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 OpenHands/extensions --skill canvas-extension-apigit clone --depth 1 https://github.com/OpenHands/extensionsWrote 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/openhands/extensions/canvas-extension-api)<a href="https://agentmods.dev/skills/openhands/extensions/canvas-extension-api"><img src="https://agentmods.dev/badge/skills/openhands/extensions/canvas-extension-api/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/openhands/extensions/canvas-extension-api"><img src="https://agentmods.dev/badge/skills/openhands/extensions/canvas-extension-api.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 | $0.00152 | $0.04261 |
| Opus 5.5 | $0.00061 | $0.01704 |
| Sonnet 5.5 | $0.00030 | $0.00852 |
| Haiku 4.5 | $0.00015 | $0.00426 |
Grade A, and why
canvas-extension-api 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 11d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Extensions API
Build and validate OpenHands Apps with the Canvas Extensions API, targeting the currently implemented manifest schema 1 and host API 1 routed-page ABI.
Use the naming layers consistently:
- OpenHands Apps - customer-facing category for interfaces people discover, install, enable, and open.
- Apps for Agent Canvas - product phrasing that clarifies where apps run.
- Canvas Extensions API - developer platform used to build apps.
- Canvas extension package - technical artifact containing
canvas-extension.jsonand its entrypoint. - OpenHands Extensions - ecosystem and repository umbrella for apps, skills, plugins, automations, and integrations.
Use current product labels in user-facing instructions: Apps for Agent Canvas, Add app, Installed apps, App source, Enable trusted app, and Build an app. Keep technical identifiers such as canvas-extension.json, /api/canvas-extensions/*, host.extension, and /extensions/* unchanged unless the target implementation changes them.
Treat apps as trusted, same-realm browser code owned by the active Agent Server. Keep the categories distinct: apps extend what people can do in Agent Canvas, plugins extend agent runtime capabilities, and skills provide agent instructions and knowledge.
Prefer the proven App authoring loop
Treat an App as one authenticated browser dependency graph that Canvas imports from a Blob URL. Do not build a hosted SPA: the production result must be exactly one self-contained browser ESM entrypoint that exports activate(host). Always ship this UI package even when it uses an optional package-owned managed backend or a manual/deployment-owned Sidecar. Make the App page the guided UI for service setup after the App is opened. Never treat a service as another browser chunk or an automatic extension install hook.
For a new App, create an independent package in the target repository and implement its own UI, tests, and build tooling. Follow the Vite library-build reference in references/packaging-recipes.md; do not copy a shared starter or introduce a repository-wide runtime/workspace unless the target repository explicitly requires it.
What ships with it
14 files 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.
- .claude-plugin 7 B
- .codex-plugin 7 B
- .plugin/plugin.json 530 B
- README.md 973 B
- references/acceptance-checklist.md 1.6 KB
- references/backend-safety.md 4.6 KB
- references/connections.md 11 KB
- references/native-design.md 12 KB
- references/packaging-recipes.md 2.3 KB
- references/sidecar-pattern.md 6.2 KB
- references/testing-and-installation.md 11 KB
- references/v1-contract.md 16 KB
- scripts/validate-extension.mjs 9.8 KB runs code
- scripts/validate-extension.test.mjs 8.6 KB runs code
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.
- 11d ago Changed · +3 lines · +37 tokens per session 06b10c7f935e
- 18d ago Changed · +31 lines 7f9d2cd77059
- 24d ago First seen · 255 lines · 115 tokens per session scan A a36bcb910714
canvas-extension-api is a skill published in the GitHub repository OpenHands/extensions (167 stars, last pushed today), licensed MIT. It adds 152 tokens to every session and 4,261 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-23.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…