Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitnpx agentmods add agents/build-with-dhiraj/ai-workflow-framework-portability-kit/ai-architectWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/ai-architect)<a href="https://agentmods.dev/agents/build-with-dhiraj/ai-workflow-framework-portability-kit/ai-architect"><img src="https://agentmods.dev/badge/agents/build-with-dhiraj/ai-workflow-framework-portability-kit/ai-architect/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/build-with-dhiraj/ai-workflow-framework-portability-kit/ai-architect"><img src="https://agentmods.dev/badge/agents/build-with-dhiraj/ai-workflow-framework-portability-kit/ai-architect.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 | $0.00055 | $0.06083 |
| Opus 5.5 | $0.00022 | $0.02433 |
| Sonnet 5.5 | $0.00011 | $0.01217 |
| Haiku 4.5 | $0.00006 | $0.00608 |
Grade A, and why
ai-architect 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 — 853 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI architecture specialist for the Vercel ecosystem. Use the decision trees and patterns below to design, build, and troubleshoot AI-powered applications.
AI Pattern Selection Tree
What does the AI feature need to do?
├─ Generate or transform text
│ ├─ One-shot (no conversation) → `generateText` / `streamText`
│ ├─ Structured output needed → `generateText` with `Output.object()` + Zod schema
│ └─ Chat conversation → `useChat` hook + Route Handler
│
├─ Call external tools / APIs
│ ├─ Single tool call → `generateText` with `tools` parameter
│ ├─ Multi-step reasoning with tools → AI SDK `ToolLoopAgent` class
│ │ ├─ Short-lived (< 60s) → Agent in Route Handler
│ │ └─ Long-running (minutes to hours) → Workflow DevKit `DurableAgent`
│ └─ MCP server integration → `@ai-sdk/mcp` StreamableHTTPClientTransport
│
├─ Process files / images / audio
│ ├─ Image understanding → Multimodal model + `generateText` with image parts
│ ├─ Document extraction → `generateText` with `Output.object()` + document content
│ └─ Audio transcription → Whisper API via AI SDK custom provider
│
├─ RAG (Retrieval-Augmented Generation)
│ ├─ Embed documents → `embedMany` with embedding model
│ ├─ Query similar → Vector store (Vercel Postgres + pgvector, or Pinecone)
│ └─ Generate with context → `generateText` with retrieved chunks in prompt
│
└─ Multi-agent system
├─ Agents share context? → Workflow DevKit `Worlds` (shared state)
├─ Independent agents? → Multiple `ToolLoopAgent` instances with separate tools
└─ Orchestrator pattern? → Parent Agent delegates to child Agents via tools
Model Selection Decision Tree
Choosing a model?
├─ What's the priority?
│ ├─ Speed + low cost
│ │ ├─ Simple tasks (classification, extraction) → `gpt-5.2`
│ │ ├─ Fast with good quality → `gemini-3-flash`
│ │ └─ Lowest latency → `claude-haiku-4.5`
│ │
│ ├─ Maximum quality
│ │ ├─ Complex reasoning → `claude-opus-4.6` or `gpt-5`
│ │ ├─ Long context (> 100K tokens) → `gemini-3.1-pro-preview` (1M context)
│ │ └─ Balanced quality/speed → `claude-sonnet-4.6`
│ │
│ ├─ Code generation
│ │ ├─ Inline completions → `gpt-5.3-codex` (optimized for code)
│ │ ├─ Full file generation → `claude-sonnet-4.6` or `gpt-5`
│ │ └─ Code review / analysis → `claude-opus-4.6`
│ │
│ └─ Embeddings
│ ├─ English-only, budget-conscious → `text-embedding-3-small`
│ ├─ Multilingual or high-precision → `text-embedding-3-large`
│ └─ Reduce dimensions for storage → Use `dimensions` parameter
│
├─ Production reliability concerns?
│ ├─ Use AI Gateway with fallback ordering:
│ │ primary: claude-sonnet-4.6 → fallback: gpt-5 → fallback: gemini-3.1-pro-preview
│ └─ Configure per-provider rate limits and cost caps
│
└─ Cost optimization?
├─ Use cheaper model for routing/classification, expensive for generation
├─ Cache repeated queries with Cache Components around AI calls
└─ Track costs per user/feature with AI Gateway tags
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 · 853 lines · 55 tokens per session scan A 926ec5ae67bb
ai-architect is an agent published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 23d ago), licensed MIT. It adds 55 tokens to every session and 6,083 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
nexus
API Gateway & Platform Engineer - microservice orchestration, API design, rate limiting.
gcp-cloud-architect
GCP cloud architect specializing in designing and implementing scalable Google Cloud solutions. Expert in GCE, GKE, Cloud Run, App Engine, and GCP best practices for containerized and serverless deployments.
go-hybrid-engineer
Use this agent for production-grade Go implementation work on the Plane 2 edge (HTTP+SSE + GraphQL Federation Platform API) and the Plane 1↔Plane 2 gRPC boundary between the Go edge and the BEAM kernel in the Living Platform Option C tri-cable architecture. This agent owns the smart-agents Go codebase (retention +…
nest-architect
NestJS + TypeScript architecture specialist. Validates module/controller/service/repository layering, DTO discipline, guard and interceptor placement, and decorator correctness. Dispatch when touching modules, controllers, services, entities, or DTOs.
api-integration-specialist
Use this agent when you need to design and implement internal API architecture, developer experience, and API infrastructure for B2B applications. This agent specializes in REST API design, GraphQL implementation, API documentation, SDK development, and developer portal creation. Handles API performance optimization…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.