Change Order Processor logo

Change Order Processor

Community
datadrivenconstruction
change-order-processor

Process and manage construction change orders. Track costs, approvals, and impact on schedule and budget.

Overview

Publisherdatadrivenconstruction
RepositoryDDC_Skills_for_AI_Agents_in_Construction
Skill namechange-order-processor
Stars
365
Forks
91
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by datadrivenconstruction on GitHub. Read the source before you install it.

Installation

Install the Change Order Processor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/main/1_DDC_Toolkit/Cost-Management/change-order-processor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction.git /tmp/DDC_Skills_for_AI_Agents_in_Construction
mkdir -p .claude/skills
cp -r /tmp/DDC_Skills_for_AI_Agents_in_Construction/1_DDC_Toolkit/Cost-Management/change-order-processor .claude/skills/change-order-processor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Change Order Processor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Change Order Processor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Change Order Processor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Change Order Processor

Business Case

Problem Statement

Change orders cause project disruption:

  • Delayed processing affects cash flow
  • Unclear cost impact
  • Lost documentation
  • Schedule impacts not tracked

Solution

Streamlined change order processing with cost analysis, approval workflow, and impact tracking.

Business Value

  • Faster processing - Reduce approval cycle time
  • Cost control - Accurate change pricing
  • Documentation - Complete audit trail
  • Impact visibility - Schedule and budget effects

Technical Implementation

python
import pandas as pd
from datetime import datetime, date, timedelta
from typing import Dict, Any, List, Optional
from dataclasses import dataclass, field
from enum import Enum


class ChangeOrderStatus(Enum):
    """Change order status."""
    DRAFT = "draft"
    PENDING_REVIEW = "pending_review"
    PENDING_APPROVAL = "pending_approval"
    APPROVED = "approved"
    REJECTED = "rejected"
    VOID = "void"


class ChangeType(Enum):
    """Type of change."""
    OWNER_REQUESTED = "owner_requested"
    DESIGN_CHANGE = "design_change"
    FIELD_CONDITION = "field_condition"
    CODE_COMPLIANCE = "code_compliance"
    VALUE_ENGINEERING = "value_engineering"
    ERROR_OMISSION = "error_omission"


class ImpactType(Enum):
    """Impact categories."""
    COST_INCREASE = "cost_increase"
    COST_DECREASE = "cost_decrease"
    TIME_INCREASE = "time_increase"
    TIME_DECREASE = "time_decrease"
    NO_IMPACT = "no_impact"


@dataclass
class CostItem:
    """Change order cost item."""
    description: str
    quantity: float
    unit: str
    unit_cost: float
    total_cost: float
    category: str  # labor, material, equipment, subcontractor
    markup_percent: float = 0.0


@dataclass
class ApprovalRecord:
    """Approval workflow record."""
    approver_name: str
    approver_role: str
    action: str  # approved, rejected, returned
    action_date: datetime
    comments: str = ""


@dataclass
class ChangeOrder:
    """Change order record."""
    co_number: str
    title: str
    description: str
    change_type: ChangeType
    status: ChangeOrderStatus
    created_date: date
    created_by: str

    # Cost
    cost_items: List[CostItem] = field(default_factory=list)
    direct_cost: float = 0.0
    overhead_cost: float = 0.0
    profit_cost: float = 0.0
    total_cost: float = 0.0

    # Schedule
    schedule_impact_days: int = 0
    affected_activities: List[str] = field(default_factory=list)

    # Workflow
    approvals: List[ApprovalRecord] = field(default_factory=list)
    approved_date: Optional[date] = None
    approved_by: str = ""

    # References
    rfi_reference: str = ""
    spec_section: str = ""
    drawing_reference: str = ""
    location: str = ""

    def to_dict(self) -> Dict[str, Any]:
        return {
            'co_number': self.co_number,
            'title': self.title,
            'change_type': self.change_type.value,
            'status': self.status.value,
            'created_date': self.created_date.isoformat(),
            'direct_cost': self.direct_cost,
            'overhead_cost': self.overhead_cost,
            'profit_cost': self.profit_cost,
            'total_cost': self.total_cost,
            'schedule_impact': self.schedule_impact_days,
            'approved_date': self.approved_date.isoformat() if self.approved_date else None
        }


class ChangeOrderProcessor:
    """Process and manage change orders."""

