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 agentmods add instructions/vishalsachdev/canvas-mcp/claude-mdgit clone --depth 1 https://github.com/vishalsachdev/canvas-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/vishalsachdev/canvas-mcp/claude-md)<a href="https://agentmods.dev/instructions/vishalsachdev/canvas-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vishalsachdev/canvas-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.10262 | $0.10262 |
| Opus 5 | $0.05131 | $0.05131 |
| Sonnet 5 | $0.02052 | $0.02052 |
| Haiku 4.5 | $0.01026 | $0.01026 |
Grade A, and why
canvas-mcp CLAUDE.md scanned grade A with 1 finding 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 today.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
so in any working config egress falls back to the in-process Node guard, which `child_process` How it starts
The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Note: This guide is for developers working ON the Canvas MCP codebase. If you're an AI agent USING the MCP server, see AGENTS.md instead.
Canvas MCP Development Guide
Environment Setup
- Install uv package manager:
pip install uv - Install dependencies:
uv pip install -e . - Create
.envfile withCANVAS_API_TOKENandCANVAS_API_URL - Server installed as CLI command:
canvas-mcp-server
Commands
- Start server:
canvas-mcp-server(or./start_canvas_server.shfor legacy setup) - Test server:
canvas-mcp-server --test - View config:
canvas-mcp-server --config - MCP client config: Update your MCP client's configuration file (e.g.,
~/Library/Application Support/Claude/claude_desktop_config.jsonfor Claude Desktop)
Repository Structure
canvas-mcp/
├── src/canvas_mcp/ # Main application code
│ ├── core/ # Core utilities (client, config, validation)
│ ├── tools/ # MCP tool implementations (up to 101 tools across 20 files)
│ ├── resources/ # MCP resources and prompts
│ └── server.py # FastMCP server entry point
├── skills/ # Agent skills for skills.sh (8 skills)
├── tests/ # 900+ tests (pytest + pytest-asyncio)
├── docs/ # GitHub Pages site + guides
├── tools/ # Tool documentation (README.md, TOOL_MANIFEST.json)
├── archive/ # Legacy code (git-ignored)
└── .env # Configuration (CANVAS_API_TOKEN, CANVAS_API_URL)
Architecture Overview
FastMCP server; type-driven validation via @validate_params; dual-layer course code↔ID caching; flexible identifiers (get_course_id()); ISO-8601 dates. Tools use a List→Details→Content→Analytics progressive-disclosure pattern, grouped by Canvas entity, named {action}_{entity}. All Canvas calls route through make_canvas_request() with async I/O, automatic pagination, and configurable anonymization.
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.
- today Changed · +18 lines · +389 tokens per session 2fcc97c6afd9
- 5d ago First seen · 455 lines · 9,873 tokens per session scan A fbc747e69f01
canvas-mcp CLAUDE.md is an instructions file published in the GitHub repository vishalsachdev/canvas-mcp (228 stars, last pushed today), licensed MIT. It adds 10,262 tokens to every session, about $0.0513 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
skills CLAUDE.md
Claude Code instructions for mixedbread-ai/skills, covering mixedbread skills, repository structure, conventions, adding a new skill and testing a skill.
symphony CLAUDE.md
Instructions for broomva/symphony, covering claude.md - symphony, project, gathering context, commands and cli testing.
symphony AGENTS.md
Instructions for broomva/symphony, covering agents.md - symphony, repository purpose, architecture, key design decisions and gathering context from the knowledge graph.
agent-skills AGENTS.md
AGENTS.md instructions for racastellanosm/agent-skills, covering agents.md, 1. vision & architectural invariants, 2. repository architecture & layout, 3. harness support & installation paths and 4. scripting & tooling guardrails.
skillless CLAUDE.md
Instructions for 5kahoisaac/skillless, covering skillless, what it does, key commands, run the main tool and install skills from a category.
skillme CLAUDE.md
Claude Code instructions for shennawardana23/skillme, a project described as: :pagefacingup: Skillme — Agent Skills Production-grade engineering skills for AI coding agents.