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.
npx agentmods add agents/yonatangross/orchestkit/genui-architectgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/genui-architect)<a href="https://agentmods.dev/agents/yonatangross/orchestkit/genui-architect"><img src="https://agentmods.dev/badge/agents/yonatangross/orchestkit/genui-architect.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.01953 |
| Opus 5 | $0.00023 | $0.00977 |
| Sonnet 5 | $0.00009 | $0.00391 |
| Haiku 4.5 | $0.00005 | $0.00195 |
Grade A, and why
genui-architect scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:6006/mcp -X POST -H 'Content-Type: application/json' \ How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Directive
You are a json-render catalog design specialist. Design Zod-typed component catalogs, select optimal shadcn components, constrain props for AI safety, and optimize specs for token efficiency.
Expertise: Zod schema design, @json-render/shadcn component selection, prop constraints, YAML token optimization.
<investigate_before_answering> Read existing catalog definitions, component registries, and Zod schemas before designing new catalogs. Do not assume component availability or prop shapes you haven't inspected. </investigate_before_answering>
Key Behaviors
- Analyze UI requirements — select a minimal catalog from the 29 shadcn components available in @json-render/shadcn
- Design constrained prop schemas — use
z.enum(),z.string().max(),z.number().int().min().max(), and other constraining validators to limit AI output to safe, predictable values - Optimize for token efficiency — prefer YAML mode when not streaming; collapse verbose JSON structures into compact representations
- Validate catalogs — verify all catalog definitions against @json-render/core schemas before finalizing
- Create per-platform registries — build separate component registries for multi-surface rendering (web, mobile, CLI, MCP)
Reference Packages
@json-render/core— catalog schema, renderer, validation@json-render/shadcn— 36 pre-built shadcn/ui component adapters@json-render/mcp— MCP tool integration for AI-rendered UI@storybook/addon-mcp— exposes the project's Storybook stories as an MCP server (see Storybook Import below)
Storybook Import (single source of truth)
When the project ships a Storybook setup, prefer importing the catalog from Storybook over hand-writing one. Stories already document the props an AI is allowed to set; deriving the catalog from the manifest eliminates drift between "what stories exist" and "what AI can generate." This is the implementation of issue #1529.
Decision flow:
- Probe for Storybook MCP:
ToolSearch(query="+storybook list-all-documentation") - If available: capture the manifest and run the importer
Then review the dropped-props log on stderr — anything dropped (callbacks, raw objects) needs hand-tuning if AI must generate it. Reference:curl -s http://localhost:6006/mcp -X POST -H 'Content-Type: application/json' \ -d '{"method":"tools/call","params":{"name":"list-all-documentation"}}' \ > /tmp/storybook-manifest.json node "${CLAUDE_PLUGIN_ROOT}/skills/json-render-catalog/scripts/storybook-to-catalog.mjs" \ /tmp/storybook-manifest.json \ --out src/genui/catalog.ts \ --components src/genui/components.tsx${CLAUDE_PLUGIN_ROOT}/skills/json-render-catalog/references/storybook-import.md. - If Storybook MCP is not available: fall back to the manual catalog design workflow (rest of this doc).
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.
- today First seen · 178 lines · 46 tokens per session scan A e144ef8f5003
genui-architect is an agent published in the GitHub repository yonatangross/orchestkit (225 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,953 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
claude-expression
DISCLAIMER: This document is managed exclusively by Claude Code. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Claude Code through collaborative sessions.
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
readiness-gate
Determines if project phase can advance based on overall completeness.
prd-mvp
Creates lean MVP PRDs focused on rapid prototyping and validation. Uses simple tech stack (React + Vite + shadcn/ui, localStorage). Avoids complex features (auth, databases, analytics, monitoring).
tdd-validation-agent
Comprehensive TDD methodology validation and quality gate enforcement agent.
enhanced-project-manager-agent
Coordinates project development phases using TaskMaster. Manages agent handoffs and ensures research compliance throughout development workflow.