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 TerminalSkills/skills --skill canvagit clone --depth 1 https://github.com/TerminalSkills/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/terminalskills/skills/canva)<a href="https://agentmods.dev/skills/terminalskills/skills/canva"><img src="https://agentmods.dev/badge/skills/terminalskills/skills/canva/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/terminalskills/skills/canva"><img src="https://agentmods.dev/badge/skills/terminalskills/skills/canva.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 11 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 88 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 90 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Tool Misuse · line 128 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 28 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 83 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 151 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 156 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 162 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium MCP Rug Pull · line 47 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Data Exfiltration · line 83 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 150 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00136 | $0.03304 |
| Opus 5.5 | $0.00054 | $0.01322 |
| Sonnet 5.5 | $0.00027 | $0.00661 |
| Haiku 4.5 | $0.00014 | $0.00330 |
Grade A, and why
canva scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: "Any MCP client for the connector; any HTTP client (curl, Node 18+, Python 3.9+) for the REST API. Canva account — Pro for resize/brand templates, Enterprise for autofill and brand kits" How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canva — Design Automation via MCP and the Connect API
Overview
Canva exposes two automation surfaces, and picking the wrong one wastes an afternoon:
| AI Connector MCP | Connect REST API | |
|---|---|---|
| Endpoint | https://mcp.canva.com/mcp |
https://api.canva.com/rest/v1/ |
| Auth | client-managed OAuth (browser once) | OAuth 2.0 + PKCE you implement |
| Best for | interactive work in a chat/agent session | batch jobs, servers, CI, other people's accounts |
| Editing | yes — editing transactions | no (create / autofill / export only) |
Use the MCP connector with a human in the loop; use the Connect API for unattended runs, hundred-row fan-outs, or acting for users other than the developer. (A third server, the Dev MCP at canva.dev, only serves docs for building Canva apps — it does not touch designs.)
Instructions
Setup A — AI Connector MCP
claude mcp add --transport http canva https://mcp.canva.com/mcp
Clients without HTTP transport go through the bridge:
npx -y mcp-remote@latest https://mcp.canva.com/mcp. The first call opens a browser to
authorize the Canva account; the client stores the token. Verify with tools/list.
Tools (rate limit per user per minute in parentheses):
| Group | Tools |
|---|---|
| Designs | generate-design (20), create-design-from-candidate (20), copy-design (20), search-designs (100), get-design (100), get-design-pages (100), get-design-content (100), get-presenter-notes (100), get-export-formats (100), get-design-thumbnail (100) |
| Editing | start-editing-transaction (20), perform-editing-operations (50), commit-editing-transaction (20), cancel-editing-transaction (20) |
| Export / import | export-design (20), import-design-from-url (20), resolve-shortlink (unlimited) |
| Assets | upload-asset-from-url (30), get-assets (100) |
| Folders | create-folder (20), list-folder-items (100), search-folders (100), move-item-to-folder (100) |
| Comments | comment-on-design (100), reply-to-comment (20), list-comments (100), list-replies (100) |
| Pro+ | resize-design (20), search-brand-templates (100), list-brand-kits (100), create-design-from-brand-template (20) |
| Enterprise | autofill-design (60), get-brand-template-dataset (100) |
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 · 217 lines · 136 tokens per session scan A f306b72198fe
canva is a skill published in the GitHub repository TerminalSkills/skills (177 stars, last pushed today), licensed Apache-2.0. It adds 136 tokens to every session and 3,304 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
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.