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 skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill material-trackergit clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_ConstructionWrote 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.
[](https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/material-tracker)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/material-tracker"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/material-tracker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/material-tracker"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/material-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.02780 |
| Opus 5 | $0.00014 | $0.01390 |
| Sonnet 5 | $0.00005 | $0.00556 |
| Haiku 4.5 | $0.00003 | $0.00278 |
Grade A, and why
material-tracker 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- material-tracker — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Material Tracker
Business Case
Problem Statement
Material management challenges:
- Tracking multiple orders
- Coordinating deliveries
- Avoiding stockouts
- Managing lead times
Solution
Comprehensive material tracking system to monitor orders, deliveries, inventory, and alert on potential issues.
Technical Implementation
import pandas as pd
from typing import Dict, Any, List, Optional
from dataclasses import dataclass, field
from datetime import date, timedelta
from enum import Enum
class OrderStatus(Enum):
DRAFT = "draft"
SUBMITTED = "submitted"
CONFIRMED = "confirmed"
IN_PRODUCTION = "in_production"
SHIPPED = "shipped"
DELIVERED = "delivered"
PARTIAL = "partial"
CANCELLED = "cancelled"
class PriorityLevel(Enum):
CRITICAL = "critical"
HIGH = "high"
NORMAL = "normal"
LOW = "low"
@dataclass
class MaterialOrder:
order_id: str
material_code: str
material_name: str
supplier: str
quantity: float
unit: str
unit_cost: float
total_cost: float
order_date: date
required_date: date
expected_delivery: date
actual_delivery: Optional[date]
status: OrderStatus
priority: PriorityLevel
delivered_qty: float = 0
notes: str = ""
@dataclass
class InventoryItem:
material_code: str
material_name: str
current_stock: float
unit: str
min_stock: float
max_stock: float
reorder_point: float
location: str
last_updated: date
@dataclass
class Delivery:
delivery_id: str
order_id: str
delivery_date: date
quantity: float
received_by: str
condition: str # good, damaged, partial
notes: str = ""
class MaterialTracker:
"""Track construction materials."""
def __init__(self, project_name: str):
self.project_name = project_name
self.orders: Dict[str, MaterialOrder] = {}
self.inventory: Dict[str, InventoryItem] = {}
self.deliveries: List[Delivery] = []
def create_order(self,
order_id: str,
material_code: str,
material_name: str,
supplier: str,
quantity: float,
unit: str,
unit_cost: float,
required_date: date,
lead_time_days: int = 14,
priority: PriorityLevel = PriorityLevel.NORMAL) -> MaterialOrder:
"""Create new material order."""
order = MaterialOrder(
order_id=order_id,
material_code=material_code,
material_name=material_name,
supplier=supplier,
quantity=quantity,
unit=unit,
unit_cost=unit_cost,
total_cost=round(quantity * unit_cost, 2),
order_date=date.today(),
required_date=required_date,
expected_delivery=date.today() + timedelta(days=lead_time_days),
actual_delivery=None,
status=OrderStatus.DRAFT,
priority=priority
)
self.orders[order_id] = order
return order
def update_order_status(self, order_id: str, status: OrderStatus):
"""Update order status."""
if order_id in self.orders:
self.orders[order_id].status = status
def record_delivery(self,
order_id: str,
quantity: float,
received_by: str,
condition: str = "good",
notes: str = "") -> Optional[Delivery]:
"""Record material delivery."""
if order_id not in self.orders:
return None
order = self.orders[order_id]
delivery = Delivery(
delivery_id=f"DEL-{len(self.deliveries)+1:04d}",
order_id=order_id,
delivery_date=date.today(),
quantity=quantity,
received_by=received_by,
condition=condition,
notes=notes
)
self.deliveries.append(delivery)
# Update order
order.delivered_qty += quantity
order.actual_delivery = date.today()
if order.delivered_qty >= order.quantity:
order.status = OrderStatus.DELIVERED
else:
order.status = OrderStatus.PARTIAL
# Update inventory
if order.material_code in self.inventory:
self.inventory[order.material_code].current_stock += quantity
self.inventory[order.material_code].last_updated = date.today()
return delivery
def add_inventory_item(self,
material_code: str,
material_name: str,
current_stock: float,
unit: str,
min_stock: float,
max_stock: float,
location: str):
"""Add item to inventory tracking."""
reorder_point = min_stock + (max_stock - min_stock) * 0.3
self.inventory[material_code] = InventoryItem(
material_code=material_code,
material_name=material_name,
current_stock=current_stock,
unit=unit,
min_stock=min_stock,
max_stock=max_stock,
reorder_point=reorder_point,
location=location,
last_updated=date.today()
)
def consume_material(self,
material_code: str,
quantity: float,
activity: str = "") -> bool:
"""Record material consumption."""
if material_code not in self.inventory:
return False
item = self.inventory[material_code]
if item.current_stock < quantity:
return False
item.current_stock -= quantity
item.last_updated = date.today()
return True
def get_pending_orders(self) -> List[MaterialOrder]:
"""Get all pending orders."""
