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-delivery-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-delivery-tracker)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/material-delivery-tracker"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/material-delivery-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-delivery-tracker"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/material-delivery-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 | $0.00024 | $0.02812 |
| Opus 5 | $0.00012 | $0.01406 |
| Sonnet 5 | $0.00005 | $0.00562 |
| Haiku 4.5 | $0.00002 | $0.00281 |
Grade A, and why
material-delivery-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 12d 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-delivery-tracker — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Material Delivery Tracker
Business Case
Problem Statement
Material logistics cause project delays:
- Missed deliveries impact schedule
- Storage space constraints
- No visibility into delivery status
- Difficult coordination with vendors
Solution
Centralized material delivery tracking system that manages schedules, monitors status, and coordinates site logistics.
Business Value
- Schedule protection - Timely material availability
- Cost savings - Reduce expediting fees
- Site efficiency - Optimized storage planning
- Vendor coordination - Better communication
Technical Implementation
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 DeliveryStatus(Enum):
"""Delivery status."""
SCHEDULED = "scheduled"
IN_TRANSIT = "in_transit"
DELIVERED = "delivered"
PARTIAL = "partial"
DELAYED = "delayed"
CANCELLED = "cancelled"
class DeliveryPriority(Enum):
"""Delivery priority."""
CRITICAL = "critical"
HIGH = "high"
NORMAL = "normal"
LOW = "low"
class MaterialCategory(Enum):
"""Material categories."""
STRUCTURAL = "structural"
CONCRETE = "concrete"
MEP = "mep"
FINISHES = "finishes"
EQUIPMENT = "equipment"
OTHER = "other"
@dataclass
class MaterialItem:
"""Material item in delivery."""
item_id: str
description: str
quantity_ordered: float
quantity_received: float
unit: str
category: MaterialCategory
spec_section: str = ""
notes: str = ""
@property
def is_complete(self) -> bool:
return self.quantity_received >= self.quantity_ordered
@dataclass
class Delivery:
"""Material delivery record."""
delivery_id: str
po_number: str
vendor: str
vendor_contact: str
vendor_phone: str
scheduled_date: date
priority: DeliveryPriority
status: DeliveryStatus
items: List[MaterialItem]
delivery_location: str
storage_area: str
receiver: str = ""
actual_date: Optional[date] = None
tracking_number: str = ""
carrier: str = ""
notes: str = ""
delay_reason: str = ""
def to_dict(self) -> Dict[str, Any]:
return {
'delivery_id': self.delivery_id,
'po_number': self.po_number,
'vendor': self.vendor,
'scheduled_date': self.scheduled_date.isoformat(),
'actual_date': self.actual_date.isoformat() if self.actual_date else None,
'status': self.status.value,
'priority': self.priority.value,
'items_count': len(self.items),
'location': self.delivery_location,
'storage': self.storage_area
}
@dataclass
class StorageArea:
"""Site storage area."""
area_id: str
name: str
location: str
capacity_sqm: float
current_usage_sqm: float
material_types: List[str]
is_covered: bool
access_restrictions: str = ""
class MaterialDeliveryTracker:
"""Track material deliveries and logistics."""
def __init__(self, project_name: str):
self.project_name = project_name
self.deliveries: Dict[str, Delivery] = {}
self.storage_areas: Dict[str, StorageArea] = {}
self._delivery_counter = 0
def schedule_delivery(self,
po_number: str,
vendor: str,
scheduled_date: date,
delivery_location: str,
storage_area: str,
priority: DeliveryPriority = DeliveryPriority.NORMAL,
vendor_contact: str = "",
vendor_phone: str = "") -> Delivery:
"""Schedule new delivery."""
self._delivery_counter += 1
delivery_id = f"DEL-{self._delivery_counter:05d}"
delivery = Delivery(
delivery_id=delivery_id,
po_number=po_number,
vendor=vendor,
vendor_contact=vendor_contact,
vendor_phone=vendor_phone,
scheduled_date=scheduled_date,
priority=priority,
status=DeliveryStatus.SCHEDULED,
items=[],
delivery_location=delivery_location,
storage_area=storage_area
)
self.deliveries[delivery_id] = delivery
return delivery
def add_item(self, delivery_id: str,
description: str,
quantity: float,
unit: str,
category: MaterialCategory,
spec_section: str = "") -> MaterialItem:
"""Add item to delivery."""
if delivery_id not in self.deliveries:
raise ValueError(f"Delivery {delivery_id} not found")
delivery = self.deliveries[delivery_id]
item_id = f"{delivery_id}-{len(delivery.items) + 1:03d}"
item = MaterialItem(
item_id=item_id,
description=description,
quantity_ordered=quantity,
quantity_received=0,
unit=unit,
category=category,
spec_section=spec_section
)
delivery.items.append(item)
return item
def update_status(self, delivery_id: str, status: DeliveryStatus,
tracking_number: str = "", carrier: str = "",
delay_reason: str = ""):
"""Update delivery status."""
