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 skills add build-with-dhiraj/ai-workflow-framework-portability-kit --skill json-rendergit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/json-render)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/json-render"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/json-render/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/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/json-render"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/json-render.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 | $0.00045 | $0.02645 |
| Opus 5.5 | $0.00018 | $0.01058 |
| Sonnet 5.5 | $0.00009 | $0.00529 |
| Haiku 4.5 | $0.00005 | $0.00265 |
Grade A, and why
json-render 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Chat Response Rendering
You are an expert in rendering AI SDK v6 chat responses — UIMessage parts, tool call results, streaming states, and structured data display in React applications.
The Problem
When building chat interfaces with AI SDK v6, the raw message format includes multiple part types (text, tool calls, reasoning, images). Without proper rendering, responses appear as raw JSON or malformed output.
AI SDK v6 Message Format
In v6, messages use the UIMessage type with a parts array:
interface UIMessage {
id: string
role: 'user' | 'assistant'
parts: UIMessagePart[]
}
// Part types:
// - { type: 'text', text: string }
// - { type: 'tool-<toolName>', toolCallId: string, state: string, input?: unknown, output?: unknown }
// state values: 'partial-call' | 'call' | 'output-available' | 'approval-requested' | 'approval-responded' | 'output-denied'
// - { type: 'reasoning', text: string }
// - { type: 'step-start' } // internal, skip in rendering
Recommended: Use AI Elements
The simplest approach is to use AI Elements, which handles all part types automatically:
import { Message } from '@/components/ai-elements/message'
import { Conversation } from '@/components/ai-elements/conversation'
{messages.map((message) => (
<Message key={message.id} message={message} />
))}
⤳ skill: ai-elements — Full component library for AI interfaces
Manual Rendering Pattern
If you need custom rendering without AI Elements, follow this pattern:
'use client'
import { useChat } from '@ai-sdk/react'
import { DefaultChatTransport } from 'ai'
export function Chat() {
const { messages, sendMessage, status } = useChat({
transport: new DefaultChatTransport({ api: '/api/chat' }),
})
const isLoading = status === 'streaming' || status === 'submitted'
return (
<div>
{messages.map((message) => (
<div key={message.id}>
{message.parts?.map((part, i) => {
// 1. Text parts — render as formatted text
if (part.type === 'text' && part.text.trim()) {
return (
<div key={i} className={
message.role === 'user'
? 'bg-primary text-primary-foreground rounded-lg px-3 py-2'
: 'bg-muted rounded-lg px-3 py-2'
}>
{part.text}
</div>
)
}
// 2. Tool parts — type is "tool-<toolName>"
if (part.type.startsWith('tool-')) {
const toolPart = part as {
type: string
toolCallId: string
state: string
input?: unknown
output?: unknown
}
const toolName = toolPart.type.replace('tool-', '')
if (toolPart.state === 'output-available' && toolPart.output) {
return <ToolResultCard key={i} name={toolName} output={toolPart.output} />
}
if (toolPart.state === 'output-denied') {
return (
<div key={i} className="text-sm text-muted-foreground">
{toolName} was denied
</div>
)
}
if (toolPart.state === 'approval-requested') {
return (
<div key={i} className="text-sm text-yellow-500">
{toolName} requires approval
</div>
)
}
return (
<div key={i} className="text-sm text-muted-foreground animate-pulse">
Running {toolName}...
</div>
)
}
// 3. Reasoning parts
if (part.type === 'reasoning') {
return (
<details key={i} className="text-xs text-muted-foreground">
<summary>Thinking...</summary>
<p className="whitespace-pre-wrap">{(part as { text: string }).text}</p>
</details>
)
}
// 4. Skip unknown types (step-start, etc.)
return null
})}
</div>
))}
</div>
)
}
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 · 361 lines · 45 tokens per session scan A 3c6067cb2dc0
json-render is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 20d ago), licensed MIT. It adds 45 tokens to every session and 2,645 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 2026-09-21.
Other skills, from other repositories
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
huggingface-best
Find and compare recommended Hugging Face models for a task using benchmarks, model size, and device constraints. Use for model selection questions; use huggingface-local-models for GGUF setup and hf-cli for Hub operations.
mcp-builder
Guide the creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when the user wants to build an MCP server to integrate an external API or service, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
huggingface-community-evals
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .evalresults publication, or community-evals automation.