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 JohannsenLum/canvas-api-mcp --skill canvas-week-plangit clone --depth 1 https://github.com/JohannsenLum/canvas-api-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/johannsenlum/canvas-api-mcp/canvas-week-plan)<a href="https://agentmods.dev/skills/johannsenlum/canvas-api-mcp/canvas-week-plan"><img src="https://agentmods.dev/badge/skills/johannsenlum/canvas-api-mcp/canvas-week-plan/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/johannsenlum/canvas-api-mcp/canvas-week-plan"><img src="https://agentmods.dev/badge/skills/johannsenlum/canvas-api-mcp/canvas-week-plan.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 | $0.00080 | $0.00826 |
| Opus 5.5 | $0.00032 | $0.00330 |
| Sonnet 5.5 | $0.00016 | $0.00165 |
| Haiku 4.5 | $0.00008 | $0.00083 |
Grade A, and why
canvas-week-plan 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Week Plan
Read-only planning skill. Never modify, submit, or post anything: only report what the canvas-api-mcp tools return.
Prerequisites
The canvas-api-mcp MCP server must be installed and connected in the current client.
If tool calls to whats_due, my_courses, or my_submission are not available, tell
the user to install it first: https://mcp.johannsenlum.com/canvas-lms/install
Procedure
-
Get upcoming work. Call the MCP tool
whats_dueto retrieve assignments/items due in the near term. Do not guess or estimate due dates: use only what the tool returns. -
Resolve course names. Call
my_coursesand join each item from step 1 to its course name/code using the course id. Do not invent a course name if it can't be matched: show the raw course id instead and note it's unresolved. -
Disambiguate anything unclear. For any item where submission/completion state is ambiguous or missing from step 1's output, call
my_submissionfor that specific assignment to get its authoritative submitted/graded state. Do not assume "not shown" means "not submitted". Check before reporting. -
Build the table. Present the results as a single table ordered by due date (soonest first), with these columns:
- Course (resolved name, or course id + "(unresolved)")
- Assignment
- Due date/time
- Days remaining (compute from the due date and current time only, do not invent a "today" if it isn't available from context)
- Submitted state (Submitted / Not submitted / Graded / Unknown, from tool output only)
-
Flag risk items, called out clearly below the table (not buried in it):
- Anything due within 48 hours that is NOT submitted: flag explicitly, e.g. "DUE SOON, UNSUBMITTED".
- Any two or more items that share the same due date/day ("same-day collision"): list them together so the student sees the pile-up.
-
Check whether
whats_dueactually answered. If it returns{"error": true, ...}with noitemskey, every source failed to load: that is not an empty schedule. Say Canvas could not be reached and quote thewarnings; never turn a failed read into "nothing is due".
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.
- 1mo ago First seen · 70 lines · 80 tokens per session scan A ffbb99feb323
canvas-week-plan is a skill published in the GitHub repository JohannsenLum/canvas-api-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 826 once invoked, about $0.0003 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
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…
canvas-admin-roster
Admin skill for walking the Canvas account hierarchy: list accounts and sub-accounts, see courses and users under each, look up which canned reports are available, and enroll or remove users from a specific course — one action at a time. Trigger phrases include "admin roster", "list accounts", "sub accounts", "account…
canvas-peer-review-tracker
Educator skill for tracking peer-review assignments in Canvas. Lists who has been asked to review whom, who has submitted versus who is still pending, and lets you assign new reviewers or send reminder messages — one student at a time. Trigger phrases include "peer reviews", "who hasn't done their peer review", "peer…
canvas-course-requirements
Student plan for one Canvas course, built from the requirement graph instead of guessed from raw module flags. Shows what is genuinely left, what is blocked, and what Canvas cannot yet say either way, with the endpoint and field behind every verdict. Trigger phrases include "what do I still have to do in this course"…
canvas-accessibility-sweep
Educator and learning-designer skill for a pre-launch accessibility and broken-link sweep of a Canvas course. Walks the structural accessibility audit and the link audit over a course's pages, assignments, syllabus, announcements, and (optionally) quizzes, then produces a prioritised remediation list you can work…
canvas-course-pulse
Educator skill for tracking week-over-week course health trends in Canvas. Surfaces assignment performance trends, login activity, engagement gaps, and struggling students across a longer time horizon than a daily check. Trigger phrases include "course pulse", "course health", "course trends", "week-over-week…