What is agentic-ai-dev?

A development guide for production AI agents, retrieval-augmented generation systems, graph workflows, tools, memory, and tests using Python, LangChain, LangGraph, and FastAPI. Retrieval-augmented generation lets an agent find relevant source material before answering.

Use it to scaffold and configure agent services, define typed state and tools, build graph workflows, add memory and checkpoints, and write agent tests.

It provides patterns for controlling agent loops, involving a human when needed, validating inputs and outputs, and storing state reliably.

agentic-ai-dev — Skill for Claude Code by kumaran-is

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.

Any agent

npx skills add kumaran-is/claude-code-onboarding --skill agentic-ai-dev

Clone the repo

git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/agentic-ai-dev/github.svg)](https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/agentic-ai-dev)

Your own site

<a href="https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/agentic-ai-dev"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/agentic-ai-dev/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kumaran-is/claude-code-onboarding/agentic-ai-dev"><img src="https://agentmods.dev/badge/skills/kumaran-is/claude-code-onboarding/agentic-ai-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,086 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00073	$0.02086
Opus 5	$0.00036	$0.01043
Sonnet 5	$0.00015	$0.00417
Haiku 4.5	$0.00007	$0.00209

Measured 6d ago against content hash 8f732634cdba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agentic-ai-dev 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 6d 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.

.claude/skills/agentic-ai-dev/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iron Law

NO AGENT GRAPH WITHOUT AN ITERATION LIMIT AND A HUMAN-IN-THE-LOOP CHECKPOINT — unbounded loops and silent runaway agents are production incidents

Agentic AI Development Skill — Python 3.14 + LangChain + LangGraph + FastAPI

Quick Scaffold

uv init my-agent-service && cd my-agent-service
uv add "langchain-core>=1.2.8" "langchain-anthropic>=1.3.0" "langchain-openai>=1.1.0" "langgraph>=1.0.7" \
  "fastapi>=0.135.2" "uvicorn[standard]" pydantic pydantic-settings \
  langsmith prometheus-client structlog httpx asyncpg \
  "langgraph-checkpoint-postgres>=3.0.0"
uv add --dev pytest pytest-asyncio httpx ruff mypy

Process

Scaffold — uv init + install dependencies
Configure — core/config.py with pydantic-settings, .env, structured logging
Define State — TypedDict with Annotated[list, add_messages] for each agent
Build Graph — StateGraph with typed nodes, conditional edges, checkpointing
Define Tools — @tool with docstrings, Pydantic input schemas, error handling
Add Memory — Checkpointing (PostgresSaver), semantic memory (vector store)
Add Guardrails — Input validation, prompt injection detection, output validation
Expose API — FastAPI routes for invoke/stream with thread_id propagation
Write Tests — Basic invoke, tool usage, iteration limit, error recovery, RAG quality
Deploy — Docker multi-stage, gunicorn + uvicorn, health checks, Prometheus

Key Patterns

Pattern	Implementation	Reference
Agent Graphs	`StateGraph` + typed nodes + conditional edges	`agentic-templates-basic.md`
Tools	`@tool` + docstring + Pydantic input + try/except	`agentic-templates-tools.md`
LLM Binding	Factory function per provider, `.bind_tools()`	`agentic-llm-routing.md`
Routing	`Command(goto=...)` pattern (LangGraph)	`agentic-templates-advanced.md`
Checkpointing	`PostgresSaver` (prod) / `MemorySaver` (test)	`agentic-memory-systems.md`
Streaming	`astream()` + `stream_mode` + FastAPI SSE	`agentic-streaming-hitl.md`
Human-in-the-Loop	`interrupt_before` + approval node	`agentic-streaming-hitl.md`
RAG	Embeddings → Vector Store → Retriever → Reranker	`agentic-templates-rag.md`
Guardrails	12-layer pipeline: input → process → output	`agentic-guardrails-security.md`
Structured Output	`.with_structured_output(PydanticModel)`	`agentic-prompt-engineering.md`
Error Recovery	Retry node + fallback model + graceful degradation	`agentic-templates-resilience.md`
Config	pydantic-settings + fail-fast validators	`agentic-config-project.md`
Caching	4-tier Q1→Q2→Q3→L3 with backfill; @cached_tool decorator	`agentic-caching-patterns.md`

Read the full file on GitHub · 132 lines

Files

What ships with it

25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

6d ago First seen · 132 lines · 73 tokens per session scan A 8f732634cdba

Subscribe to this mod's changes

agentic-ai-dev is a skill published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 2,086 once invoked, about $0.0004 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 2026-09-03.

Building agents Data and AI RAG and vectors

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

azure-search-documents-dotnet

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…

microsoft/skills · 102 tokens

browserwing-admin

Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.

MemTensor/MemOS · 47 tokens

similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

foryourhealth111-pixel/Vibe-Skills · 30 tokens