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 retention-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/retention-tracker)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/retention-tracker"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/retention-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/retention-tracker"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/retention-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 | $0.00031 | $0.03834 |
| Opus 5 | $0.00015 | $0.01917 |
| Sonnet 5 | $0.00006 | $0.00767 |
| Haiku 4.5 | $0.00003 | $0.00383 |
Grade A, and why
retention-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 8d 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:
- retention-tracker — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retention Tracker
Overview
Track retainage (retention) amounts held and released throughout construction projects. Monitor amounts by subcontractor, track release milestones, and ensure proper documentation for retention release.
Retainage Flow
┌─────────────────────────────────────────────────────────────────┐
│ RETAINAGE LIFECYCLE │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Progress Billing → Substantial → Final Release │
│ ──────────────── ─────────── ───────────── │
│ 10% withheld 50% released 50% released │
│ Each pay app At punch list At final │
│ Cumulative completion completion │
│ │
│ Owner holds from GC → GC holds from subs → Flow-down │
│ │
└─────────────────────────────────────────────────────────────────┘
Technical Implementation
from dataclasses import dataclass, field
from typing import List, Dict, Optional
from datetime import datetime, timedelta
from enum import Enum
class RetentionStatus(Enum):
HELD = "held"
PARTIAL_RELEASE = "partial_release"
PENDING_RELEASE = "pending_release"
RELEASED = "released"
class ReleaseMilestone(Enum):
SUBSTANTIAL_COMPLETION = "substantial_completion"
PUNCH_LIST_COMPLETE = "punch_list_complete"
FINAL_COMPLETION = "final_completion"
WARRANTY_EXPIRATION = "warranty_expiration"
@dataclass
class RetentionEntry:
pay_app_number: int
billing_date: datetime
gross_billing: float
retention_rate: float
retention_amount: float
status: RetentionStatus = RetentionStatus.HELD
@dataclass
class RetentionRelease:
id: str
release_date: datetime
milestone: ReleaseMilestone
amount: float
remaining_after: float
approved_by: str
conditions_met: List[str] = field(default_factory=list)
lien_waivers_received: bool = False
consent_of_surety: bool = False
@dataclass
class SubcontractorRetention:
subcontractor_id: str
subcontractor_name: str
trade: str
contract_value: float
retention_rate: float
entries: List[RetentionEntry] = field(default_factory=list)
releases: List[RetentionRelease] = field(default_factory=list)
total_billed: float = 0.0
total_retained: float = 0.0
total_released: float = 0.0
balance_held: float = 0.0
status: RetentionStatus = RetentionStatus.HELD
class RetentionTracker:
"""Track construction retainage amounts."""
# Default release schedule
DEFAULT_RELEASE_SCHEDULE = {
ReleaseMilestone.SUBSTANTIAL_COMPLETION: 0.50, # 50% at substantial
ReleaseMilestone.FINAL_COMPLETION: 0.50, # 50% at final
}
def __init__(self, project_name: str, default_rate: float = 0.10):
self.project_name = project_name
self.default_rate = default_rate
self.subcontractors: Dict[str, SubcontractorRetention] = {}
self.release_schedule = dict(self.DEFAULT_RELEASE_SCHEDULE)
# Project-level retention (from owner)
self.owner_retention = SubcontractorRetention(
subcontractor_id="OWNER",
subcontractor_name="Owner Retention",
trade="GC",
contract_value=0,
retention_rate=default_rate
)
def set_release_schedule(self, schedule: Dict[ReleaseMilestone, float]):
"""Set custom release schedule."""
self.release_schedule = schedule
def add_subcontractor(self, id: str, name: str, trade: str,
contract_value: float,
retention_rate: float = None) -> SubcontractorRetention:
"""Add subcontractor to track."""
sub = SubcontractorRetention(
subcontractor_id=id,
subcontractor_name=name,
trade=trade,
contract_value=contract_value,
retention_rate=retention_rate if retention_rate else self.default_rate
)
self.subcontractors[id] = sub
return sub
def record_billing(self, subcontractor_id: str, pay_app_number: int,
billing_date: datetime, gross_billing: float) -> RetentionEntry:
"""Record billing and calculate retention."""
