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 awesome-town/canvas-mcp-skills --skill grade-submissionsgit clone --depth 1 https://github.com/awesome-town/canvas-mcp-skillsWrote 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/awesome-town/canvas-mcp-skills/grade-submissions)<a href="https://agentmods.dev/skills/awesome-town/canvas-mcp-skills/grade-submissions"><img src="https://agentmods.dev/badge/skills/awesome-town/canvas-mcp-skills/grade-submissions/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/awesome-town/canvas-mcp-skills/grade-submissions"><img src="https://agentmods.dev/badge/skills/awesome-town/canvas-mcp-skills/grade-submissions.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 | $0.00093 | $0.04147 |
| Opus 5 | $0.00046 | $0.02073 |
| Sonnet 5 | $0.00019 | $0.00829 |
| Haiku 4.5 | $0.00009 | $0.00415 |
Grade A, and why
grade-submissions 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grade Submissions
Grade every submission for a single Canvas assignment. Drafts scores + 1–2 sentences of feedback per submission, presents a review table, pushes to Canvas only after the teacher confirms.
Grades are not posted to students automatically. The skill writes the grade to Canvas, but whether students see the grade is governed by the assignment's Canvas posting policy (manual vs automatic). If your assignment uses manual posting, grades remain hidden until you click Post Grades in Canvas yourself. The skill will tell you the posting policy before any writes happen.
When to use
A teacher has a Canvas assignment with student submissions and wants AI-assisted grading. Common phrasings:
- "Grade this assignment: https://…/courses/123/assignments/456"
- "Grade the watershed quiz"
- "Score all submissions for the prototyping project"
When NOT to use
- No submissions yet — the skill needs actual student work to grade.
- You want to give per-comment feedback only, no scores — that's a separate manual workflow; this skill always drafts a score (or uses rubric criteria).
- Re-grading a single student — call
grade_submission/grade_with_rubricdirectly via the MCP.
Prerequisites
- canvas-mcp installed and configured.
- For Google Docs/Slides submissions: the Claude Drive MCP (already authenticated in the Claude.ai / Claude Desktop session).
- For visual / image-heavy grading: file-upload submission type works best (the skill renders PDFs and images directly).
A note on pseudonyms during grading
By default, the Canvas MCP returns pseudonymized student names (Student 1, Student 2, …) — that's the FERPA-safe default. The grade itself uses the numeric Canvas user_id (which is always real, never anonymized), so grades attach to the right student regardless of pseudonymization. But the teacher may want to see real names while grading to remember which student is which.
Two options for the teacher:
- Run
create_student_anonymization_mapfirst — gets a real-name → pseudonym mapping for the course (visible only ifCANVAS_MCP_ALLOW_DEANONYMIZE=trueon the server). The teacher uses this as a local lookup while reviewing the draft. - Set
CANVAS_MCP_ALLOW_DEANONYMIZE=truein the MCP server env temporarily — then submission responses include real names. Flip it back tofalseafter the grading session.
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 Changed f708845f6898
- 11d ago First seen · 268 lines · 93 tokens per session scan A 60eb69bd8f14
grade-submissions is a skill published in the GitHub repository awesome-town/canvas-mcp-skills (1 stars, last pushed 8d ago), licensed MIT. It adds 93 tokens to every session and 4,147 once invoked, about $0.0005 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.