    DEFAULT_OVERHEAD_RATE = 0.10
    DEFAULT_PROFIT_RATE = 0.10

    def __init__(self, project_name: str, original_contract: float,
                 overhead_rate: float = None, profit_rate: float = None):
        self.project_name = project_name
        self.original_contract = original_contract
        self.overhead_rate = overhead_rate or self.DEFAULT_OVERHEAD_RATE
        self.profit_rate = profit_rate or self.DEFAULT_PROFIT_RATE
        self.change_orders: Dict[str, ChangeOrder] = {}
        self._co_counter = 0

    def create_change_order(self,
                           title: str,
                           description: str,
                           change_type: ChangeType,
                           created_by: str,
                           rfi_reference: str = "",
                           location: str = "") -> ChangeOrder:
        """Create new change order."""
        self._co_counter += 1
        co_number = f"CO-{self._co_counter:04d}"

        co = ChangeOrder(
            co_number=co_number,
            title=title,
            description=description,
            change_type=change_type,
            status=ChangeOrderStatus.DRAFT,
            created_date=date.today(),
            created_by=created_by,
            rfi_reference=rfi_reference,
            location=location
        )

        self.change_orders[co_number] = co
        return co

    def add_cost_item(self, co_number: str,
                     description: str,
                     quantity: float,
                     unit: str,
                     unit_cost: float,
                     category: str,
                     markup_percent: float = 0.0):
        """Add cost item to change order."""
        if co_number not in self.change_orders:
            raise ValueError(f"Change order {co_number} not found")

        co = self.change_orders[co_number]

        total = quantity * unit_cost * (1 + markup_percent)
        item = CostItem(
            description=description,
            quantity=quantity,
            unit=unit,
            unit_cost=unit_cost,
            total_cost=total,
            category=category,
            markup_percent=markup_percent
        )

        co.cost_items.append(item)
        self._recalculate_totals(co)

    def _recalculate_totals(self, co: ChangeOrder):
        """Recalculate change order totals."""
        co.direct_cost = sum(item.total_cost for item in co.cost_items)
        co.overhead_cost = co.direct_cost * self.overhead_rate
        co.profit_cost = (co.direct_cost + co.overhead_cost) * self.profit_rate
        co.total_cost = co.direct_cost + co.overhead_cost + co.profit_cost

    def set_schedule_impact(self, co_number: str, days: int,
                           affected_activities: List[str] = None):
        """Set schedule impact."""
        if co_number not in self.change_orders:
            raise ValueError(f"Change order {co_number} not found")

        co = self.change_orders[co_number]
        co.schedule_impact_days = days
        co.affected_activities = affected_activities or []

    def submit_for_review(self, co_number: str):
        """Submit change order for review."""
        if co_number not in self.change_orders:
            raise ValueError(f"Change order {co_number} not found")

        co = self.change_orders[co_number]
        if co.status != ChangeOrderStatus.DRAFT:
            raise ValueError("Can only submit draft change orders")

        co.status = ChangeOrderStatus.PENDING_REVIEW

    def submit_for_approval(self, co_number: str, reviewer: str, comments: str = ""):
        """Submit for approval after review."""
        if co_number not in self.change_orders:
            raise ValueError(f"Change order {co_number} not found")

        co = self.change_orders[co_number]
        if co.status != ChangeOrderStatus.PENDING_REVIEW:
            raise ValueError("Must be in review status")

        co.approvals.append(ApprovalRecord(
            approver_name=reviewer,
            approver_role="Reviewer",
            action="reviewed",
            action_date=datetime.now(),
            comments=comments
        ))

        co.status = ChangeOrderStatus.PENDING_APPROVAL

    def approve_change_order(self, co_number: str, approver: str,
                            approver_role: str, comments: str = ""):
        """Approve change order."""
        if co_number not in self.change_orders:
            raise ValueError(f"Change order {co_number} not found")

        co = self.change_orders[co_number]

        co.approvals.append(ApprovalRecord(
            approver_name=approver,
            approver_role=approver_role,
            action="approved",
            action_date=datetime.now(),
            comments=comments
        ))

        co.status = ChangeOrderStatus.APPROVED
        co.approved_date = date.today()
        co.approved_by = approver

    def reject_change_order(self, co_number: str, rejector: str,
                           reason: str):
        """Reject change order."""
        if co_number not in self.change_orders:
            raise ValueError(f"Change order {co_number} not found")

        co = self.change_orders[co_number]

        co.approvals.append(ApprovalRecord(
            approver_name=rejector,
            approver_role="Approver",
            action="rejected",
            action_date=datetime.now(),
            comments=reason
        ))

        co.status = ChangeOrderStatus.REJECTED

    def get_summary(self) -> Dict[str, Any]:
        """Generate change order summary."""
        cos = list(self.change_orders.values())

        by_status = {}
        by_type = {}
        total_approved = 0
        total_pending = 0
        total_schedule_impact = 0

        for co in cos:
            # By status
            status = co.status.value
            by_status[status] = by_status.get(status, 0) + 1

