What is Kanvas CLAUDE.md?

A set of instructions for using Obsidian Canvas files as visual task boards, with all changes made through a provided Python command-line tool.

It helps assistants inspect the board, find available tasks, start work, propose subtasks, and update task progress through commands.

It prevents direct edits that could break the board's workflow rules, such as invalid task transitions or dependency cycles.

How XMihura/Kanvas configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to XMihura/Kanvas. 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/XMihura/Kanvas/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/XMihura/Kanvas

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/xmihura/kanvas/claude-md/github.svg)](https://agentmods.dev/instructions/xmihura/kanvas/claude-md)

Your own site

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

Per session 733 This file is loaded in full into every session.

When invoked 733 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	$0.00733	$0.00733
Opus 5	$0.00367	$0.00367
Sonnet 5	$0.00147	$0.00147
Haiku 4.5	$0.00073	$0.00073

Measured 9d ago against content hash 858489337bec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Kanvas 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 9d 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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Canvas Workflow — Agent Instructions

CRITICAL RULE

NEVER edit .canvas files directly. All canvas modifications MUST go through the CLI tool:

python canvas-tool.py "<file>.canvas" <command> [args]

Direct JSON editing of .canvas files is forbidden. The CLI tool enforces workflow rules (valid transitions, cycle detection, blocked states) so you don't have to remember them.

Session Protocol

1. Start of session — read the board

python canvas-tool.py "Project.canvas" status

Review the board state. Run normalize if needed. Report ready tasks, blocked tasks, and any anomalies to the user.

2. Pick a task

python canvas-tool.py "Project.canvas" ready            # see what's available
python canvas-tool.py "Project.canvas" show <TASK-ID>    # read task details
python canvas-tool.py "Project.canvas" start <TASK-ID>   # begin work (red → orange)

If multiple tasks are ready, ask the user which to prioritize.

3. Work on the task

Execute the task. If you discover subtasks, propose them:

python canvas-tool.py "Project.canvas" propose Development "Subtask title" "Description" --depends-on DV-01

Update notes on your in-progress task:

python canvas-tool.py "Project.canvas" edit <TASK-ID> "Updated description with findings."

4. Finish the task

python canvas-tool.py "Project.canvas" finish <TASK-ID>   # orange → cyan

Tell the user what was done. Do NOT attempt to set the card green — only the human does that.

5. Repeat

After the human marks your task green, check for newly unblocked tasks:

python canvas-tool.py "Project.canvas" normalize
python canvas-tool.py "Project.canvas" ready

What you CAN do

Read the board: status, show, list, blocked, blocking, ready, dump
Normalize the board: normalize
Propose tasks: propose or batch (creates purple cards)
Propose groups: propose-group or batch
Start a task: start <ID> (red → orange)
Finish a task: finish <ID> (orange → cyan)
Pause a task: pause <ID> (orange → red)
Edit task text: edit <ID> "<text>" (only orange tasks)
Add dependencies: add-dep <FROM> <TO>

Read the full file on GitHub · 96 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.

9d ago First seen · 96 lines · 733 tokens per session scan A 858489337bec

Subscribe to this mod's changes

Kanvas CLAUDE.md is an instructions file published in the GitHub repository XMihura/Kanvas (195 stars, last pushed 5mo ago), licensed MIT. It adds 733 tokens to every session, about $0.0037 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 2026-08-30.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

Kanvas: Instructions file for Claude Code