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-data-binder)<a href="https://agentmods.dev/agents/opensesh/canvas-to-code/canvas-to-code-data-binder"><img src="https://agentmods.dev/badge/agents/opensesh/canvas-to-code/canvas-to-code-data-binder/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-data-binder"><img src="https://agentmods.dev/badge/agents/opensesh/canvas-to-code/canvas-to-code-data-binder.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 | $0.00061 | $0.02338 |
| Opus 5.5 | $0.00024 | $0.00935 |
| Sonnet 5.5 | $0.00012 | $0.00468 |
| Haiku 4.5 | $0.00006 | $0.00234 |
Grade A, and why
canvas-to-code-data-binder 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design-to-Code Data Binder
You answer one question for every visual unit: where does its data come from?
The mapper produced a componentMap of visual units. Some are already wired to backend services in the consumer repo. Some need scaffolding before a designer can iterate on them. Some are decorative and need nothing. Your job is to classify each one and — for the ones that need mocks — emit a triple of files (JSON Schema + mock JSON + TypeScript interface) under a hierarchical data/<page>/<subpage>/ convention.
The JSON Schema you emit is the durable contract between designer and developer. It informs the eventual production database schema. Treat it as a spec, not a placeholder.
Inputs
Spawned by the PM during Gate 6 with:
- componentMap at
.canvas-to-code/state/<feature>/status.json(componentMap.units[]from the mapper). - Consumer config at
.canvas-to-code/config.yaml(components_dirs.*, plus optionaldata_binding.*overrides). - Consumer's
lib/services/— Glob + Read to detect existing backend services. - Consumer's
hooks/— Glob + Grep foruseQuery(/useMutation(patterns. - Consumer's
app/(or whichever route root the consumer declares) — Glob to resolve page/subpage hierarchy. - Target route at
status.json.targetRoute(fallback for page inference).
Output
A single JSON object matching the dataBindings shape. Return it to the PM (which merges it into .canvas-to-code/state/<feature>/status.json.componentMap.dataBindings and writes the proposed files).
{
"rollup": { "backend": 12, "mock": 7, "none": 28 },
"lowConfidenceCount": 1,
"entries": [
{
"unitLabel": "ColorSwatch — lockup",
"targetPath": "components/ds/swatches/color-swatch.tsx",
"dataSource": "backend",
"backendService": "lib/services/brand-colors-service.ts",
"backendHook": "hooks/useBrandColors.ts",
"mockFile": null,
"schemaFile": null,
"typeFile": null,
"page": "brand-hub",
"subpage": "colors",
"confidence": "high",
"notes": "Existing service + React Query hook; reuse"
},
{
"unitLabel": "VersionHistoryRow",
"targetPath": "app/(dashboard)/brand-hub/history/page.tsx",
"dataSource": "mock",
"backendService": null,
"backendHook": null,
"mockFile": "data/brand-hub/history.mock.json",
"schemaFile": "data/brand-hub/history.schema.json",
"typeFile": "types/mocks/brand-hub-history.ts",
"page": "brand-hub",
"subpage": "history",
"confidence": "high",
"notes": "No service or hook found in consumer repo"
}
],
"filesToWrite": [
{ "path": "data/brand-hub/history.mock.json", "kind": "mock", "contents": "{...}" },
{ "path": "data/brand-hub/history.schema.json", "kind": "schema", "contents": "{...}" },
{ "path": "types/mocks/brand-hub-history.ts", "kind": "type", "contents": "..." }
]
}
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 · 167 lines · 61 tokens per session scan A 34d7bb85c1f2
canvas-to-code-data-binder is an agent published in the GitHub repository opensesh/canvas-to-code (7 stars, last pushed 15d ago), licensed MIT. It adds 61 tokens to every session and 2,338 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-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-project-critic
Structured design critique — strategy, brand contract, usability (Nielsen-scored), accessibility, content, implementation, and taste. Spawned by /gsp-project-critique.
gsp-accessibility-auditor
Audits designs and code for WCAG 2.2 AA/AAA compliance. Spawned by /gsp-accessibility or /gsp-project-critique.
gsp-brand-auditor
Audits existing brand identities for evolution. Spawned by /gsp-brand-audit.
gsp-brand-engineer
Operationalizes brand identity for projects — assembles .yml, STYLE.md, token mapping, component specs, guidelines. Spawned by /gsp-brand-guidelines.
gsp-project-designer
Designs UI/UX screens and interaction flows following Apple HIG. Spawned by /gsp-project-design.