Borrowing it
Nothing to install: this file belongs to chrischall/canvas-parent-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chrischall/canvas-parent-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/chrischall/canvas-parent-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/instructions/chrischall/canvas-parent-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/canvas-parent-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/canvas-parent-mcp/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.
<a href="https://agentmods.dev/instructions/chrischall/canvas-parent-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/canvas-parent-mcp/claude-md.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 | $0.03919 | $0.03919 |
| Opus 5 | $0.01959 | $0.01959 |
| Sonnet 5 | $0.00784 | $0.00784 |
| Haiku 4.5 | $0.00392 | $0.00392 |
Grade A, and why
canvas-parent-mcp 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 4d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
canvas-parent-mcp
MCP server for Canvas LMS (Instructure). Stdio transport, read-mostly tools scoped for student self-access and parent observers (mirrors sibling infinitecampus-mcp's parent-portal scope).
The npm package is canvas-parent-mcp because canvas-mcp and canvas-lms-mcp are both taken. Tools, env vars, and the user-facing skill stay branded canvas / Canvas because that's what users say.
Commands
npm run build # tsc + esbuild bundle → dist/
npm test # tsc typecheck + vitest run (all tests)
npm run test:watch # vitest in watch mode
npm run dev # node --env-file=.env dist/index.js (needs prior build)
dist/ is gitignored; CI rebuilds it and the published npm tarball includes it (files array in package.json).
Bins
canvas-parent-mcp→dist/index.js— the MCP server (stdio).canvas-parent-mcp-qr-login→dist/qr-login-cli.js— one-off helper that decodes a Canvas mobile-login QR URL and prints OAuth env vars to stdout. Used for SSO accounts that can't use username/password.
Architecture
src/
index.ts # MCP server entry — loads dotenv, runs resolveAuth(), builds client, registers all tools
auth.ts # resolveAuth(): four-path priority (token → OAuth → session-scrape → fetchproxy → error). Template for sibling MCPs
config.ts # loadAccount(env) → discriminated union Account = TokenAccount | SessionAccount | OAuthAccount
client.ts # CanvasClient: auth+401-retry, pagination, download. Custom error types. Accepts a `refreshSession` browser lift from the fetchproxy path
session-login.ts # POSTs /login/canvas form, harvests pseudonym_credentials cookie (legacy path 3)
qr-login.ts # Mobile QR → mobile_verify.json → authorization_code exchange → OAuth tokens (bootstraps path 2)
qr-login-cli.ts # Thin CLI wrapper around qr-login (printed as env vars)
view.ts # CV_VIEWS/viewArg/viewResponse — the `view` rung (compact default, full opt-in). Wired ONLY into the reads whose Canvas payload embeds a user object; see its docblocks for the KEEP/DROP reasoning
tools/
_shared.ts # textContent(), buildPath(), userSegment(), is404(), toArray()
profile.ts announcements.ts calendar.ts conversations.ts
courses.ts discussions.ts files.ts grades.ts
observees.ts planner.ts submissions.ts assignments.ts
tests/ # Mirrors src/. Mocks CanvasClient.request/requestPaginated/download via vi.spyOn
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.
- 4d ago Changed · +35 lines · +564 tokens per session 88336f9835e4
- 8d ago First seen · 191 lines · 3,355 tokens per session scan A b54ee5c01551
canvas-parent-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/canvas-parent-mcp (0 stars, last pushed today), licensed MIT. It adds 3,919 tokens to every session, about $0.0196 per session on Opus 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.