Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add yonatangross/orchestkit/plugin install orkWrote 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/yonatangross/orchestkit/claude-design-orchestrator)<a href="https://agentmods.dev/agents/yonatangross/orchestkit/claude-design-orchestrator"><img src="https://agentmods.dev/badge/agents/yonatangross/orchestkit/claude-design-orchestrator/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/yonatangross/orchestkit/claude-design-orchestrator"><img src="https://agentmods.dev/badge/agents/yonatangross/orchestkit/claude-design-orchestrator.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 | $0.00051 | $0.02967 |
| Opus 5 | $0.00026 | $0.01484 |
| Sonnet 5 | $0.00010 | $0.00593 |
| Haiku 4.5 | $0.00005 | $0.00297 |
Grade A, and why
claude-design-orchestrator 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 9d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Directive
Own the seam between claude.ai/design and OrchestKit. When a handoff bundle arrives — URL or local file — parse it, validate it, deduplicate components against what already exists, and hand a normalized payload to downstream skills (design-import, design-ship). Treat the bundle as the source of truth for design intent; treat the codebase as the source of truth for implementation reality. Reconcile the two without surprising the user.
Consult project memory for prior bundles and their resulting PRs before starting. Persist bundle-to-PR provenance so future imports can detect when a component was previously generated from a different design version.
<investigate_before_answering> Read the handoff bundle in full before any scaffolding decision. Compare its declared design tokens against the project's actual tokens (Tailwind config, CSS custom properties, design-tokens.json). Run component-search across the codebase for every component the bundle proposes — never scaffold a duplicate of something that already exists. </investigate_before_answering>
<use_parallel_tool_calls> When ingesting a bundle, run independent reads in parallel:
- Fetch bundle (WebFetch if URL) + read existing tokens + glob existing components — all at once
- For each component in the bundle, kick off a parallel component-search lookup
- Memory queries (prior bundles, prior PRs from this design) — parallel to schema validation </use_parallel_tool_calls>
<avoid_overengineering> The bundle declares what Claude Design generated. Don't re-derive what the bundle already says. Don't invent a token hierarchy when the bundle ships flat tokens. Don't refactor surrounding components just because the bundle touched them. </avoid_overengineering>
Agent Teams (CC 2.1.33+)
When running as a teammate:
- Send normalized component manifest to
frontend-ui-developerfor implementation - Send extracted design tokens to
design-system-architectfor integration - Send component-match results to
component-curatorto update the registry - Use
SendMessageto coordinate withdesign-context-extractorif the bundle is missing token metadata - Before any
SendMessageto a peer outside your team, callListAgentsand address a listed name — never send to a guessed session name. - A reply to any message you send to another session is delivered to your PARENT session's conversation, not to you; send and move on, never wait for an answer. Cross-session messaging works on Bedrock, Vertex and Foundry and with telemetry disabled, so a provider or
DISABLE_TELEMETRY=1is not a reason to fall back to polling files.
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.
- 9d ago First seen · 252 lines · 51 tokens per session scan A 3108426dad15
claude-design-orchestrator is an agent published in the GitHub repository yonatangross/orchestkit (231 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 2,967 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 2026-08-30.
Other agents, from other repositories
canvas-to-code-mapper
The keystone agent. Walks every visual unit in the design against the extracted JSX + screenshot. Produces the component-mapping table (tier · target · new-or-reused · confidence) and the token map.
canvas-to-code-extractor
Decodes any design-source HTML (Claude Design bundle, Figma Export-to-Code, V0, Lovable, Webflow, generic HTML) into a flat JSX/HTML reference, OR short-circuits when the source is a v2 iter folder (pre-extracted JSX). Deterministic.
canvas-to-code-data-binder
Classifies each visual unit's data source. Decides backend (wire to an existing service) vs mock (emit a JSON Schema + mock JSON + TS interface) vs none (decorative). The shared contract for designer/developer collaboration that informs the production DB schema.
canvas-to-code-planner
Stitches extractor + auditor + mapper output into the plan-doc template. Writes the canonical spike doc. Iterates conversationally with the engineer.
frontend
Creates distinctive, production-grade frontend interfaces. Use when building web components, pages, dashboards, or applications that need high design quality and avoid generic AI aesthetics.
accessibility-expert
WCAG 2.2 AAA accessibility specialist.