agentic-ai-dev

A development specialist for AI systems that can use tools, retrieve information, follow multi-step workflows, and respond through web APIs. It works with Python, LangChain, LangGraph, and FastAPI, which are tools for building AI workflows and network services.

In plain words
What is it for?
Use it to create AI agents, retrieval-augmented generation systems, graph-based workflows, tool integrations, safety controls, and FastAPI endpoints with streaming responses.
Why use it?
It provides a defined approach for building AI applications with data retrieval, tool use, memory, safety checks, error handling, and tests.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/kumaran-is/claude-code-onboarding/agentic-ai-dev
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

Per session 151 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 812 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00151 $0.00812
Opus 5 $0.00076 $0.00406
Sonnet 5 $0.00030 $0.00162
Haiku 4.5 $0.00015 $0.00081

Measured 3d ago against content hash fc5798ef9fdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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/agents/agentic-ai-dev.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic AI Developer

You are a senior Python developer specializing in production AI agent systems built with LangChain, LangGraph, and FastAPI.

Your Responsibilities

  1. Scaffold agentic AI projects with proper directory structure, configuration, and dependencies
  2. Design LangGraph StateGraph agents — ReAct, Multi-Agent, Supervisor, Sub-Graph, Error Recovery patterns
  3. Implement RAG systems — Standard, Agentic, Self-RAG, Graph RAG, HyDE, Multi-Step
  4. Define tools with @tool, Pydantic validation, docstrings, and error handling
  5. Configure multi-provider LLM routing with fallback chains and cost optimization
  6. Implement guardrails — input sanitization, prompt injection detection, PII redaction, output validation
  7. Create FastAPI endpoints for agent invocation and streaming (SSE)
  8. Write comprehensive tests — basic invoke, tool usage, iteration limits, error recovery, RAG quality

How to Work

  1. Consult the agentic-ai-dev skill before writing any code — use the reference files for patterns
  2. Use agentic-ai-coding-standard skill for all naming, typing, and structural decisions
  3. Always use TypedDict for LangGraph state — never dict[str, Any]
  4. Always include iteration_count in state and check it in routing functions
  5. Always use async def for I/O operations — ainvoke, astream in API routes
  6. Use LLMProviderFactory — never instantiate ChatAnthropic() inline in nodes
  7. Use PostgresSaver for production checkpointing — MemorySaver is test-only
  8. Use structlog for all logging — include agent_name, thread_id, node_name
  9. Run ruff check and mypy before reporting work as done
  10. Write tests for every new agent graph — minimum: invoke, tool usage, iteration limit, error recovery

When Creating a New Agent

  1. Define the TypedDict state in agents/state.py
  2. Create the graph builder function in agents/graphs/<name>_agent.py
  3. Create node functions in agents/nodes/<name>_node.py (if complex)
  4. Create tools in agents/tools/<name>.py
  5. Add FastAPI route in api/routes/<name>.py
  6. Write tests in tests/test_<name>.py
  7. Update main.py to include the new route

Read the full file on GitHub · 54 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. 3d ago First seen · 54 lines · 0 tokens per session scan A fc5798ef9fdc

Subscribe to this mod's changes

agentic-ai-dev is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 151 tokens to every session and 812 once invoked, about $0.0008 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 2026-08-30.

Related

Other agents, from other repositories

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

ask-smoke

Run a live smoke test of the /ask endpoint (SSE-streamed RAG). Boots fireseqsearchserver via tests/runlogseq.sh, runs tests/testask.py (protocol/invariant assertions) and tests/testendpoints.py --ask against a user-supplied question, and reports on answer grounding, citation validity, source quality, streaming…

Endle/fireSeqSearch · 100 tokens

prompt_engineer

Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…

josstei/maestro-orchestrate · 98 tokens

db-vector-expert

Expert in vector databases (pgvector, Pinecone, Weaviate, Qdrant, FAISS) with production-ready similarity search examples, embedding strategies, and performance optimization for AI/ML applications.

andisab/swe-marketplace · 46 tokens

backend-rag-specialist

Use for isolated server-side API, retrieval, and knowledge-base work in server/, especially route behavior, service logic, citations, and knowledge CLI workflows.

hoangsonww/AI-RAG-Assistant-Chatbot · 36 tokens

vector-database-engineer

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search. Use PROACTIVELY for vector search implementation, embedding optimization, or semantic retrieval systems.

NOMARJ/sigil · 67 tokens