            # By type
            change_type = co.change_type.value
            by_type[change_type] = by_type.get(change_type, 0) + co.total_cost

            # Totals
            if co.status == ChangeOrderStatus.APPROVED:
                total_approved += co.total_cost
                total_schedule_impact += co.schedule_impact_days
            elif co.status in [ChangeOrderStatus.PENDING_REVIEW, ChangeOrderStatus.PENDING_APPROVAL]:
                total_pending += co.total_cost

        current_contract = self.original_contract + total_approved

        return {
            'project': self.project_name,
            'original_contract': self.original_contract,
            'approved_changes': total_approved,
            'current_contract': current_contract,
            'pending_changes': total_pending,
            'potential_contract': current_contract + total_pending,
            'total_change_orders': len(cos),
            'by_status': by_status,
            'by_type': by_type,
            'total_schedule_impact_days': total_schedule_impact,
            'change_percent': round(total_approved / self.original_contract * 100, 1) if self.original_contract > 0 else 0
        }

    def get_pending_approvals(self) -> List[ChangeOrder]:
        """Get change orders pending approval."""
        return [co for co in self.change_orders.values()
                if co.status in [ChangeOrderStatus.PENDING_REVIEW, ChangeOrderStatus.PENDING_APPROVAL]]

    def export_log(self, output_path: str):
        """Export change order log to Excel."""
        with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
            # Summary
            summary = self.get_summary()
            summary_df = pd.DataFrame([
                {'Metric': 'Original Contract', 'Value': summary['original_contract']},
                {'Metric': 'Approved Changes', 'Value': summary['approved_changes']},
                {'Metric': 'Current Contract', 'Value': summary['current_contract']},
                {'Metric': 'Pending Changes', 'Value': summary['pending_changes']},
                {'Metric': 'Change %', 'Value': f"{summary['change_percent']}%"},
                {'Metric': 'Schedule Impact (days)', 'Value': summary['total_schedule_impact_days']}
            ])
            summary_df.to_excel(writer, sheet_name='Summary', index=False)

            # Change order list
            co_data = [co.to_dict() for co in self.change_orders.values()]
            pd.DataFrame(co_data).to_excel(writer, sheet_name='Change Orders', index=False)

            # Cost details
            cost_data = []
            for co in self.change_orders.values():
                for item in co.cost_items:
                    cost_data.append({
                        'CO Number': co.co_number,
                        'Description': item.description,
                        'Quantity': item.quantity,
                        'Unit': item.unit,
                        'Unit Cost': item.unit_cost,
                        'Total': item.total_cost,
                        'Category': item.category
                    })
            if cost_data:
                pd.DataFrame(cost_data).to_excel(writer, sheet_name='Cost Details', index=False)

        return output_path

Quick Start

python
# Initialize processor
processor = ChangeOrderProcessor(
    project_name="Office Tower",
    original_contract=50000000
)

# Create change order
co = processor.create_change_order(
    title="Additional Electrical Outlets",
    description="Add 50 electrical outlets per owner request",
    change_type=ChangeType.OWNER_REQUESTED,
    created_by="Project Manager"
)

# Add cost items
processor.add_cost_item(co.co_number, "Electrical outlets", 50, "EA", 150, "material")
processor.add_cost_item(co.co_number, "Installation labor", 25, "HR", 85, "labor")

# Set schedule impact
processor.set_schedule_impact(co.co_number, days=5)

# Submit for approval
processor.submit_for_review(co.co_number)

Common Use Cases

1. Process Approval

python
processor.submit_for_approval(co.co_number, "Reviewer", "Cost verified")
processor.approve_change_order(co.co_number, "Owner Rep", "Owner", "Approved per request")

2. Get Summary

python
summary = processor.get_summary()
print(f"Contract value: ${summary['current_contract']:,.0f}")
print(f"Change %: {summary['change_percent']}%")

3. Export Log

python
processor.export_log("change_order_log.xlsx")

Resources

  • DDC Book: Chapter 3.1 - Cost Management
  • Reference: AIA Document G701

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Change Order Processor AI skill do?

Process and manage construction change orders. Track costs, approvals, and impact on schedule and budget.

Why use Change Order Processor on TypingMind?

Because you install it once and use it with any model. Change Order Processor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Change Order Processor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/main/1_DDC_Toolkit/Cost-Management/change-order-processor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Change Order Processor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Change Order Processor?

As many as you like. As long as a model supports skills, you can use Change Order Processor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Change Order Processor AI skill free?

Yes. It is published on GitHub by datadrivenconstruction under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