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-accessibility-auditorgit 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-accessibility-auditor)<a href="https://agentmods.dev/skills/vishalsachdev/canvas-mcp/canvas-accessibility-auditor"><img src="https://agentmods.dev/badge/skills/vishalsachdev/canvas-mcp/canvas-accessibility-auditor/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/vishalsachdev/canvas-mcp/canvas-accessibility-auditor"><img src="https://agentmods.dev/badge/skills/vishalsachdev/canvas-mcp/canvas-accessibility-auditor.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 | $0.00060 | $0.01540 |
| Opus 5 | $0.00030 | $0.00770 |
| Sonnet 5 | $0.00012 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
canvas-accessibility-auditor 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 9d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Accessibility Auditor
Full accessibility audit cycle for Learning Designers: scan course content, generate a prioritized report, guide remediation of fixable issues, re-scan to verify fixes, and produce an accessibility review summary.
Prerequisites
- Canvas MCP server must be running and connected.
- Authenticated user must have instructor, TA, or designer role in the target course.
- For UFIXIT integration: the course must have a UFIXIT report page (generated by your institution's accessibility tool).
Steps
1. Identify Target Course
Ask the user which course to audit. Accept a course code, Canvas ID, or course name.
If not specified, prompt:
Which course would you like to audit for accessibility?
2. Scan Course Content
Run two scans in parallel if possible:
Scan A -- Direct content scan:
scan_course_content_accessibility(course_identifier, "pages,assignments")
This checks all page and assignment HTML for:
- Images missing alt text (WCAG 1.1.1, Level A)
- Empty headings (WCAG 2.4.6, Level AA)
- Tables missing headers (WCAG 1.3.1, Level A)
- Non-descriptive link text like "click here" (WCAG 2.4.4, Level A)
Scan B -- UFIXIT report (if available):
fetch_ufixit_report(course_identifier)
If the UFIXIT page exists, parse it:
parse_ufixit_violations(report_json)
3. Generate Prioritized Report
Combine results from both scans. Call format_accessibility_summary if using UFIXIT data.
Present issues sorted by priority:
## Accessibility Audit: [Course Name]
### Summary
- Content scanned: 20 pages, 15 assignments
- Total issues: 12
- Auto-fixable: 8 | Manual review needed: 4
### Level A Violations (must fix)
1. **Missing alt text** -- 5 images across 3 pages
- Page "Week 1 Overview": 2 images
- Page "Lab Instructions": 2 images
- Assignment "Final Project": 1 image
2. **Tables missing headers** -- 2 tables
- Page "Grade Scale": 1 table
- Page "Schedule": 1 table
3. **Non-descriptive links** -- 3 instances of "click here"
- Page "Resources": 2 links
- Page "Week 3 Overview": 1 link
### Level AA Violations (should fix)
4. **Empty headings** -- 2 empty heading elements
- Page "Week 5 Notes": 1 empty h3
- Page "Midterm Review": 1 empty h2
### Manual Review Required
- Color contrast: Cannot be checked automatically (requires visual inspection)
- Video captions: Cannot be verified via API (check in Canvas media player)
- PDF accessibility: Cannot be parsed via API (use Adobe Acrobat checker)
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.
- 9d ago First seen · 197 lines · 60 tokens per session scan A e5af383dd46a
canvas-accessibility-auditor is a skill published in the GitHub repository vishalsachdev/canvas-mcp (232 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,540 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…