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-grading-passgit 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-grading-pass)<a href="https://agentmods.dev/skills/bruchris/canvas-lms-mcp/canvas-grading-pass"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-grading-pass/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-grading-pass"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-grading-pass.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 | $0.00066 | $0.01304 |
| Opus 5 | $0.00033 | $0.00652 |
| Sonnet 5 | $0.00013 | $0.00261 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
canvas-grading-pass 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Grading Pass
Work through an assignment's ungraded submissions one at a time — viewing the student's work, applying the rubric, entering a score, and adding a comment — with a confirmation gate before each write operation.
Prerequisites
- Canvas MCP server must be running and connected.
- You must have instructor or TA role in the target course.
- The assignment must accept online submissions (file upload, text entry, URL, etc.).
Steps
1. Select the Course and Assignment
Ask the instructor which course and assignment to grade.
If unclear, call list_courses to let them choose a course, then call list_assignments (with the course ID) to select an assignment. Prefer assignments with workflow_state=published and a past due date.
2. Load the Rubric (if attached)
Call list_rubrics for the course to see available rubrics. If the assignment has an associated rubric (check rubric_id in the assignment object from get_assignment), call get_rubric with that rubric ID to retrieve criteria, rating descriptions, and point values.
Display the rubric criteria to the instructor before grading begins so they have it in view throughout.
3. Retrieve Ungraded Submissions
Call list_submissions_awaiting_grading with the course ID and assignment_ids=[<assignment>] to get exactly the submissions still needing a grade — it filters to workflow_state=submitted and pending_review for you and returns them oldest-waiting first, so you grade the longest-waiting students first. (Falling back to list_submissions and filtering workflow_state=submitted locally also works if you want the full submission list.) Present the count:
"Found [n] ungraded submissions for [Assignment]. Grading one at a time."
For assignments with more than 50 students, note: pace your session — Canvas rate-limits write operations. Take a short break between batches of 20–25 submissions if you encounter slowdowns.
4. Grade Each Submission (one at a time)
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 · 126 lines · 66 tokens per session scan A 91c7bc44b204
canvas-grading-pass is a skill published in the GitHub repository bruchris/canvas-lms-mcp (5 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 1,304 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 2026-08-31.
Other skills, from other repositories
stage-and-commit
Stage changed files and create a commit following the repo's translation, formatting, and git workflow rules. Use when the user asks to stage, commit, or both.
live-tutorial
Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application. Use when asked for a tutorial video, not merely to watch an action live.
read-book
When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work. Reads in chunks (by chapter when a TOC exists, by 50-page blocks otherwise), extracts per-chapter TL;DR + key concepts + quotes + action items + frameworks, and offers to…
subscription-setup
A setup workflow for creating recurring medical-learning subscriptions after a doctor’s profile has been registered.
habit-formation
Atomic habits, cue-routine-reward loops, habit stacking, accountability systems, and behavior change.
magpie-onboarding-concierge
Answer a newcomer's "how do I contribute here" question by grounding the response in CONTRIBUTING.md and the project's own docs. Classifies the question (setup / workflow / first-issue / out-of-scope), retrieves the relevant guide excerpt, and drafts a concise answer in the Agentic Mentoring teaching register. Routes…