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/agricidaniel/claude-canvas/claude-mdgit clone --depth 1 https://github.com/AgriciDaniel/claude-canvasWhat 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 | $0.00481 | $0.00481 |
| Opus 5 | $0.00241 | $0.00241 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
claude-canvas 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 yesterday.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-canvas — AI-Orchestrated Visual Production
This is a Claude Code plugin for creating, populating, and laying out Obsidian Canvas files with AI assistance.
What It Does
Claude acts as Creative Director for Obsidian Canvas. Describe what you want — a presentation, mood board, flowchart, or knowledge graph — and get a fully populated, professionally laid-out canvas with AI-generated images, diagrams, and text.
Directory Structure
skills/
canvas/ Main orchestrator — routes commands to sub-skills
canvas-create/ Create blank or templated canvases
canvas-populate/ Add nodes, edges, zones to existing canvases
canvas-layout/ Re-layout with 6 algorithms
canvas-present/ Build presentation-mode canvases for Advanced Canvas
canvas-generate/ AI-orchestrated full canvas generation (flagship)
canvas-template/ Browse and instantiate 12 archetype templates
canvas-export/ Export canvas to PNG/SVG/PDF
agents/ 3 sub-agents: layout, media, composer
scripts/ Python CLI tools (validate, layout, template)
templates/ 12 JSON Canvas archetype templates
bin/ Setup script for optional dependencies
Quick Commands
| You say | Claude does |
|---|---|
/canvas |
List canvases with node counts |
/canvas create my-project |
Create a new canvas |
/canvas add image photo.png |
Add an image node |
/canvas add banana "hero image" |
Generate AI image, add to canvas |
/canvas layout dagre |
Re-layout with hierarchical algorithm |
/canvas present "Q3 Review" |
Build a presentation canvas |
/canvas generate "mood board for game" |
Full AI-orchestrated generation |
/canvas template list |
Browse 12 archetypes |
Canvas Location
- If
wiki/canvases/exists (claude-obsidian vault): uses that - Otherwise: creates
.canvases/in the current project directory
Integration
Works with /banana (AI images), /svg (diagrams), /claude-gif-* (animations) when installed. Gracefully degrades if not available.
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.
- yesterday First seen · 48 lines · 481 tokens per session scan A bfaac10d4bfc
claude-canvas CLAUDE.md is an instructions file published in the GitHub repository AgriciDaniel/claude-canvas (288 stars, last pushed 4mo ago), licensed MIT. It adds 481 tokens to every session, about $0.0024 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.
Other instructions, from other repositories
claude-obsidian GEMINI.md
Gemini CLI instructions for AgriciDaniel/claude-obsidian: Read AGENTS.md as the canonical host-neutral contract. Skills live in skills/ /SKILL.md and the portable core lives in claudeobsidian/.
claude-obsidian AGENTS.md
AGENTS.md instructions for AgriciDaniel/claude-obsidian, covering claude-obsidian: agent instructions, product and vault boundaries, bootstrap, canonical skills and mutation protocol.
claude-obsidian copilot-instructions.md
Copilot instructions for AgriciDaniel/claude-obsidian: Read AGENTS.md before proposing changes. The repository is an Agent Skills package, Claude Code adapter, standard-library Python core, and deterministic vault template—not the default live user vault.
awesome-second-brain CLAUDE.md
Instructions for superuser-pal/awesome-second-brain, covering awesome second brain, rules, skills & capabilities, prompts & strategies and custom slash commands.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.