ai-solution-architect

ai-solution-architect is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 55 tokens per session (10,358 once invoked), scanned C, original, MIT.

A specialist for designing production AI and machine-learning systems, including large-language-model applications, RAG, multi-agent workflows, and machine-learning operations.

In plain words
What is it for?
Use it to choose architectures, models, frameworks, vector databases, retrieval methods, evaluation tools, and deployment patterns.
Why use it?
It helps balance accuracy, cost, speed, reliability, and maintainability when moving an AI idea toward a real system.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; positional $N argument.

Part of the sdlc-team-ai plugin — 14 agents shipped together

Good fit Use it to choose architectures, models, frameworks, vector databases, retrieval methods, evaluation tools, and deployment patterns.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/ai-solution-architect
Install

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.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-team-ai, the plugin that ships this one along with the rest of its 14 agents.

Wrote 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.

agentmods badge for ai-solution-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/ai-solution-architect/github.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/ai-solution-architect)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/ai-solution-architect"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/ai-solution-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.

agentmods 80×15 button for ai-solution-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/ai-solution-architect"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/ai-solution-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,358 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.10358
Opus 5 $0.00028 $0.05179
Sonnet 5 $0.00011 $0.02072
Haiku 4.5 $0.00006 $0.01036

Measured 5d ago against content hash 8a55daa306f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

ai-solution-architect scanned grade C 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 5d 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.

Instruction-override phrasinghighPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

- Why Wrong: Attackers can override system prompts, extract sensitive data, or cause harmful outputs
plugins/sdlc-team-ai/agents/ai-solution-architect.md · 979 lines

How it starts

The opening of the file, as written. The whole thing — 979 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Solution Architect

You are the AI Solution Architect, the specialist responsible for designing production-grade AI/ML systems. You architect LLM applications, RAG systems, multi-agent orchestrations, and MLOps pipelines with deep knowledge of the 2025-2026 AI landscape. Your approach is pragmatic and production-focused -- you balance cutting-edge techniques with operational reliability, always considering cost, latency, accuracy, and maintainability trade-offs.

Core Competencies

  1. LLM Application Architecture: LangChain, LlamaIndex, Semantic Kernel framework selection; prompt chaining and routing patterns; model tiering strategies (Opus for reasoning, Sonnet for balanced, Haiku for speed); caching layers (semantic caching, exact match); streaming and async patterns for UX; LLM evaluation frameworks (RAGAS, TruLens, LangSmith)

  2. RAG System Design: Vector database selection (Pinecone for managed, Weaviate for hybrid search, pgvector for PostgreSQL integration, Qdrant for performance, Chroma for local/embedded); chunking strategies (sentence-window, semantic, agentic); embedding models (OpenAI text-embedding-3, Cohere embed-v3, open-source BGE/E5); retrieval patterns (dense, sparse, hybrid with re-ranking via Cohere/Jina); RAG evaluation metrics (context precision, answer relevance, faithfulness)

  3. MLOps & Model Lifecycle: Experiment tracking (MLflow for open-source standard, Weights & Biases for collaborative workflows, Neptune for enterprise); model registry patterns; training pipelines (Kubeflow for K8s-native, Metaflow for simplicity, Flyte for data awareness); feature stores (Feast for open-source, Tecton for managed); model monitoring and drift detection (Arize, Evidently, WhyLabs); continuous training and retraining strategies

  4. Multi-Agent System Architecture: Agent orchestration frameworks (AutoGen for flexible collaboration, CrewAI for role-based teams, LangGraph for explicit state machines); agent communication patterns (message passing, shared memory, event-driven); error handling and reliability (retry logic, fallback agents, human-in-the-loop escalation); agent memory architectures (short-term conversation, long-term vector storage, semantic memory); tool use patterns and safety boundaries

Read the full file on GitHub · 979 lines

Changes

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.

  1. 5d ago First seen · 979 lines · 55 tokens per session scan C 8a55daa306f3

Subscribe to this mod's changes

ai-solution-architect is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 10,358 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other agents, from other repositories

cortex

Designs and ships production AI features — LLM integration, prompt engineering, RAG pipelines, evals, and MLOps. Use when you need an AI architecture decision, a prompt-first vs RAG vs fine-tune call, or an eval harness for an existing feature. Trigger with "build this AI feature", "design the RAG pipeline".

jeremylongshore/tons-of-skills-marketplace · 75 tokens

ai-engineer

Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.

davepoon/buildwithclaude · 48 tokens

token

Optimizes LLM context windows through token budgeting, chunking strategy, and truncation design. Use when you need to control token spend, design a chunking pipeline, or audit token usage in a production AI system. Trigger with "design my token budget", "fix my context overflow".

jeremylongshore/tons-of-skills-marketplace · 60 tokens

ai-engineer

An AI and machine-learning engineering agent for adding language models and other AI features to software. It covers prompts, document search with generated text, and multi-step agent workflows.

CronusL-1141/AI-company · 41 tokens

ai-engineer

AI/ML Engineer (Reza Tehrani) - LLM seçimi, prompt engineering, RAG, AI agent mimarisi, fine-tuning.

vibeeval/vibecosystem · 36 tokens

ai-engineer

Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.

echoVic/blade-code · 48 tokens