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 vishalsachdev/canvas-mcp --skill canvas-course-buildergit clone --depth 1 https://github.com/vishalsachdev/canvas-mcpWrote 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/vishalsachdev/canvas-mcp/canvas-course-builder)<a href="https://agentmods.dev/skills/vishalsachdev/canvas-mcp/canvas-course-builder"><img src="https://agentmods.dev/badge/skills/vishalsachdev/canvas-mcp/canvas-course-builder.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 89 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00064 | $0.01578 |
| Opus 5 | $0.00032 | $0.00789 |
| Sonnet 5 | $0.00013 | $0.00316 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
canvas-course-builder 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 8d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Course Builder
Build complete Canvas course structures from a natural language description, a JSON template, or by cloning an existing course. Creates modules with pages, assignments, discussions, and proper organization in one workflow.
Prerequisites
- Canvas MCP server must be running and connected.
- Authenticated user must have instructor or designer role in the target course.
- Target course must already exist in Canvas (this skill populates it, does not create the course itself).
Modes
This skill operates in three modes:
Mode 1: Build from Spec (default)
The user describes the course structure in natural language or provides a structured spec.
Mode 2: Build from Template
Load a saved JSON template to scaffold a course.
Mode 3: Clone from Existing Course
Read the structure of Course A and replicate it into Course B.
Steps
1. Determine Mode and Gather Input
Ask the user how they want to build:
How would you like to build the course structure?
- Describe it -- Tell me the structure (e.g., "15 weeks, each with an overview page, assignment, and discussion")
- From template -- Load a saved template file
- Clone another course -- Copy structure from an existing course
For Mode 1 (Spec): Ask for:
- Target course (code or ID)
- Number of modules/weeks/units
- Module naming pattern (e.g., "Week N: [Topic]")
- Standard items per module (overview page, assignment, discussion, etc.)
- Any module-specific variations (midterm week, final project, etc.)
For Mode 2 (Template): Ask for the template file path. Parse the JSON template.
For Mode 3 (Clone): Ask for:
- Source course (code or ID)
- Target course (code or ID)
- Call
get_course_structure(source_course)to read the full structure
2. Generate Structure Preview
Build a preview of what will be created and present it to the user:
## Course Build Plan: [Course Name]
### Structure: 15 modules x 4 items each = 60 items total
| Module | Page | Assignment | Discussion | SubHeader |
|--------|------|------------|------------|-----------|
| Week 1: Introduction | Overview | HW 1 (10 pts) | Week 1 Forum | Materials |
| Week 2: Fundamentals | Overview | HW 2 (10 pts) | Week 2 Forum | Materials |
| ... | ... | ... | ... | ... |
| Week 14: Review | Overview | -- | Review Forum | Materials |
| Week 15: Final | Overview | Final Project (100 pts) | -- | Materials |
### Items to create:
- 15 modules
- 15 overview pages
- 14 assignments
- 14 discussion topics
- 15 subheaders
- Total: 73 Canvas objects
Shall I proceed?
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.
- 8d ago First seen · 196 lines · 64 tokens per session scan A 8b91817cf8b2
canvas-course-builder is a skill published in the GitHub repository vishalsachdev/canvas-mcp (231 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,578 once invoked, about $0.0003 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
education-program
When the user wants to plan, implement, or optimize student and education discount programs. Also use when the user mentions "student discount," "education discount," "student plan," "for students," ".edu discount," "academic pricing," "student verification," "SheerID," "UNiDAYS," or "education program." For startup…
startups-page-generator
When the user wants to create, optimize, or audit a startups, education, or special program page. Also use when the user mentions "startups program," "for startups," "education discount," "student plan," "for students," or "special pricing." For education discounts, use education-program.
scout-mindset-bias-check
Detects and removes cognitive biases from reasoning using Julia Galef's Scout Mindset framework. Provides reversal tests, scope sensitivity checks, status quo bias tests, confidence interval audits, and full bias audits. Use when a prediction feels emotional, stuck at 50/50, or when validating forecasting process. Use…
creating-explainers
Use when creating an interactive explainer - a single self-contained HTML page with hand-built Canvas figures. Handles source-file explainers, topic-driven research explainers, and mixed intake where files provide the spine and research adds support. Trigger phrases include "make an explainer", "turn this paper into…
explaining-codebases
Use when creating an interactive explainer about a codebase, repository, or source files. Handles onboarding overviews, architecture maps, and deep-dives on real implementation paths. Trigger phrases include "explain this codebase", "interactive guide to this repo", "walk through how X works in the code", or…
source-driven-development
Grounds framework-specific code decisions in official documentation instead of training data or memory. Use before writing framework- or library-specific code (forms, routing, data fetching, auth, state management), when the user asks for "current best practices" or "documented"/"verified" code, or before reviewing…