f67890",
"type": "file",
"x": 500,
"y": 0,
"width": 400,
"height": 300,
"file": "Folder/My Note.md",
"subpath": "#Overview"
}
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.
- 10d ago First seen · 184 lines · 56 tokens per session scan A 8c27b11e875c
json-canvas is a skill published in the GitHub repository allenhutchison/obsidian-gemini (524 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 1,555 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 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.