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 brsbl/moss-skills --skill moss-canvasgit clone --depth 1 https://github.com/brsbl/moss-skillsWrote 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/brsbl/moss-skills/moss-canvas)<a href="https://agentmods.dev/skills/brsbl/moss-skills/moss-canvas"><img src="https://agentmods.dev/badge/skills/brsbl/moss-skills/moss-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/brsbl/moss-skills/moss-canvas"><img src="https://agentmods.dev/badge/skills/brsbl/moss-skills/moss-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 | $0.00040 | $0.00649 |
| Opus 5 | $0.00020 | $0.00324 |
| Sonnet 5 | $0.00008 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
moss-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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moss Canvas
Canvas is a rough editable spatial surface, not a text-diagram renderer.
Creation Authority
- Preserve and edit an existing
moss-canvasblock when the task requires it. - Create a new canvas when the user asks for canvas or explicitly requests an editable spatial diagram.
- For a generic diagram, flow, wireframe, menu, or option sketch, use a fenced ASCII code block instead.
- Use an image for a polished static visual, a chart for quantitative shape, and HTML only for genuine interaction.
Use canvas when relative position, connectors, and rough shapes matter more than readable text in the grid. Grid characters become ink; readable words must be label metadata.
Fence And Payload
Create new blocks with moss-canvas. Preserve existing legacy moss-sketch fences rather than renaming them incidentally.
```moss-canvas
[moss:grid:v2]
[moss:labels:[{"id":"research","text":"Research","col":8,"row":4}]]
....########................................
....#......#................................
....########................................
```
This is a complete valid input. Moss accepts up to 60 grid rows of up to 120 characters, pads missing cells as empty, truncates excess cells, and normalizes a saved canvas to exactly 120 columns by 60 rows.
Payload order:
[moss:grid:v2].- Optional single-line
[moss:labels:<JSON array>]. - Grid rows.
Grid rules:
.and spaces are empty.- Every other character becomes filled ink; letters and box-drawing glyphs do not remain readable text.
- Coordinates are zero-based: columns
0-119, rows0-59. - Keep drawings sparse and labels clear of strokes.
Each label object requires:
| Field | Contract |
|---|---|
id |
Unique non-empty string within the canvas. |
text |
Non-empty string; keep it under 80 characters. |
col |
Integer from 0 through 119. |
row |
Integer from 0 through 59. |
Use valid compact JSON on the metadata line. Do not duplicate label IDs or rely on malformed label objects being repaired.
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.
- 10d ago First seen · 74 lines · 40 tokens per session scan A 829e642c51b8
moss-canvas is a skill published in the GitHub repository brsbl/moss-skills (11 stars, last pushed 16d ago), licensed MIT. It adds 40 tokens to every session and 649 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
design
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.
icon-composer-app-icon-workflow
Design, preview, validate, and integrate Apple app icons with Icon Composer. Use when a task mentions Icon Composer, .icon documents, Liquid Glass app icons, ictool preview exports, app icon design for iOS, iPadOS, macOS, or watchOS, or guided Icon Composer GUI work through Computer Use.
sf-symbols-workflow
Guide SF Symbols selection, inspection, customization, rendering modes, variable color, symbol effects, animated symbols, custom symbols, accessibility semantics, availability checks, and Apple app integration. Use when a task mentions SF Symbols, the SF Symbols app, systemImage names, symbolRenderingMode…
apple-typography-workflow
Guide Apple platform typography decisions and implementation across SwiftUI Font, UIKit UIFont, AppKit NSFont, San Francisco system fonts, SF Pro, SF Compact, SF Mono, SF Pro Rounded, New York serif design, Dynamic Type, text styles, fontDesign, fontWeight, fontWidth, monospaced digits, custom font bundle integration…
apple-ui-accessibility-workflow
Guide Apple UI accessibility implementation and review for SwiftUI-first code, with UIKit and AppKit bridge guidance plus explicit verification expectations and testing handoffs. Use when the user wants help making Apple UI accessible, reviewing accessibility semantics, shaping the accessibility tree, or planning…
core-animation-layer-workflow
Guide Core Animation layer-backed rendering and animation decisions for Apple apps, including CALayer trees, layer-backed AppKit and UIKit views, SwiftUI bridges, implicit and explicit CAAnimation, CATransaction, CAMediaTiming, model versus presentation layers, shape, gradient, replicator, emitter, text, tiled, and…