Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Canvas-LMS-MCP/canvas-teacher-mcpnpx agentmods add skills/canvas-lms-mcp/canvas-teacher-mcp/gradeWrote 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/canvas-lms-mcp/canvas-teacher-mcp/grade)<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/grade"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/grade/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/canvas-lms-mcp/canvas-teacher-mcp/grade"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/grade.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 | $0.00147 | $0.04582 |
| Opus 5.5 | $0.00059 | $0.01833 |
| Sonnet 5.5 | $0.00029 | $0.00916 |
| Haiku 4.5 | $0.00015 | $0.00458 |
Grade A, and why
grade 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 2mo 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
grade — the runbook
Run THIS to grade. Never hand-roll fetch / score / post.
GRADING A QUIZ / EXAM? Read GRADING.md PART D (scored per QUESTION, never
fudge_points) and CourseGlobalWorkflow/README.md §the same symmetry on the GRADING side
(a quiz is 3 tiers: graders/quiz.py only ITERATES attempt × question and calls the SAME type
graders; a question carries its OWN published rubric, which outranks any grader default).
Everything else on this page applies to a quiz unchanged.
Policy → GRADING.md · Flow → skills/grade/SKILL.md · Engine contracts → GradingEngine/*.
This file is the ORDER. It does not re-explain them. Incident history → Appendix, bottom.
THE LOOP (memorize)
READ instructions → RUBRIC from them → Stage A (--rubric) → READ evidence (Read tool)
→ judge → render → table → self-challenge → [go + gate] → POST
5 RULES THAT DECIDE PASS/RE-RUN
- READ FIRST. The assignment page — every quiz QUESTION too — before the engine runs.
grade_skill.py … --fetch-instructionswrites<code>_instructions.md, grades nothing. - RUBRIC = THE PAGE. Pass it:
--rubric. Engine default is never the answer. - EVIDENCE =
ReadTOOL. Batch severalReadcalls in ONE message.cat/sedleaves no record → the view-gate blocks the post. Same round-trips, so there is no speed argument. - NEVER TRUNCATE (§0Z). Full text, every screenshot VIEWED, at the ENGINE path.
- ENGINE + POLICY ONLY. No new scripts. Missing capability → add it to the engine or ask.
Each is checked mechanically later. Skipping buys a re-run, never time.
GATES — test, never ask
| Gate | Effect |
|---|---|
| post-gate | posting (even dry-run) blocked unless the instructor opened ~/.claude/.post-gate from a real terminal. You cannot open it. |
| code-gate | no new .py/.js/.sh. Extend canonical code by Edit. |
| view-gate | post ABORTS if any manifest artifact was never Read. Contract: GradingEngine/ViewGate.md. |
| quote gate | report_generator refuses a render whose evidence[item].quote is not a real substring of the student's work. |
| comment gate | comment_render raises unless every below-max row has a reason + a For full marks: fix. |
| floor gate | the render refuses any student whose total falls below their Canvas entered_score. Override with "allow_lower": true + a reason. |
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.
- 2mo ago First seen · 294 lines · 147 tokens per session scan A 47e822de1b47
grade is a skill published in the GitHub repository Canvas-LMS-MCP/canvas-teacher-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 147 tokens to every session and 4,582 once invoked, about $0.0006 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 2026-08-31.
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…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
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.