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 bruchris/canvas-lms-mcp --skill canvas-accessibility-sweepgit clone --depth 1 https://github.com/bruchris/canvas-lms-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/bruchris/canvas-lms-mcp/canvas-accessibility-sweep)<a href="https://agentmods.dev/skills/bruchris/canvas-lms-mcp/canvas-accessibility-sweep"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-accessibility-sweep/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/bruchris/canvas-lms-mcp/canvas-accessibility-sweep"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-accessibility-sweep.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 | $0.00131 | $0.01902 |
| Opus 5 | $0.00066 | $0.00951 |
| Sonnet 5 | $0.00026 | $0.00380 |
| Haiku 4.5 | $0.00013 | $0.00190 |
Grade A, and why
canvas-accessibility-sweep 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Accessibility Sweep
A read-only pre-launch pass over a course's content that flags structurally-detectable accessibility problems (WCAG 2.1) and broken or stale links, then hands you a prioritised remediation list. Built for the moment before a term starts — or right after a course copy — when you want to catch the issues that silently break for students before they do.
What this skill does NOT do
canvas-lms-mcp exposes two read-only audit tools for this workflow — audit_course_accessibility and audit_course_links. There is no fix tool: neither the accessibility domain nor the link domain can edit content. This skill therefore surfaces and prioritises problems; the actual edits happen in the Canvas Rich Content Editor. Do not claim to have "fixed" anything.
Two limits are worth stating up front so you don't over-promise:
- No color-contrast checking.
audit_course_accessibilitydoes structural checks only — it cannot see rendered theme CSS, so it does not evaluate text/background contrast. For contrast, point the user at Canvas's own in-app Accessibility Checker (course navigation → Accessibility → Scan Course), which this skill complements rather than replaces. - No outbound link-reachability checking.
audit_course_linksdoes structural checks only — it does not make HTTP requests, so it cannot tell you whether an external URL returns 404. It finds cross-course references (links still pointing at a previous copy of the course — the canonical stale-copy failure after an import) and empty or malformed URLs. A link to a genuinely dead external site will not be flagged.
Prerequisites
- Canvas MCP server must be running and connected.
- Instructor (or TA/designer) permissions on the course are required. Both audit tools return 403 without them.
- Content in the target course must be created before the sweep is meaningful — running it on an empty shell finds nothing.
Steps
1. Identify the Target Course
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 · 108 lines · 131 tokens per session scan A f6b88ffa89fd
canvas-accessibility-sweep is a skill published in the GitHub repository bruchris/canvas-lms-mcp (5 stars, last pushed today), licensed MIT. It adds 131 tokens to every session and 1,902 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
ship-feature
End-to-end feature delivery — implement a feature, verify builds/tests pass, open a fully-filled draft PR, then automatically push every feedback round and review iteration to the same PR. Use when the user asks to implement or build a feature, fix-and-ship a change, or iterate on an existing feature PR.
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
Vibe Coding Mastery
The complete operating system for building software with AI. From first prompt to production deployment — prompting frameworks, architecture patterns, testing strategies, debugging playbooks, and production graduation checklists. Works with Claude Code, Cursor, Windsurf, Copilot, and any AI coding tool.
workshop-testing
Walk through the .NET AI Workshop as an attendee to validate that the READMEs, commands, and code snapshots still work. USE FOR: testing the workshop, testing a specific Part, dry-running the labs, verifying a README against its snapshot, reconciling or refreshing code snapshots, producing a workshop test report. DO…
Automation Interview Prep
Prepare for SDET and automation interviews round by round, covering coding screens, framework design, API testing tasks, scenario questions, and STAR stories built from real testing work.
paperlab_exam_alignment
Check whether a PaperLab course book prepares students for the associated exercises and exams. Use this when a book has source folders with exams, exercise PDFs, review chapters, learning objectives, or end-of-chapter questions.