canvas-to-code-mapper

canvas-to-code-mapper is an agent for coding agents from opensesh/canvas-to-code. It costs 50 tokens per session (2,154 once invoked), scanned A, original, MIT.

A design-to-code analysis agent that compares a design screenshot with extracted JSX, which is JavaScript and XML used to describe interface components. It maps each visual part to a component file and records design tokens such as shared colours and spacing.

In plain words
What is it for?
Use it to create a component map, classify interface parts, record confidence, and identify where design data should connect to code.
Why use it?
It shows which existing components can be reused and which new ones are needed, reducing guesswork when rebuilding a design.

Agent

Part of the canvas-to-code plugin — 4 commands, 7 agents shipped together

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 agents/opensesh/canvas-to-code/canvas-to-code-mapper
Clone the repo
git clone --depth 1 https://github.com/opensesh/canvas-to-code

Or install canvas-to-code, the plugin that ships this one along with the rest of its 4 commands, 7 agents.

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-to-code-mapper

README.md
[![agentmods](https://agentmods.dev/badge/agents/opensesh/canvas-to-code/canvas-to-code-mapper.svg)](https://agentmods.dev/agents/opensesh/canvas-to-code/canvas-to-code-mapper)
Your own site
<a href="https://agentmods.dev/agents/opensesh/canvas-to-code/canvas-to-code-mapper"><img src="https://agentmods.dev/badge/agents/opensesh/canvas-to-code/canvas-to-code-mapper.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,154 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 $0.00050 $0.02154
Opus 5 $0.00025 $0.01077
Sonnet 5 $0.00010 $0.00431
Haiku 4.5 $0.00005 $0.00215

Measured 4d ago against content hash 436973edf9d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

canvas-to-code-mapper 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 4d 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/canvas-to-code-mapper.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design-to-Code Mapper

You are the keystone agent. Your output — the componentMap — is what makes everything downstream cheap. Every visual unit in the design gets categorised by tier and pointed at a concrete target file. The dashboard's component +/− diff lives or dies by the honesty of your newOrReused flag.

Inputs

Spawned by the PM during Gate 5 with:

  • Extracted JSX at /tmp/<feature>-template.tsx (from canvas-to-code-extractor).
  • Screenshot(s) in .claude-design/<feature>/screenshots/.
  • Consumer config at .canvas-to-code/config.yaml (specifically components_dirs.*).
  • Token map at .canvas-to-code/token-map.yaml.
  • Audit at .canvas-to-code/state/<feature>/audit.md (from canvas-to-code-auditor).
  • The consumer's components/ tree — read it via Glob + Read.

Output

Write a JSON object matching the componentMap shape in the status.json schema. Return it to the PM (which writes it into .canvas-to-code/state/<feature>/status.json).

{
  "totalUnits": 47,
  "byTier": {
    "base":          { "reused": 19, "new":  0 },
    "ds":            { "reused":  4, "new":  1 },
    "custom-shared": { "reused":  0, "new":  8 },
    "custom-page":                  { "new": 12 },
    "net-new":                      { "new":  3 }
  },
  "lowConfidenceCount": 2,
  "iconGaps": ["slack", "asterisk-4-point"],
  "tokenMapDelta": [
    { "hex": "#FE5102", "proposed": "bg-bg-brand-solid", "note": "Aperol CTA color" }
  ],
  "units": [
    {
      "label": "Top nav (3 tabs)",
      "tier": "base",
      "target": "components/base/application/tabs/tabs.tsx",
      "props": "type=\"underline\" size=\"md\"",
      "newOrReused": "reused",
      "confidence": "high",
      "notes": "Matches Brand Hub run; existing primitive"
    }
  ]
}

The tier model

For every visual unit, classify into exactly one tier. Cheapest first; only escalate if the cheaper tier doesn't fit.

Tier Where to look When
base config.yaml.components_dirs.base (default components/base/) Vendor primitive used as-is.
ds config.yaml.components_dirs.ds (default components/ds/) Thin wrapper or token mapping over base.
custom-shared config.yaml.components_dirs.custom_shared (default components/custom/shared/) Cross-page composition.
custom-page config.yaml.components_dirs.custom_pages — see resolution note below (default components/custom/pages/<route>/) Page-scoped composition.
net-new (no primitive) Icon gaps, arbitrary Tailwind values, ad-hoc SVG.

Read the full file on GitHub · 162 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.

  1. 4d ago First seen · 162 lines · 50 tokens per session scan A 436973edf9d6

Subscribe to this mod's changes

canvas-to-code-mapper is an agent published in the GitHub repository opensesh/canvas-to-code (6 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 2,154 once invoked, about $0.0003 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 2026-08-31.

Related

Other agents, from other repositories

claude-design-orchestrator

Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.

yonatangross/orchestkit · 51 tokens

synthesis-master

Grand orchestrator of all LibreUIUX plugins. Coordinates archetypal-alchemy, design-mastery, accessibility, security, performance, and testing agents to create complete, production-ready UI/UX. The conductor of the plugin symphony. Use PROACTIVELY for any comprehensive UI/UX work.

HermeticOrmus/LibreUIUX-Claude-Code · 65 tokens

archetypal-alchemist

Master of Jungian archetypes + Tarot symbolism for UI/UX design. Synthesizes psychological patterns with symbolic color to create meaningful, coherent design systems. Use PROACTIVELY for any UI work involving archetypal themes, symbolic meaning, or when the user wants design with psychological depth.

HermeticOrmus/LibreUIUX-Claude-Code · 66 tokens

design-master

Comprehensive design guide drawing from timeless principles, legendary designers, and historical movements. Masters visual hierarchy, color theory, typography, composition, and translates classical design wisdom into modern implementation. Use PROACTIVELY for any UI/UX design, component creation, or visual…

HermeticOrmus/LibreUIUX-Claude-Code · 59 tokens

visual-historian

Expert in design history, movements, and the evolution of visual culture. Connects contemporary design decisions to their historical roots. Use when exploring design movements, studying legendary designers, or understanding why certain aesthetics feel the way they do.

HermeticOrmus/LibreUIUX-Claude-Code · 50 tokens

gsp-brand-creative-director

Creative director — makes visual identity decisions (logo, color, typography, imagery). Domain skills enrich with technical precision. Spawned by /gsp-brand-identity.

jubscodes/get-shit-pretty · 41 tokens