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 Canvas-LMS-MCP/canvas-teacher-mcp --skill nb-homework-creategit clone --depth 1 https://github.com/Canvas-LMS-MCP/canvas-teacher-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/canvas-lms-mcp/canvas-teacher-mcp/nb-homework-create)<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/nb-homework-create"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/nb-homework-create/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/nb-homework-create"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/nb-homework-create.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 | $0.00118 | $0.04774 |
| Opus 5.5 | $0.00047 | $0.01910 |
| Sonnet 5.5 | $0.00024 | $0.00955 |
| Haiku 4.5 | $0.00012 | $0.00477 |
Grade A, and why
nb-homework-create 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nb-homework-create — build an NB template the grader can anchor
⛔ READ skills/grade-nb/SKILL.md FIRST. Creation and grading are mirrors: the grader resolves a
question by its anchor (@answer → @anchor → instruction text → position). If you don't stamp the
anchors + answer cells here, the grader falls back to fuzzy/positional matching and flags for manual
review. Stamp them, and grading is deterministic. Policy homes: GRADING.md Part C + NbInspect.md.
1. Anchor the PROBLEM cells (anchor-only; answer = the REGION after it)
Every gradeable problem's instruction (markdown) carries a hidden anchor in its SOURCE — invisible in the Colab render, preserved across "Save a copy" (more robust than cell metadata, which Colab reassigns):
[problem — markdown] <!-- @anchor:P3.1 type=code --> #### Problem 3.1 complete the function …
- Anchor = "grade HERE". Use the instructor's OWN problem number as the id (
@anchor:P3.1,@anchor:E2for "Exercise 2").type=code|explainis a SOFT hint (not a hard gate). Also write the nbgradergrade_idinto metadata for tooling. - No separate
@answercell, no inserted cell. The answer = the REGION from this anchor to the NEXT anchor — whatever the student writes there (a code cell, an edited "Answer here", added cells) is included, and the grader judges code AND explanation together against what the problem asks. - Stamp ONE anchor per REAL problem; SKIP global "run all cells / figure out" instruction cells and pure
examples. Stamper =
nb_create.py stamp --manifest <AI-judged problem list>— READ the template and judge which cells are problems; do NOT keyword-guess (keyword auto-detect is noisy — proven on ch03). - Anchor = a cell the STUDENT fills (graded for correctness). A pre-filled example / run cell needs NO
anchor — completeness (
nb_inspect: executed ÷ non-blank code cells) already enforces "run every cell". BUT a blank "type it yourself" slot left un-anchored is EXCLUDED (_is_blank_code) → graded NOWHERE; to make active-typing practice gradeable + tested, ANCHOR it (with an expected-output line).
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 · 252 lines · 118 tokens per session scan A aac80988b8ac
nb-homework-create is a skill published in the GitHub repository Canvas-LMS-MCP/canvas-teacher-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 118 tokens to every session and 4,774 once invoked, about $0.0005 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.