return [
o for o in self.orders.values()
if o.status not in [OrderStatus.DELIVERED, OrderStatus.CANCELLED]
]
def get_late_orders(self) -> List[Dict[str, Any]]:
"""Get orders that are late or at risk."""
late = []
today = date.today()
for order in self.orders.values():
if order.status in [OrderStatus.DELIVERED, OrderStatus.CANCELLED]:
continue
days_late = (today - order.expected_delivery).days
if days_late > 0 or (order.required_date - today).days < 3:
late.append({
'order_id': order.order_id,
'material': order.material_name,
'supplier': order.supplier,
'required_date': order.required_date,
'expected_delivery': order.expected_delivery,
'days_late': max(0, days_late),
'days_until_required': (order.required_date - today).days,
'status': order.status.value,
'priority': order.priority.value
})
return sorted(late, key=lambda x: x['days_until_required'])
def get_low_stock_items(self) -> List[Dict[str, Any]]:
"""Get items at or below reorder point."""
low_stock = []
for item in self.inventory.values():
if item.current_stock <= item.reorder_point:
low_stock.append({
'material_code': item.material_code,
'material_name': item.material_name,
'current_stock': item.current_stock,
'reorder_point': item.reorder_point,
'min_stock': item.min_stock,
'unit': item.unit,
'location': item.location,
'urgency': 'CRITICAL' if item.current_stock <= item.min_stock else 'REORDER'
})
return sorted(low_stock, key=lambda x: x['current_stock'])
def get_delivery_schedule(self, days_ahead: int = 14) -> pd.DataFrame:
"""Get expected deliveries for coming days."""
today = date.today()
end_date = today + timedelta(days=days_ahead)
scheduled = []
for order in self.orders.values():
if order.status in [OrderStatus.DELIVERED, OrderStatus.CANCELLED]:
continue
if today <= order.expected_delivery <= end_date:
scheduled.append({
'Date': order.expected_delivery,
'Order ID': order.order_id,
'Material': order.material_name,
'Quantity': order.quantity,
'Unit': order.unit,
'Supplier': order.supplier,
'Priority': order.priority.value
})
return pd.DataFrame(scheduled).sort_values('Date') if scheduled else pd.DataFrame()
def calculate_material_cost_summary(self) -> Dict[str, Any]:
"""Calculate material cost summary."""
total_ordered = sum(o.total_cost for o in self.orders.values())
total_delivered = sum(
o.delivered_qty * o.unit_cost
for o in self.orders.values()
)
total_pending = total_ordered - total_delivered
by_supplier = {}
for order in self.orders.values():
if order.supplier not in by_supplier:
by_supplier[order.supplier] = 0
by_supplier[order.supplier] += order.total_cost
return {
'total_ordered': round(total_ordered, 2),
'total_delivered': round(total_delivered, 2),
'total_pending': round(total_pending, 2),
'order_count': len(self.orders),
'by_supplier': by_supplier
}
def export_to_excel(self, output_path: str) -> str:
"""Export material tracking to Excel."""
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Orders
orders_df = pd.DataFrame([
{
'Order ID': o.order_id,
'Material': o.material_name,
'Supplier': o.supplier,
'Quantity': o.quantity,
'Unit': o.unit,
'Unit Cost': o.unit_cost,
'Total Cost': o.total_cost,
'Order Date': o.order_date,
'Required': o.required_date,
'Expected': o.expected_delivery,
'Status': o.status.value,
'Delivered': o.delivered_qty
}
for o in self.orders.values()
])
orders_df.to_excel(writer, sheet_name='Orders', index=False)
# Inventory
if self.inventory:
inv_df = pd.DataFrame([
{
'Code': i.material_code,
'Name': i.material_name,
'Stock': i.current_stock,
'Unit': i.unit,
'Min': i.min_stock,
'Max': i.max_stock,
'Reorder Point': i.reorder_point,
'Location': i.location
}
for i in self.inventory.values()
])
inv_df.to_excel(writer, sheet_name='Inventory', index=False)
# Late orders
late = self.get_late_orders()
if late:
late_df = pd.DataFrame(late)
late_df.to_excel(writer, sheet_name='Late Orders', index=False)
# Low stock
low = self.get_low_stock_items()
if low:
low_df = pd.DataFrame(low)
low_df.to_excel(writer, sheet_name='Low Stock', index=False)
return output_path
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 434 lines · 27 tokens per session scan A 4d599fe5bcf6
material-tracker is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (310 stars, last pushed 21d ago), licensed MIT. It adds 27 tokens to every session and 2,780 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 2026-09-03.
Other skills, from other repositories
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
proposal-writer
Write a client proposal, quote, scope of work, or engagement letter for a service business. Covers project understanding, scope, timeline, pricing presentation, and terms. Use whenever the user asks for a proposal, quote, project proposal, client proposal, SOW, statement of work, engagement letter, or B2B service…