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 cligit 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/cli)<a href="https://agentmods.dev/skills/canva-sdks/canva-skills/cli"><img src="https://agentmods.dev/badge/skills/canva-sdks/canva-skills/cli/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/cli"><img src="https://agentmods.dev/badge/skills/canva-sdks/canva-skills/cli.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 | $0.00054 | $0.00940 |
| Opus 5.5 | $0.00022 | $0.00376 |
| Sonnet 5.5 | $0.00011 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
canva-cli 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canva CLI
Use the Canva CLI when a request requires direct, programmatic interaction with Canva or local files. Do not use it for purely conversational design work that is better handled through Canva's AI-assisted workflows.
Set up the CLI when needed
Before using the CLI, check whether canva --version succeeds.
If the CLI is unavailable, explain that it requires Node.js v24 and npm v11. Install it only when the user has explicitly requested or approved installation:
npm install -g @canva/cli@latest
Before accessing Canva resources, ensure the intended user is logged in:
canva login
Login opens a browser authorization flow and requires the user to approve access. In a remote or headless environment, use canva login --mode manual. Do not request, print, inspect, or copy the locally stored auth token. When multiple Canva accounts are relevant, require the user to identify the intended profile before running commands against it. Use --profile for a one-off command rather than changing the active profile unless the user asks to switch it.
Find the right operation
Do not guess commands, flags, or request shapes.
- Start with
canva api --help, then narrow by resource group. - Use
canva api <group> <command> --helpto inspect flags. - Use
canva api describe <group> <command>when the command contract is needed as JSON. - CLI commands follow REST API operation names, not URL paths.
- Prefer documented flags. Use
--body @file.jsononly when a nested JSON payload cannot be expressed with flags.
Authenticate and validate
- Commands act as the logged-in Canva account. Run
canva loginwhen needed. - If a request returns
MISSING_SCOPE, log in again before retrying. - Before a command that creates, changes, or uploads content, run it with
--dry-runwhen available to validate its arguments and login without making the API request. - Ensure the target design, folder, asset, or other resource is unambiguous before making a state-changing request.
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.
- 2d ago First seen · 103 lines · 54 tokens per session scan A 5d6ad867acb5
canva-cli is a skill published in the GitHub repository canva-sdks/canva-skills (126 stars, last pushed 2d ago), licensed Apache-2.0. It adds 54 tokens to every session and 940 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 2026-10-17.
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.