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.
git clone --depth 1 https://github.com/AgriciDaniel/claude-canvasWrote 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/commands/agricidaniel/claude-canvas/canvas)<a href="https://agentmods.dev/commands/agricidaniel/claude-canvas/canvas"><img src="https://agentmods.dev/badge/commands/agricidaniel/claude-canvas/canvas/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/commands/agricidaniel/claude-canvas/canvas"><img src="https://agentmods.dev/badge/commands/agricidaniel/claude-canvas/canvas.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 | $0.00025 | $0.00297 |
| Opus 5.5 | $0.00010 | $0.00119 |
| Sonnet 5.5 | $0.00005 | $0.00059 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
canvas 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 1mo 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.
What it actually says
Read the canvas skill. Then execute the requested operation.
Usage:
/canvas— show status and list canvases/canvas create [name]— create a new canvas (blank or from template)/canvas add [type] [content]— add a node (image, text, pdf, note, link, mermaid, svg, gif, banana)/canvas zone [name] [color]— create a labeled zone/canvas connect [from] [to] [label]— add an edge between nodes/canvas from banana— import recent AI-generated images/canvas layout [algorithm]— re-layout nodes (auto, grid, dagre, radial, force, linear)/canvas present [topic]— build a presentation canvas/canvas generate [description]— AI-orchestrated full generation/canvas template list— browse 12 archetypes/canvas export png [path]— export to image/canvas list— list all canvases with node counts
If no canvas directory exists, create .canvases/ in the current project.
If wiki/canvases/ exists (claude-obsidian vault), use that instead.
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.
- 1mo ago First seen · 23 lines · 25 tokens per session scan A cf8b1907590c
canvas is a command published in the GitHub repository AgriciDaniel/claude-canvas (301 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 297 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
daily-okr
Run a daily knowledge compound loop (7 KR). Invoke with /daily-okr or "start my daily review".
open
Open the memex vault in Finder or Obsidian.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.