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 aileron-platform/aileron --skill aileron-web-canvasgit clone --depth 1 https://github.com/aileron-platform/aileronWrote 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/aileron-platform/aileron/aileron-web-canvas)<a href="https://agentmods.dev/skills/aileron-platform/aileron/aileron-web-canvas"><img src="https://agentmods.dev/badge/skills/aileron-platform/aileron/aileron-web-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/aileron-platform/aileron/aileron-web-canvas"><img src="https://agentmods.dev/badge/skills/aileron-platform/aileron/aileron-web-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 | $0.00069 | $0.01668 |
| Opus 5 | $0.00034 | $0.00834 |
| Sonnet 5 | $0.00014 | $0.00334 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade B, and why
aileron-web-canvas scanned grade B with 1 finding 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 12d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- Do not hand-roll a different preview mechanism: never tell the user to run a How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aileron Web Canvas
Use this skill when the user asks to create, regenerate, or modify a website, page, static HTML canvas, Next.js app, prototype, dashboard, slide-like page, or visual web artifact for Aileron Web Canvas preview.
Core Contract
- Work under
/workspace. - Do not start package managers or dev servers.
- Do not hand-roll a different preview mechanism: never tell the user to run a dev server, share a raw file path, or paste HTML into the chat.
- Canvas is declared only by
/workspace/.aileron/canvas.json. - Ask structured questions with
mcp__aileron__ask_user_question. - Announce completed canvas artifacts with
mcp__aileron__show_canvas_artifact. - Put generated canvas content under
/workspace/.aileron/canvases/aileron-web-canvas/<slug>/. - Do not put active canvas content under
/workspace/canvases/...; relative manifest paths resolve from/workspace/.aileron/. - Set manifest
owner.skillNametoaileron-web-canvas.
Discovery
For a new canvas request whose brief leaves decisions that materially change the
artifact, make the first response one short prose line followed immediately by
mcp__aileron__ask_user_question, then end the turn. Before that form call, do
not read files, run Bash, or write files.
Ask no more than five questions. A question earns its place only when its answer
changes what you would build for this brief. Set each question's default to
your best inference from the brief so the user confirms rather than fills; omit
default only when there is no reasonable basis to infer an answer.
Use option-cards or color only when visual direction is genuinely undecided. Skip questions already answered by the user.
If the user's brief is already specific enough to build without a decision-changing answer, skip the form and start the workflow directly.
Static Canvas
Use static canvas for HTML, CSS, JavaScript, media, diagrams, decks, and prototypes that do not need Next.js.
Expected structure:
/workspace/.aileron/
├── canvas.json
└── canvases/aileron-web-canvas/<slug>/
├── index.html
├── app.js
├── styles.css
└── assets/
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.
- 12d ago First seen · 193 lines · 69 tokens per session scan B c4c6e855a684
aileron-web-canvas is a skill published in the GitHub repository aileron-platform/aileron (11 stars, last pushed 19d ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,668 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…