if subcontractor_id not in self.subcontractors:
raise ValueError(f"Subcontractor {subcontractor_id} not found")
sub = self.subcontractors[subcontractor_id]
retention_amount = gross_billing * sub.retention_rate
entry = RetentionEntry(
pay_app_number=pay_app_number,
billing_date=billing_date,
gross_billing=gross_billing,
retention_rate=sub.retention_rate,
retention_amount=retention_amount
)
sub.entries.append(entry)
# Update totals
sub.total_billed += gross_billing
sub.total_retained += retention_amount
sub.balance_held = sub.total_retained - sub.total_released
return entry
def record_owner_billing(self, pay_app_number: int, billing_date: datetime,
gross_billing: float) -> RetentionEntry:
"""Record owner-level retention."""
retention_amount = gross_billing * self.owner_retention.retention_rate
entry = RetentionEntry(
pay_app_number=pay_app_number,
billing_date=billing_date,
gross_billing=gross_billing,
retention_rate=self.owner_retention.retention_rate,
retention_amount=retention_amount
)
self.owner_retention.entries.append(entry)
self.owner_retention.total_billed += gross_billing
self.owner_retention.total_retained += retention_amount
self.owner_retention.balance_held = (
self.owner_retention.total_retained - self.owner_retention.total_released
)
return entry
def release_retention(self, subcontractor_id: str, milestone: ReleaseMilestone,
amount: float = None, approved_by: str = "",
conditions: List[str] = None,
lien_waivers: bool = False,
consent_of_surety: bool = False) -> RetentionRelease:
"""Release retention for subcontractor."""
if subcontractor_id not in self.subcontractors:
raise ValueError(f"Subcontractor {subcontractor_id} not found")
sub = self.subcontractors[subcontractor_id]
# Calculate release amount if not specified
if amount is None:
release_pct = self.release_schedule.get(milestone, 0.5)
amount = sub.balance_held * release_pct
if amount > sub.balance_held:
amount = sub.balance_held
release_id = f"REL-{subcontractor_id}-{len(sub.releases)+1:03d}"
release = RetentionRelease(
id=release_id,
release_date=datetime.now(),
milestone=milestone,
amount=amount,
remaining_after=sub.balance_held - amount,
approved_by=approved_by,
conditions_met=conditions or [],
lien_waivers_received=lien_waivers,
consent_of_surety=consent_of_surety
)
sub.releases.append(release)
sub.total_released += amount
sub.balance_held -= amount
if sub.balance_held <= 0:
sub.status = RetentionStatus.RELEASED
elif sub.total_released > 0:
sub.status = RetentionStatus.PARTIAL_RELEASE
return release
def release_owner_retention(self, milestone: ReleaseMilestone,
amount: float = None,
approved_by: str = "") -> RetentionRelease:
"""Release owner-level retention."""
if amount is None:
release_pct = self.release_schedule.get(milestone, 0.5)
amount = self.owner_retention.balance_held * release_pct
if amount > self.owner_retention.balance_held:
amount = self.owner_retention.balance_held
release_id = f"REL-OWNER-{len(self.owner_retention.releases)+1:03d}"
release = RetentionRelease(
id=release_id,
release_date=datetime.now(),
milestone=milestone,
amount=amount,
remaining_after=self.owner_retention.balance_held - amount,
approved_by=approved_by
)
self.owner_retention.releases.append(release)
self.owner_retention.total_released += amount
self.owner_retention.balance_held -= amount
return release
def check_release_conditions(self, subcontractor_id: str) -> Dict:
"""Check conditions required for retention release."""
if subcontractor_id not in self.subcontractors:
raise ValueError(f"Subcontractor {subcontractor_id} not found")
sub = self.subcontractors[subcontractor_id]
conditions = {
"punch_list_complete": False, # Check externally
"final_lien_waiver": False,
"consent_of_surety": False,
"as_builts_submitted": False,
"warranty_documents": False,
"training_complete": False,
"closeout_docs": False
}
# Check last release for received items
if sub.releases:
last_release = sub.releases[-1]
conditions["final_lien_waiver"] = last_release.lien_waivers_received
conditions["consent_of_surety"] = last_release.consent_of_surety
missing = [k for k, v in conditions.items() if not v]
return {
"subcontractor": sub.subcontractor_name,
"balance_held": sub.balance_held,
"conditions_status": conditions,
"missing_conditions": missing,
"ready_for_release": len(missing) == 0
}
def get_retention_summary(self) -> Dict:
"""Get overall retention summary."""
