canvas

canvas is a skill for Claude Code, Codex from phodal/routa. It costs 33 tokens per session (599 once invoked), scanned A, original, MIT.

A tool for creating or updating a live visual, interactive canvas for a task. The available details do not explain what kinds of canvases it can create.

In plain words
What is it for?
Use it for tasks that call for an interactive visual canvas, such as arranging information or presenting a visual concept.
Why use it?
It provides a shared visual workspace when plain text is not enough, but the input does not specify which particular problem it solves.

Skill for Claude CodeCodex

About the project

Routa is a workspace-based coordination platform for delivering software with multiple AI agents, keeping goals, tasks, sessions, traces, evidence, and review decisions visible on a shared board. It is intended for teams managing agent-assisted development across web and desktop applications. The catalogue contains skills and instructions for working with Routa's delivery workflows.

phodal/routa · 1,809 stars · on GitHub · phodal.github.io

Install

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.

agentmods
npx agentmods add skills/phodal/routa/canvas
Any agent
npx skills add phodal/routa --skill canvas
Clone the repo
git clone --depth 1 https://github.com/phodal/routa

Made for: Claude Code, Codex.

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.

agentmods badge for canvas

README.md
[![agentmods](https://agentmods.dev/badge/skills/phodal/routa/canvas.svg)](https://agentmods.dev/skills/phodal/routa/canvas)
Your own site
<a href="https://agentmods.dev/skills/phodal/routa/canvas"><img src="https://agentmods.dev/badge/skills/phodal/routa/canvas.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00599
Opus 5 $0.00016 $0.00300
Sonnet 5 $0.00007 $0.00120
Haiku 4.5 $0.00003 $0.00060

Measured 5d ago against content hash fb660e0589f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 5d 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.

.agents/skills/canvas/SKILL.md · 46 lines

What it actually says

Use Routa Canvas for this turn.

Canvas behavior:

  • Create or overwrite exactly one *.canvas.tsx file during the tool run.
  • The file content must be the TSX source itself, not markdown.
  • Prefer storing the file under the selected repository when appropriate.
  • Use a short descriptive file name ending in .canvas.tsx.
  • After the file is created, mention the created path briefly.

Source contract:

  • Create a Routa browser canvas as TSX source code.
  • Return only the TSX source.
  • Do not include markdown code fences.
  • Do not include explanations, notes, or prose before or after the code.
  • The source must export default function Canvas() or export default Canvas.
  • Prefer a self-contained component with inline styles.
  • If you import anything, you may only import from react, routa/canvas, routa/canvas/*, @canvas-sdk, or @canvas-sdk/*.
  • Do not use browser globals or side effects such as window, document, fetch, or localStorage.
  • Do not render fake shell chrome such as browser frames, global app shells, left sidebars, or chat panes unless the prompt explicitly asks for it.
  • Keep the composition flat, minimal, purposeful; avoid gradients, emojis, box shadows.

Canvas SDK access:

  • Prefer MCP tool read_canvas_sdk_resource with uri resource://routa/canvas-sdk/manifest.
  • If your provider supports native MCP resource reads, you may read that same URI directly instead.
  • That manifest is the authoritative Canvas SDK index for this session.
  • Then read only the defs resources you actually need from its definitionResources list, preferably through read_canvas_sdk_resource.
  • Import only from routa/canvas or react.
  • If a symbol or prop is not present in those resources, do not invent it.
  • Example definition resources:
  • resource://routa/canvas-sdk/defs/primitives
  • resource://routa/canvas-sdk/defs/hooks
  • resource://routa/canvas-sdk/defs/data-display
  • resource://routa/canvas-sdk/defs/containers
  • resource://routa/canvas-sdk/defs/controls
  • resource://routa/canvas-sdk/defs/charts
  • resource://routa/canvas-sdk/defs/diff-view
  • resource://routa/canvas-sdk/defs/dag-layout
  • If neither direct resource reads nor the helper tool are available, stay conservative and use only the symbols named in the manifest.
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.

  1. 5d ago First seen · 46 lines · 33 tokens per session scan A fb660e0589f9

Subscribe to this mod's changes

canvas is a skill published in the GitHub repository phodal/routa (1,809 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 599 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens