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-course-requirementsgit 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-course-requirements)<a href="https://agentmods.dev/skills/bruchris/canvas-lms-mcp/canvas-course-requirements"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-course-requirements/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-course-requirements"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-course-requirements.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 | $0.00107 | $0.02331 |
| Opus 5.5 | $0.00043 | $0.00932 |
| Sonnet 5.5 | $0.00021 | $0.00466 |
| Haiku 4.5 | $0.00011 | $0.00233 |
Grade A, and why
canvas-course-requirements 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 6d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Course Requirements
Turn one Canvas course into an honest plan — what you still owe, what you cannot act on yet, and what Canvas simply has not told anyone. This workflow reads a single composite tool and presents its verdicts. It does not decide them, and it must never second-guess them.
Prerequisites
- Canvas MCP server must be running and connected.
- You must be authenticated as a student enrolled in the course. The verdicts below depend on it — Canvas attaches per-requirement completion only where it loaded a module progression, which it does only for a student caller. An educator or admin token produces a course full of
unknown, not a course full of work.
Steps
1. Read the requirement graph — one call, and only this call
Call get_my_course_requirements with the course ID (ask for it if the user has not given one).
include_discussionsdefaults to true and adds the discussion obligations that are not module completion requirements. Leave it on unless the user only wants modules.include_contextdefaults to false. Turn it on only when the user asks "when should I do this", and read the caveat in step 7 first.max_modulesbounds the walk. Raise it only if step 2 says the result was truncated.
This tool is the single source of truth for this workflow. Do not rebuild the graph from list_modules, list_module_items, list_discussions, get_my_submissions or get_course_structure. Those return a raw completion_requirement without the cross-references that make it truthful, so every rule in the output below would turn back into a guess — and the guess is silent and confidently wrong. If get_my_course_requirements returns an error, report the error and stop. Do not substitute lower-level calls, and do not fill a gap in its output by inferring completion from a submission list, a module flag, a discussion entry or a planner item.
For a different question, use a different tool rather than this one plus arithmetic — project_grade or explain_grade for grade outcomes, get_my_grades for posted scores, list_my_planner_items for the cross-course week.
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.
- 6d ago First seen · 118 lines · 107 tokens per session scan A fc6e5d4a1796
canvas-course-requirements is a skill published in the GitHub repository bruchris/canvas-lms-mcp (10 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 2,331 once invoked, about $0.0004 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 2026-10-22.
Other skills, from other repositories
education-expert
Expert-level education technology, learning management systems, and ed-tech platforms. Use when the user mentions edtech, lms, e learning, or assessment, or when the task involves Educational Technology or Standards.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
write-changelog
Write ClassroomIO's weekly customer changelog from the previous week's shipped work. Produce a concise customer email, a separate changelog-site article and a step-by-step demo walkthrough backed by seeded demo data, capture framed PNG screenshots, and draft the Resend broadcast. Use every Monday when preparing the…
add-landing-template
Add a new org landing-page template to the ClassroomIO monorepo. Use when the user asks to "create/add a new landing template", "add a new template like X to the org landing pages", "build a new theme for the org landing page", or hands over a design reference (image, URL, prototype) for a new landing visual style.