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 HK-hub/AgentSkills --skill json-canvasgit clone --depth 1 https://github.com/HK-hub/AgentSkillsWrote 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/hk-hub/agentskills/json-canvas)<a href="https://agentmods.dev/skills/hk-hub/agentskills/json-canvas"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/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/hk-hub/agentskills/json-canvas"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/json-canvas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.02225 |
| Opus 5 | $0.00027 | $0.01112 |
| Sonnet 5 | $0.00011 | $0.00445 |
| Haiku 4.5 | $0.00005 | $0.00222 |
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 8d 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.
This is a copy
100% identical to json-canvas — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JSON Canvas Skill
File Structure
A canvas file (.canvas) contains two top-level arrays following the JSON Canvas Spec 1.0:
{
"nodes": [],
"edges": []
}
nodes(optional): Array of node objectsedges(optional): Array of edge objects connecting nodes
Common Workflows
1. Create a New Canvas
- Create a
.canvasfile with the base structure{"nodes": [], "edges": []} - Generate unique 16-character hex IDs for each node (e.g.,
"6f0ad84f44ce9c17") - Add nodes with required fields:
id,type,x,y,width,height - Add edges referencing valid node IDs via
fromNodeandtoNode - Validate: Parse the JSON to confirm it is valid. Verify all
fromNode/toNodevalues exist in the nodes array
2. Add a Node to an Existing Canvas
- Read and parse the existing
.canvasfile - Generate a unique ID that does not collide with existing node or edge IDs
- Choose position (
x,y) that avoids overlapping existing nodes (leave 50-100px spacing) - Append the new node object to the
nodesarray - Optionally add edges connecting the new node to existing nodes
- Validate: Confirm all IDs are unique and all edge references resolve to existing nodes
3. Connect Two Nodes
- Identify the source and target node IDs
- Generate a unique edge ID
- Set
fromNodeandtoNodeto the source and target IDs - Optionally set
fromSide/toSide(top, right, bottom, left) for anchor points - Optionally set
labelfor descriptive text on the edge - Append the edge to the
edgesarray - Validate: Confirm both
fromNodeandtoNodereference existing node IDs
4. Edit an Existing Canvas
- Read and parse the
.canvasfile as JSON - Locate the target node or edge by
id - Modify the desired attributes (text, position, color, etc.)
- Write the updated JSON back to the file
- Validate: Re-check all ID uniqueness and edge reference integrity after editing
What ships with it
1 file 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.
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.
- 8d ago First seen · 245 lines · 54 tokens per session scan A 97d1ae072895
json-canvas is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 25d ago), licensed MIT. It adds 54 tokens to every session and 2,225 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to json-canvas, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
mermaid
Create, validate, and repair Mermaid.js diagrams. Use when generating flowcharts, sequence, class, ER, state, or Gantt diagrams, or any visualization.
loft
Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks.…
plannotator-annotate
Open Plannotator's annotation UI for a file, folder, or URL, then address the returned annotations.
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…