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 subhansh-dev/agent-maxxing --skill 12-canvasgit clone --depth 1 https://github.com/subhansh-dev/agent-maxxingWrote 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/subhansh-dev/agent-maxxing/12-canvas)<a href="https://agentmods.dev/skills/subhansh-dev/agent-maxxing/12-canvas"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/12-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/subhansh-dev/agent-maxxing/12-canvas"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/12-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 | $0.00023 | $0.00583 |
| Opus 5 | $0.00012 | $0.00292 |
| Sonnet 5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
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 5d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas
Use canvas to show HTML on connected Mac/iOS/Android nodes.
Model
- Canvas host serves files from
plugins.entries.canvas.config.host.root. - Canvas routes live on the Gateway HTTP port (
gateway.port, default18789). - Node bridge sends canvas URLs to connected node apps.
- Node apps render URLs in a WebView.
- Host name follows
gateway.bind: loopback local only, LAN IP for LAN, Tailscale host for tailnet, auto picks best route. - Localhost URLs only work for a node on the same machine.
- Paired nodes normally receive node-scoped
pluginSurfaceUrls.canvascapability URLs; prefer those when available.
Config
Active config: $AGENT_CONFIG_PATH or ~/.agent/config.json.
{
"plugins": {
"entries": {
"canvas": {
"config": {
"host": {
"enabled": true,
"root": "~/.agent/canvas",
"liveReload": true
}
}
}
}
},
"gateway": { "bind": "auto" }
}
Actions
present: show canvas, optional URL.hide: hide canvas.navigate: open new URL.eval: run JavaScript in current canvas.snapshot: capture screenshot.
Workflow
- Ensure Canvas plugin host is enabled.
- Put HTML/CSS/JS under
plugins.entries.canvas.config.host.rootor the default state canvas dir. - Use a route reachable by the target node.
- Present the hosted URL:
/<canvas-route>/<file>.html. - Use
snapshotwhen the user needs proof.
URL shape
http://<gateway-host>:<gateway.port>/<canvas-route>/index.html
http://<gateway-host>:<gateway.port>/<canvas-route>/games/snake.html
Path mapping:
/<canvas-route>/index.html-><canvas host root>/index.html/<canvas-route>/games/snake.html-><canvas host root>/games/snake.html
Troubleshooting
- Node sees localhost but is remote: fix
gateway.bindor public URL, regenerate URL. - LAN node cannot load: verify same network, firewall, Gateway port, and auth/capability URL.
- Tailnet node cannot load: verify Tailscale status and advertised host.
- Blank page: open URL locally, check browser console, then snapshot node.
- Live reload missing: verify
liveReloadand file write under root.
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.
- 5d ago First seen · 79 lines · 23 tokens per session scan A 1df2e3ac0fab
canvas is a skill published in the GitHub repository subhansh-dev/agent-maxxing (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 583 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
ux-capture
Capture playbook for the pi-ux render-and-inspect loop: screenshotting a UI you just built via local headless Chrome vs webscreenshot, daemon reachability (localhost vs LAN IP vs host.docker.internal), SSRF-protected daemons, and cloudflared tunnels. Load when setting up render inspection or when a UI screenshot…
url-to-code
Recreate an authorized live website or app URL as a faithful, runnable, frontend-only local implementation.
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.