Scan
Read configured Canvas courses, bucket pending work by urgency, and write a plan instead of starting work immediately.
Local-first Canvas LMS agent
A workflow layer for recurring Canvas coursework. It scans Canvas, writes an approval plan, and executes only approved draft-and-review workflows through reusable course patterns.
$ scan canvas
plan.json written | 5 items | waiting for approval
| # | Course pattern | Workflow | Boundary |
|---|---|---|---|
| 1 | Weekly code assignment | spec -> tests -> bundle | review draft |
| 2 | Reading annotation | PDF -> notes -> checks | review draft |
| 3 | Problem set | fetch -> solve -> render | review PDF |
$ approve 1,2
OK executing approved workflows only
OK result.json per item
WAIT REPORT.md ready for student review
What it does
Canvas API tools can tell an agent what exists in Canvas. Canvas Pilot is built around what repeats: where a course hides its real specs, which output format the instructor expects, what verification checks matter, and where the student must approve the next action.
Read configured Canvas courses, bucket pending work by urgency, and write a plan instead of starting work immediately.
The student reviews the plan and chooses what can run. The approval boundary is part of the product, not a prompt suggestion.
Approved items dispatch into course-specific workflows that produce review-ready drafts, result files, and a run report.
Who it is for
Canvas Pilot makes the most sense if you already use local agent tooling such as Codex or Claude Code and want repeated Canvas work to become a one-command workflow.
If you are not comfortable running an agent locally, reading a report, and reviewing generated drafts before submission, this is not the right product shape yet.
Start here