state-engineer

state-engineer is an agent for Claude Code from TheLobbi/claude. It costs 19 tokens per session (4,255 once invoked), scanned A, original, MIT.

An agent that designs the state schema for a LangGraph application. A state schema is the defined shape of the information shared and updated as a graph runs.

In plain words
What is it for?
Use it to define typed fields, message lists, custom update rules, nested state, state transformations, and serialization—the way state is converted for storage or transfer.
Why use it?
It helps prevent unclear or incompatible data passing between workflow steps and provides patterns for validation, nested data, updates, and saving state.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Part of the langgraph-architect plugin — 5 commands, 12 agents, 1 MCP server shipped together

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/thelobbi/claude/state-engineer
Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install langgraph-architect, the plugin that ships this one along with the rest of its 5 commands, 12 agents, 1 MCP server.

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 state-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thelobbi/claude/state-engineer.svg)](https://agentmods.dev/agents/thelobbi/claude/state-engineer)
Your own site
<a href="https://agentmods.dev/agents/thelobbi/claude/state-engineer"><img src="https://agentmods.dev/badge/agents/thelobbi/claude/state-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,255 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 5.1 $0.00019 $0.04255
Opus 5 $0.00010 $0.02128
Sonnet 5 $0.00004 $0.00851
Haiku 4.5 $0.00002 $0.00426

Measured today against content hash 9a264cc820d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

state-engineer 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 today.

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/plugins/langgraph-architect/agents/state-engineer.md · 703 lines

How it starts

The opening of the file, as written. The whole thing — 703 lines — stays where its author put it; the contents beside it link to each section on GitHub.

State Engineer Agent

---
name: state-engineer
version: 1.0.0
model: claude-sonnet-5
color: yellow
description: Expert in designing and managing state schemas for LangGraph applications
expertise:
  - TypedDict state definitions
  - Annotated types with reducers
  - add_messages reducer pattern
  - Custom reducer functions
  - State validation
  - Nested state schemas
  - State transformation
  - Serialization strategies
tags:
  - langgraph
  - state
  - schema
  - data-modeling
---

Core Expertise

The State Engineer is an expert in designing state schemas for LangGraph applications. State is the core data structure that flows through the graph, accumulates information, and enables nodes to communicate. Proper state design is crucial for maintainable, scalable workflows.

State Schema Patterns

1. Basic TypedDict State

Foundation for all state schemas:

from typing import TypedDict

class BasicState(TypedDict):
    """
    Simple state schema using TypedDict.
    - All fields are required by default
    - Type hints enable validation
    - Used for straightforward workflows
    """
    user_id: str
    query: str
    result: str
    timestamp: float

# Usage in graph
from langgraph.graph import StateGraph

builder = StateGraph(BasicState)

2. Optional Fields

State with optional fields:

from typing import TypedDict, NotRequired

class FlexibleState(TypedDict):
    """
    State with optional fields using NotRequired (Python 3.11+).
    """
    # Required fields
    request_id: str
    status: str

    # Optional fields
    result: NotRequired[str]
    error: NotRequired[str]
    retry_count: NotRequired[int]
    metadata: NotRequired[dict]

# Alternative for Python 3.8-3.10
class FlexibleStateLegacy(TypedDict, total=False):
    """All fields are optional when total=False."""
    result: str
    error: str
    retry_count: int

class RequiredFields(TypedDict):
    """Required fields in separate TypedDict."""
    request_id: str
    status: str

# Combine using inheritance
class CombinedState(RequiredFields, FlexibleStateLegacy):
    """Has required fields + optional fields."""
    pass

Read the full file on GitHub · 703 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. today First seen · 703 lines · 19 tokens per session scan A 9a264cc820d5

Subscribe to this mod's changes

state-engineer is an agent published in the GitHub repository TheLobbi/claude (21 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 4,255 once invoked, about $0.0001 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 2026-09-05.

Related

Other agents, from other repositories