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 canva-sdks/canva-skills --skill brand-checkgit clone --depth 1 https://github.com/canva-sdks/canva-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/canva-sdks/canva-skills/brand-check)<a href="https://agentmods.dev/skills/canva-sdks/canva-skills/brand-check"><img src="https://agentmods.dev/badge/skills/canva-sdks/canva-skills/brand-check/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/canva-sdks/canva-skills/brand-check"><img src="https://agentmods.dev/badge/skills/canva-sdks/canva-skills/brand-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.01176 |
| Opus 5 | $0.00042 | $0.00588 |
| Sonnet 5 | $0.00017 | $0.00235 |
| Haiku 4.5 | $0.00008 | $0.00118 |
Grade A, and why
canva-brand-check 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Checker
Compare a design against the user's brand kit and report, point by point, where it follows the brand and where it drifts. This is a specialised, brand-aware version of canva-design-feedback: same read-only "read the design, then critique" core, but the rubric is the brand kit. It never edits the design.
The brand-kit data gap — read this first
Canva:list-brand-kits is documented to return brand kit IDs, names, and thumbnails. It may NOT return the machine-readable palette (hex values) and font families. Your approach depends on what you actually get back:
- If the kit exposes colors/fonts → use those exact hex codes and font names as the rubric (precise check).
- If it only exposes a thumbnail/name → you cannot do an exact hex/font match. Fall back to a visual comparison against the kit thumbnail, and ASK the user to paste their brand colors (hex) and fonts so you can check precisely. Be explicit that, without those, the color/font findings are approximate.
Never invent brand colors or fonts. If you don't have the real values, say so.
Reading the design's actual colors and fonts
Canva:get-design-content returns text only — not colors or fonts.
- A read-only editing transaction (
Canva:start-editing-transaction→ inspect →Canva:cancel-editing-transaction, always cancel) reliably gives element text, positions, and sizes. - Colors and fonts are NOT reliably exposed by the transaction — tested: it often returns only text + position + dimension, with no color/font attributes. So the thumbnail is your primary evidence for color and typography. Use any style data the payload happens to include, but never assert a design's hex or font as fact unless it was actually in the payload.
Because both the brand kit (see the gap above) AND the design itself frequently lack machine-readable colors/fonts, brand-check is often a visual comparison (design thumbnail vs. brand-kit thumbnail) plus the user-supplied palette/fonts. Use Canva:get-design-thumbnail for logo placement and overall visual tone.
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 First seen · 79 lines · 84 tokens per session scan A b29218974439
canva-brand-check is a skill published in the GitHub repository canva-sdks/canva-skills (93 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,176 once invoked, about $0.0004 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 2026-08-30.
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.