What is canvas-control CLAUDE.md?

A project guide for Canvas LMS tools: a command-line program for managing course files, grades, and assignments, plus a server that connects these actions to AI assistants.

Use it when developing or maintaining the Canvas LMS command-line tool or its AI-assistant integration.

It gives coding assistants the project structure, setup steps, and important command details they need to work on the codebase correctly.

How tomtranjr/canvas-control configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tomtranjr/canvas-control. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tomtranjr/canvas-control/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tomtranjr/canvas-control

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tomtranjr/canvas-control/claude-md/github.svg)](https://agentmods.dev/instructions/tomtranjr/canvas-control/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tomtranjr/canvas-control/claude-md"><img src="https://agentmods.dev/badge/instructions/tomtranjr/canvas-control/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tomtranjr/canvas-control/claude-md"><img src="https://agentmods.dev/badge/instructions/tomtranjr/canvas-control/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,927 This file is loaded in full into every session.

When invoked 2,927 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02927	$0.02927
Opus 5.5	$0.01171	$0.01171
Sonnet 5.5	$0.00585	$0.00585
Haiku 4.5	$0.00293	$0.00293

Measured 2mo ago against content hash b942ca4e4486, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

canvas-control CLAUDE.md 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.

CLAUDE.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to AI assistants working on the canvas-control codebase.

Project Overview

canvas-control is a Canvas LMS CLI and MCP server. It provides:

A command-line tool (cvsctl) for downloading course files, viewing grades, and submitting assignments
An MCP (Model Context Protocol) server (cvsctl-mcp) for AI assistant integration (Claude Desktop, Cursor, Claude Code)

Package name: canvasctl (import path) / canvas-control (PyPI name) CLI entry point: cvsctl MCP entry point: cvsctl-mcp

Repository Layout

canvas-control/
├── pyproject.toml              # Project config, dependencies, entry points
├── uv.lock                     # Locked dependency versions
├── README.md                   # User-facing documentation
├── docs/
│   ├── cli-reference.md        # Full command tree and flags
│   ├── configuration.md        # Token setup and path config
│   └── guides.md               # Workflow examples and troubleshooting
├── scripts/
│   └── canvas-health-check.py  # Standalone health check utility
├── src/canvasctl/              # Main package
│   ├── __init__.py
│   ├── __main__.py             # Delegates to cli.main()
│   ├── auth.py                 # Token resolution (env var or prompt)
│   ├── canvas_api.py           # Canvas REST API client (httpx)
│   ├── cli.py                  # Typer CLI — all commands live here
│   ├── config.py               # TOML config load/save via platformdirs
│   ├── courses.py              # Course formatting/sorting helpers
│   ├── downloader.py           # Download orchestration and task planning
│   ├── grades.py               # Grade display, sorting, CSV/JSON export
│   ├── interactive.py          # questionary-based interactive TUI
│   ├── manifest.py             # Download manifest persistence
│   ├── mcp_server.py           # FastMCP server exposing Canvas tools
│   └── sources.py              # Content source extraction (files, assignments, etc.)
└── tests/
    ├── conftest.py             # Adds src/ to sys.path
    ├── test_auth.py
    ├── test_canvas_api.py
    ├── test_canvas_api_new_methods.py
    ├── test_cli_assignments.py
    ├── test_cli_config.py
    ├── test_cli_courses.py
    ├── test_cli_download.py
    ├── test_cli_grades.py
    ├── test_config.py
    ├── test_downloader.py
    ├── test_grades.py
    ├── test_live_smoke.py      # Requires real Canvas credentials (marked `live`)
    ├── test_manifest.py
    ├── test_mcp_server.py
    └── test_sources.py

Read the full file on GitHub · 264 lines

Changes

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 · 264 lines · 2,927 tokens per session scan A b942ca4e4486

Subscribe to this mod's changes

canvas-control CLAUDE.md is an instructions file published in the GitHub repository tomtranjr/canvas-control (3 stars, last pushed 7mo ago), licensed MIT. It adds 2,927 tokens to every session, about $0.0117 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.

Learning and teaching

canvas-control CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
canvas-control CLAUDE.mdtomtranjr/canvas-control	Instructions file	3	7mo ago	MIT	A	2,927	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	today	MIT	A	4,335	Codex, OpenCode

canvas-control: Instructions file for Claude Code