if delivery_id not in self.deliveries:
raise ValueError(f"Delivery {delivery_id} not found")
delivery = self.deliveries[delivery_id]
delivery.status = status
if tracking_number:
delivery.tracking_number = tracking_number
if carrier:
delivery.carrier = carrier
if delay_reason:
delivery.delay_reason = delay_reason
def receive_delivery(self, delivery_id: str, receiver: str,
received_quantities: Dict[str, float] = None,
actual_date: date = None):
"""Record delivery receipt."""
if delivery_id not in self.deliveries:
raise ValueError(f"Delivery {delivery_id} not found")
delivery = self.deliveries[delivery_id]
delivery.receiver = receiver
delivery.actual_date = actual_date or date.today()
# Update received quantities
if received_quantities:
for item in delivery.items:
if item.item_id in received_quantities:
item.quantity_received = received_quantities[item.item_id]
else:
# Assume full receipt
for item in delivery.items:
item.quantity_received = item.quantity_ordered
# Check if all items complete
all_complete = all(item.is_complete for item in delivery.items)
if all_complete:
delivery.status = DeliveryStatus.DELIVERED
else:
delivery.status = DeliveryStatus.PARTIAL
def add_storage_area(self, area_id: str, name: str, location: str,
capacity_sqm: float, material_types: List[str],
is_covered: bool = False) -> StorageArea:
"""Add storage area."""
area = StorageArea(
area_id=area_id,
name=name,
location=location,
capacity_sqm=capacity_sqm,
current_usage_sqm=0,
material_types=material_types,
is_covered=is_covered
)
self.storage_areas[area_id] = area
return area
def get_upcoming_deliveries(self, days: int = 7) -> List[Delivery]:
"""Get deliveries scheduled within specified days."""
cutoff = date.today() + timedelta(days=days)
return [d for d in self.deliveries.values()
if d.status in [DeliveryStatus.SCHEDULED, DeliveryStatus.IN_TRANSIT]
and d.scheduled_date <= cutoff]
def get_delayed_deliveries(self) -> List[Delivery]:
"""Get overdue deliveries."""
today = date.today()
return [d for d in self.deliveries.values()
if d.status in [DeliveryStatus.SCHEDULED, DeliveryStatus.IN_TRANSIT, DeliveryStatus.DELAYED]
and d.scheduled_date < today]
def get_deliveries_by_vendor(self, vendor: str) -> List[Delivery]:
"""Get all deliveries from a vendor."""
return [d for d in self.deliveries.values()
if vendor.lower() in d.vendor.lower()]
def get_summary(self) -> Dict[str, Any]:
"""Generate delivery summary."""
deliveries = list(self.deliveries.values())
by_status = {}
by_priority = {}
by_vendor = {}
for d in deliveries:
status = d.status.value
by_status[status] = by_status.get(status, 0) + 1
priority = d.priority.value
by_priority[priority] = by_priority.get(priority, 0) + 1
by_vendor[d.vendor] = by_vendor.get(d.vendor, 0) + 1
# Upcoming this week
upcoming = self.get_upcoming_deliveries(7)
delayed = self.get_delayed_deliveries()
# On-time delivery rate
completed = [d for d in deliveries if d.status == DeliveryStatus.DELIVERED]
on_time = sum(1 for d in completed
if d.actual_date and d.actual_date <= d.scheduled_date)
otd_rate = (on_time / len(completed) * 100) if completed else 0
return {
'project': self.project_name,
'total_deliveries': len(deliveries),
'by_status': by_status,
'by_priority': by_priority,
'by_vendor': by_vendor,
'upcoming_7_days': len(upcoming),
'overdue': len(delayed),
'on_time_delivery_rate': round(otd_rate, 1),
'storage_areas': len(self.storage_areas)
}
def export_schedule(self, output_path: str):
"""Export delivery schedule to Excel."""
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Delivery schedule
schedule_data = [d.to_dict() for d in self.deliveries.values()]
schedule_df = pd.DataFrame(schedule_data)
if not schedule_df.empty:
schedule_df.to_excel(writer, sheet_name='Schedule', index=False)
# Item details
items_data = []
for delivery in self.deliveries.values():
for item in delivery.items:
items_data.append({
'Delivery ID': delivery.delivery_id,
'PO': delivery.po_number,
'Item': item.description,
'Ordered': item.quantity_ordered,
'Received': item.quantity_received,
'Unit': item.unit,
'Category': item.category.value,
'Complete': item.is_complete
})
if items_data:
pd.DataFrame(items_data).to_excel(writer, sheet_name='Items', index=False)
# Upcoming
upcoming = self.get_upcoming_deliveries(14)
if upcoming:
upcoming_df = pd.DataFrame([d.to_dict() for d in upcoming])
upcoming_df.to_excel(writer, sheet_name='Upcoming', 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.
- 12d ago First seen · 400 lines · 24 tokens per session scan A 01a8f4934f3d
material-delivery-tracker is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (310 stars, last pushed 20d ago), licensed MIT. It adds 24 tokens to every session and 2,812 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 2026-08-30.
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.
project-health
All-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects (permissions, context quality, MCP coverage, leaked secrets, stale docs), tidies accumulated cruft, captures session learnings, and adds permission presets. Uses…