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/opensesh/canvas-to-codeWrote 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/agents/opensesh/canvas-to-code/canvas-to-code-mapper)<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/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/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="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 | $0.00050 | $0.02154 |
| Opus 5.5 | $0.00020 | $0.00862 |
| Sonnet 5.5 | $0.00010 | $0.00431 |
| Haiku 4.5 | $0.00005 | $0.00215 |
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 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.
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(fromcanvas-to-code-extractor). - Screenshot(s) in
.claude-design/<feature>/screenshots/. - Consumer config at
.canvas-to-code/config.yaml(specificallycomponents_dirs.*). - Token map at
.canvas-to-code/token-map.yaml. - Audit at
.canvas-to-code/state/<feature>/audit.md(fromcanvas-to-code-auditor). - The consumer's
components/tree — read it viaGlob+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. |
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 · 162 lines · 50 tokens per session scan A 436973edf9d6
canvas-to-code-mapper is an agent published in the GitHub repository opensesh/canvas-to-code (7 stars, last pushed 14d ago), licensed MIT. It adds 50 tokens to every session and 2,154 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
gsp-accessibility-auditor
Audits designs and code for WCAG 2.2 AA/AAA compliance. Spawned by /gsp-accessibility or /gsp-project-critique.
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.
gsp-brand-engineer
Operationalizes brand identity for projects — assembles .yml, STYLE.md, token mapping, component specs, guidelines. Spawned by /gsp-brand-guidelines.
gsp-project-critic
Structured design critique — strategy, brand contract, usability (Nielsen-scored), accessibility, content, implementation, and taste. Spawned by /gsp-project-critique.
gsp-brand-auditor
Audits existing brand identities for evolution. Spawned by /gsp-brand-audit.
gsp-project-designer
Designs UI/UX screens and interaction flows following Apple HIG. Spawned by /gsp-project-design.