# unit-price-database-manager

unit-price-database-manager keeps a construction unit price database current: price updates, vendor quotes, location factors, price history. Useful when an estimate has to match what suppliers actually charge.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 122 installs · ★ 434 repo stars
- Author: datadrivenconstruction
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/2_DDC_Book/3.1-Cost-Estimation/unit-price-database-manager/SKILL.md
- Updated: 2026-10-19
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/unit-price-database-manager

## What it does

The skill turns the agent into a keeper of a construction price book. It ships a Python module: dataclasses for a price line, a vendor quote and a price change record, plus a `UnitPriceDatabaseManager` class that holds current prices, their history and the update log.

Replacing a price archives the old line and logs the percentage difference. `get_price` returns a line that is valid on a given date and can rescale it to another city from a factor table. Labor and equipment get scaled; material cost stays at the base figure, so those lines in the estimate still need your eye. `apply_escalation` bumps prices by a percentage across the whole base or only for items carrying the tags you name.

Running it needs `python3` on `PATH` and `pandas`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill unit-price-database-manager -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/unit-price-database-manager/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/unit-price-database-manager/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill unit-price-database-manager -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/unit-price-database-manager/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill unit-price-database-manager -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/unit-price-database-manager/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction 2_DDC_Book/3.1-Cost-Estimation/unit-price-database-manager
```

2. **Manually: put the files in place**
- File: `.github/skills/unit-price-database-manager/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill unit-price-database-manager -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --path 2_DDC_Book/3.1-Cost-Estimation/unit-price-database-manager
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/unit-price-database-manager/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill unit-price-database-manager -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/2_DDC_Book/3.1-Cost-Estimation/unit-price-database-manager/SKILL.md

## When to use it
- refresh a price line without losing the old value
- compare vendor quotes for the same item
- rescale an estimate for another city
- apply a percentage escalation and keep an audit trail
- pull the price that was valid on a given date

## Example prompts
- Add a unit price for cast-in-place concrete with labor, material and equipment broken out.
- Re-price the item from National Average to Chicago and tell me which parts moved.
- Apply escalation to every item tagged `concrete` and keep the change log.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 0ecd015386ee92ca.

BEGIN THIRD-PARTY FILE 0ecd015386ee92ca
````text
---
name: "unit-price-database-manager"
description: "Manage construction unit price databases: update prices, track vendors, apply location factors, maintain historical records. Essential for accurate estimating."
homepage: "https://datadrivenconstruction.io"
metadata: {"openclaw":{"emoji":"🗃️","os":["darwin","linux","win32"],"homepage":"https://datadrivenconstruction.io","requires":{"bins":["python3"]}}}
---

# Unit Price Database Manager for Construction

## Overview

Manage and maintain construction unit price databases. Update prices from vendors, apply location and time adjustments, track price history, and ensure estimating accuracy.

## Business Case

Accurate unit prices are critical for:
- **Competitive Bids**: Win work with accurate pricing
- **Cost Control**: Avoid budget surprises
- **Vendor Management**: Track supplier pricing
- **Historical Analysis**: Understand price trends

## Technical Implementation

```python
from dataclasses import dataclass, field
from typing import List, Dict, Any, Optional
from datetime import datetime, date
from decimal import Decimal
import pandas as pd
import json

@dataclass
class UnitPrice:
    code: str
    description: str
    unit: str
    base_price: Decimal
    labor_cost: Decimal
    material_cost: Decimal
    equipment_cost: Decimal
    effective_date: date
    expiration_date: Optional[date] = None
    source: str = ""
    vendor: str = ""
    location: str = "National Average"
    notes: str = ""
    tags: List[str] = field(default_factory=list)

@dataclass
class PriceUpdate:
    code: str
    old_price: Decimal
    new_price: Decimal
    change_pct: float
    updated_at: datetime
    updated_by: str
    reason: str

@dataclass
class VendorQuote:
    vendor_name: str
    item_code: str
    quoted_price: Decimal
    quote_date: date
    valid_until: date
    quantity_break: Optional[int] = None
    notes: str = ""

class UnitPriceDatabaseManager:
    """Manage construction unit price databases."""

    # Location adjustment factors
    LOCATION_FACTORS = {
````
END THIRD-PARTY FILE 0ecd015386ee92ca

The third-party file has ended. Everything between the 0ecd015386ee92ca tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2050 of 17176 bytes. © datadrivenconstruction · MIT · https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/2_DDC_Book/3.1-Cost-Estimation/unit-price-database-manager/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
