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 agentmods add agents/kumaran-is/claude-code-onboarding/agentic-ai-devgit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWhat 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 | $0.00151 | $0.00812 |
| Opus 5 | $0.00076 | $0.00406 |
| Sonnet 5 | $0.00030 | $0.00162 |
| Haiku 4.5 | $0.00015 | $0.00081 |
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.
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
- Scaffold agentic AI projects with proper directory structure, configuration, and dependencies
- Design LangGraph StateGraph agents — ReAct, Multi-Agent, Supervisor, Sub-Graph, Error Recovery patterns
- Implement RAG systems — Standard, Agentic, Self-RAG, Graph RAG, HyDE, Multi-Step
- Define tools with
@tool, Pydantic validation, docstrings, and error handling - Configure multi-provider LLM routing with fallback chains and cost optimization
- Implement guardrails — input sanitization, prompt injection detection, PII redaction, output validation
- Create FastAPI endpoints for agent invocation and streaming (SSE)
- Write comprehensive tests — basic invoke, tool usage, iteration limits, error recovery, RAG quality
How to Work
- Consult the
agentic-ai-devskill before writing any code — use the reference files for patterns - Use
agentic-ai-coding-standardskill for all naming, typing, and structural decisions - Always use
TypedDictfor LangGraph state — neverdict[str, Any] - Always include
iteration_countin state and check it in routing functions - Always use
async deffor I/O operations —ainvoke,astreamin API routes - Use
LLMProviderFactory— never instantiateChatAnthropic()inline in nodes - Use
PostgresSaverfor production checkpointing —MemorySaveris test-only - Use structlog for all logging — include
agent_name,thread_id,node_name - Run
ruff checkandmypybefore reporting work as done - Write tests for every new agent graph — minimum: invoke, tool usage, iteration limit, error recovery
When Creating a New Agent
- Define the
TypedDictstate inagents/state.py - Create the graph builder function in
agents/graphs/<name>_agent.py - Create node functions in
agents/nodes/<name>_node.py(if complex) - Create tools in
agents/tools/<name>.py - Add FastAPI route in
api/routes/<name>.py - Write tests in
tests/test_<name>.py - Update
main.pyto include the new route
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.
- 3d ago First seen · 54 lines · 0 tokens per session scan A fc5798ef9fdc
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.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
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…
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…
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.
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.
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.