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 xmike04/canvas-student-mcp --skill canvas-grade-checkgit clone --depth 1 https://github.com/xmike04/canvas-student-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/xmike04/canvas-student-mcp/canvas-grade-check)<a href="https://agentmods.dev/skills/xmike04/canvas-student-mcp/canvas-grade-check"><img src="https://agentmods.dev/badge/skills/xmike04/canvas-student-mcp/canvas-grade-check/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/xmike04/canvas-student-mcp/canvas-grade-check"><img src="https://agentmods.dev/badge/skills/xmike04/canvas-student-mcp/canvas-grade-check.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 | $0.00052 | $0.00457 |
| Opus 5 | $0.00026 | $0.00229 |
| Sonnet 5 | $0.00010 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
canvas-grade-check 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 12d 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.
What it actually says
Canvas grade check
Report where the user actually stands, and answer the question behind the question — usually "am I okay?" or "what do I need to get?"
Steps
canvas_get_gradeswith no arguments for the cross-course overview.canvas_grade_breakdownper course for the detail: group weights, what's graded, what's outstanding. Passtarget_gradewhen the user names a goal (90 for an A, 80 for a B, or whatever they say).canvas_get_feedbackwhen a score looks low — the grader's comments usually explain it, and that's more useful than the number.
Reading the results correctly
- Distinguish "0" from "not yet graded." A gradebook placeholder or an ungraded item is not a failing grade. Say which one it is; never report an unearned zero as the user's standing.
- Respect the caveats.
canvas_grade_breakdownreturns acaveatsarray when drop rules, unposted assignment groups, or a mismatch with Canvas's own number make a projection unreliable. Repeat those caveats in your answer — a confident wrong projection about someone's GPA is worse than an honest uncertain one. - Trust Canvas for the official number. When
current_grade_computedandcanvas_reported_current_scoredisagree, report Canvas's figure as authoritative and note the difference. - Early semester: if little is graded, say the number isn't meaningful yet and pivot to what's coming.
Output
Per course: current standing (or "nothing graded yet"), then what remains and what it's worth. For a what-if question, give the direct answer first — "you need a 84% average on the remaining work" — then the arithmetic behind it briefly.
If a target is out of reach, say so plainly and give the best still-achievable outcome. Don't soften it into something misleading.
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.
- 12d ago First seen · 28 lines · 52 tokens per session scan A 5763bed01f44
canvas-grade-check is a skill published in the GitHub repository xmike04/canvas-student-mcp (1 stars, last pushed 18d ago), licensed MIT. It adds 52 tokens to every session and 457 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
schoolbridge
Check school assignments, grades, due dates, and teacher announcements from Canvas (or another LMS) via the schoolbridge CLI. Use when the user asks about homework, upcoming tests, deadlines, grades, study plans, or anything school-related — and on heartbeats/schedules to catch new school activity and report it.
local-rag-search
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of…
octave-literacy
LLM-native structured communication format. Teaches OCTAVE syntax rules, canonical forms, and warning prevention for zero-error .oct.md authoring.
greentext
Explain system behavior, request flows, architecture, or implementation logic as short 4chan-style greentext lines. Use when the user asks for a step-by-step explanation, says "explain the logic", asks for "greentext", or wants terse sequential reasoning with each line starting with >.
canvas-cli
Manage Canvas LMS (https://www.instructure.com/canvas) from the terminal with the canvas CLI — courses, assignments, submissions and grading, modules, pages, quizzes, discussions, announcements, users, enrollments, sections, files, and analytics. Use this whenever the user wants to list or create assignments, grade…
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis with two-column tables. Left column preserves the chapter content; right column maps every idea to the reader's actual life using brain context. Output is a single brain page at media/books/ -personalized plus an optional PDF via brain-pdf.