create-canvas-extension

A tool for creating or registering reusable canvas extensions in the github/awesome-copilot repository.

In plain words
What is it for?
Use it to scaffold an extension, prepare its metadata, add an entry point when requirements are known, and register it as a standalone or existing plugin component.
Why use it?
It helps keep extension metadata, entry points, previews, and plugin registration organized according to that repository's structure.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/github/awesome-copilot/create-canvas-extension
Any agent
npx skills add github/awesome-copilot --skill create-canvas-extension
Clone the repo
git clone --depth 1 https://github.com/github/awesome-copilot

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,171 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.01171
Opus 5 $0.00033 $0.00585
Sonnet 5 $0.00013 $0.00234
Haiku 4.5 $0.00007 $0.00117

Measured 2d ago against content hash 8efc23571f73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-canvas-extension 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 2d 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.

.github/skills/create-canvas-extension/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a canvas extension

Use this skill only for the github/awesome-copilot repository. Canvas extensions are reusable source components. They do not have a plugin.json under extensions/.

Required decisions

Before creating files, ask for each missing value:

  1. Extension ID: lowercase kebab-case, matching the source folder and plugin name.
  2. Display metadata:
    • description
    • version (default 1.0.0)
    • author name and optional URL
    • keywords (lowercase, hyphenated, maximum 10)
    • repository and license (default to the repository URL and MIT when appropriate)
  3. Canvas entrypoint: confirm whether the extension already has extension.mjs. If not, create a minimal entrypoint only when the user provides enough implementation details; otherwise create the directory and leave an explicit TODO.
  4. Preview image: obtain an existing assets/preview.png path or ask the user to add it. Do not invent a binary image or silently use a misleading placeholder.
  5. Plugin registration:
    • For a standalone installable canvas plugin, create plugins/<extension-id>.
    • For an extension that belongs to an existing plugin, ask for the parent plugin ID and add ./extensions/<extension-id> to that plugin's extensions.com.github.awesome-copilot.extensions.
    • If the extension should be shipped by multiple plugins, collect all plugin IDs and add the same extension ID to each mapping file.

Files to create

For a new extension plugin, create this structure:

extensions/<extension-id>/
├── extension.mjs
└── assets/
    └── preview.png

plugins/<extension-id>/
├── plugin.json
└── README.md

The extension source may contain additional files such as package.json, canvas assets, or supporting modules. Keep all reusable implementation files under extensions/<extension-id>/.

Create plugins/<extension-id>/plugin.json with this shape:

{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "<extension-id>",
  "description": "<description>",
  "version": "1.0.0",
  "author": {
    "name": "<author>"
  },
  "repository": "https://github.com/github/awesome-copilot",
  "license": "MIT",
  "keywords": [
    "<keyword>"
  ],
  "extensions": {
    "com.github.copilot": {
      "logo": "assets/preview.png"
    },
    "com.github.awesome-copilot": {
      "extensions": [
        "./extensions/<extension-id>"
      ]
    }
  }
}

Read the full file on GitHub · 125 lines

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. 2d ago First seen · 125 lines · 66 tokens per session scan A 8efc23571f73

Subscribe to this mod's changes

create-canvas-extension is a skill published in the GitHub repository github/awesome-copilot (38,502 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,171 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.