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 jackspooner/agentcanvas --skill agentcanvas-demonstrationgit clone --depth 1 https://github.com/jackspooner/agentcanvasWrote 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/jackspooner/agentcanvas/agentcanvas-demonstration)<a href="https://agentmods.dev/skills/jackspooner/agentcanvas/agentcanvas-demonstration"><img src="https://agentmods.dev/badge/skills/jackspooner/agentcanvas/agentcanvas-demonstration/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/jackspooner/agentcanvas/agentcanvas-demonstration"><img src="https://agentmods.dev/badge/skills/jackspooner/agentcanvas/agentcanvas-demonstration.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 | $0.00061 | $0.01768 |
| Opus 5.5 | $0.00024 | $0.00707 |
| Sonnet 5.5 | $0.00012 | $0.00354 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade A, and why
agentcanvas-demonstration 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentCanvas Demonstration
Create one attractive demonstration canvas that teaches by showing. The result should feel like a small product tour, not a random test board: clear hierarchy, spacious layout, a few contrasting element types, and a truthful handoff that explains what was persisted and what was visually checked.
Use the agentcanvas skill for the underlying canvas mutation, inspection,
diagnostic, coordinate, and truth-discipline rules. This skill adds the
demonstration narrative and default-install selection logic.
Demonstration promise
Show the new user these capabilities when the active runtime supports them:
- A structured canvas with a title, subtitle, sections, and a coherent theme.
- Core text, shapes, and connectors arranged as a simple agent workflow.
- A Markdown card for richer explanatory content.
- A table for compact structured comparison.
- Image cards sourced from the user or image search, when available.
- Agent-facing persistence and diagnostics: create, inspect, repair, and report a direct canvas URL.
- Host-owned macros when the generic macro tools are present: create or use a tiny versioned definition, preview it, then execute it as one atomic action.
Do not claim that a capability is available because it exists in documentation
or source folders. First call canvas_get_guidance and canvas_list_plugins,
then adapt to the returned active registry. A default install normally includes
the core canvas plus the standard Markdown, primitives, table, overlay, video,
GLB, and image-source extensions, but the runtime response is authoritative.
Walkthrough workflow
1. Discover and set expectations
- Read
canvas_get_guidanceif available. - Call
canvas_list_pluginsand record active element types, tools, and diagnostics capabilities. - Start a new canvas unless the user supplied an existing canvas to tour.
- Ask the user for two to four images they would like displayed, or ask for a visual theme if they do not have specific images. If they provide local files, URLs, or asset references, use those references according to the active runtime contract. If they do not provide images or prefer the agent to choose, use the available web/image search tools to find a small, coherent set of suitable image URLs. Do not silently invent image sources.
- Explain internally that this is a demonstration board and that generated copy is illustrative, not product documentation or researched fact.
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 · 163 lines · 61 tokens per session scan A 3a80eabb4835
agentcanvas-demonstration is a skill published in the GitHub repository jackspooner/agentcanvas (0 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 1,768 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
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.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.