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 atman-33/workhub --skill json-canvasgit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/json-canvas)<a href="https://agentmods.dev/skills/atman-33/workhub/json-canvas"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/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/atman-33/workhub/json-canvas"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/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 5.5 | $0.00022 | $0.00890 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago First seen · 245 lines · 54 tokens per session scan A 97d1ae072895
json-canvas is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 2,225 once invoked, about $0.0002 per session on Opus 5.5. 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
readmd-style-custom
Generate custom CSS rules and HTML head tags for ReadMD document styling.
readmd-export-style
Use when a ReadMD export needs a validated typography style represented as JSON.
expo-launchpad-design
Phase A design — define the ui/designTokens.ts spec (colors, spacing, radius, typography), the visual/component concept (game: code-drawn Skia shapes / app: RN primitives), and the asset plan (icon+splash branding, contrast-safe accessibility). Advances pipeline state to contract.
video-templates
ฉากวิดีโอที่ก๊อปไปใช้ได้เลย 75 ฉาก ไม่ใช่คำอธิบายว่าฉากควรหน้าตาแบบไหน แบ่งเป็นฉากเคลื่อนไหว 50 แบบ ครบสามอัตราส่วน — นอน 39 ตั้ง 6 จัตุรัส 5สำหรับเรนเดอร์เป็นคลิป (รวมเด็คนักลงทุนและพิตช์เด็คแบบเต็มเรื่อง กับอีก 9 ฉากในภาษาโฆษณาโปรดักต์ที่ถอดจากสเปกและจากการหยุดเฟรมดูคลิปจริง สี่ในนั้นเคลื่อนด้วยสปริงจริงของ Material…
aetox-shadcn
ทำงานกับ shadcn/ui, เพิ่ม ค้น แก้ ดีบัก สไตล์ และประกอบคอมโพเนนต์/ดีไซน์ซิสเทม ผ่าน registry และ CLI พร้อมกฎที่บังคับเสมอ (className สำหรับ layout ไม่ใช่สไตล์, ใช้ gap ไม่ใช่ space-x/y, size- เมื่อกว้างเท่าสูง, semantic colors, cn()) ใช้ตอนโปรเจกต์มี components.json หรือทำงานกับ shadcn/Tailwind/Base UI, "shadcn init"…
aetox-slide-templates
เทมเพลตจริงที่ก๊อปไปใช้ได้เลย ไม่ใช่คำอธิบายว่าควรหน้าตาแบบไหน เลย์เอาต์สไลด์ 41 แบบ รวมไดอะแกรม 16 แบบที่วาดด้วย CSS กับ SVG ในไฟล์เอง ชุดสี 6 โทนใน themes/ และม่านบนภาพ 5 แบบใน overlays/ ที่สลับได้ด้วยการเปลี่ยนบล็อก :root บล็อกเดียว กล่อง 1280x720 ไฟล์เดียวจบ ไม่มี CSS ภายนอก ไม่มีสคริปต์ ไม่มีกราฟจาก CDN…