total_retained = sum(s.total_retained for s in self.subcontractors.values())
total_released = sum(s.total_released for s in self.subcontractors.values())
total_held = sum(s.balance_held for s in self.subcontractors.values())
by_status = {}
for sub in self.subcontractors.values():
status = sub.status.value
by_status[status] = by_status.get(status, 0) + 1
return {
"owner_retained": self.owner_retention.total_retained,
"owner_released": self.owner_retention.total_released,
"owner_balance": self.owner_retention.balance_held,
"sub_total_retained": total_retained,
"sub_total_released": total_released,
"sub_balance_held": total_held,
"net_retention_position": self.owner_retention.balance_held - total_held,
"subcontractors_count": len(self.subcontractors),
"by_status": by_status
}
def get_aged_retention(self) -> List[Dict]:
"""Get aged retention report."""
aged = []
for sub in self.subcontractors.values():
if sub.balance_held <= 0:
continue
# Find oldest unreleased entry
oldest_date = None
for entry in sub.entries:
if entry.status == RetentionStatus.HELD:
if oldest_date is None or entry.billing_date < oldest_date:
oldest_date = entry.billing_date
days_held = (datetime.now() - oldest_date).days if oldest_date else 0
aged.append({
"subcontractor_id": sub.subcontractor_id,
"subcontractor_name": sub.subcontractor_name,
"trade": sub.trade,
"balance_held": sub.balance_held,
"oldest_entry_date": oldest_date,
"days_held": days_held
})
return sorted(aged, key=lambda x: -x["days_held"])
def forecast_releases(self, substantial_date: datetime,
final_date: datetime) -> List[Dict]:
"""Forecast retention releases."""
forecasts = []
for sub in self.subcontractors.values():
if sub.balance_held <= 0:
continue
# Substantial completion release
sub_release = sub.balance_held * self.release_schedule.get(
ReleaseMilestone.SUBSTANTIAL_COMPLETION, 0.5
)
forecasts.append({
"date": substantial_date,
"subcontractor": sub.subcontractor_name,
"milestone": "Substantial Completion",
"amount": sub_release
})
# Final completion release
final_release = sub.balance_held - sub_release
forecasts.append({
"date": final_date,
"subcontractor": sub.subcontractor_name,
"milestone": "Final Completion",
"amount": final_release
})
return sorted(forecasts, key=lambda x: x["date"])
def generate_report(self) -> str:
"""Generate retention status report."""
summary = self.get_retention_summary()
lines = [
"# Retention Status Report",
"",
f"**Project:** {self.project_name}",
f"**Date:** {datetime.now().strftime('%Y-%m-%d')}",
"",
"## Summary",
"",
"### Owner Retention",
"",
f"| Metric | Amount |",
f"|--------|--------|",
f"| Total Retained | ${summary['owner_retained']:,.0f} |",
f"| Total Released | ${summary['owner_released']:,.0f} |",
f"| **Balance Held** | **${summary['owner_balance']:,.0f}** |",
"",
"### Subcontractor Retention",
"",
f"| Metric | Amount |",
f"|--------|--------|",
f"| Total Retained | ${summary['sub_total_retained']:,.0f} |",
f"| Total Released | ${summary['sub_total_released']:,.0f} |",
f"| **Balance Held** | **${summary['sub_balance_held']:,.0f}** |",
"",
f"**Net Position:** ${summary['net_retention_position']:,.0f}",
"",
"## By Subcontractor",
"",
"| Subcontractor | Trade | Contract | Retained | Released | Held | Status |",
"|---------------|-------|----------|----------|----------|------|--------|"
]
for sub in sorted(self.subcontractors.values(),
key=lambda s: -s.balance_held):
lines.append(
f"| {sub.subcontractor_name} | {sub.trade} | "
f"${sub.contract_value:,.0f} | ${sub.total_retained:,.0f} | "
f"${sub.total_released:,.0f} | ${sub.balance_held:,.0f} | "
f"{sub.status.value} |"
)
# Aged retention
aged = self.get_aged_retention()
if aged:
lines.extend([
"",
"## Aged Retention",
"",
"| Subcontractor | Balance | Days Held |",
"|---------------|---------|-----------|"
])
for item in aged[:10]:
lines.append(
f"| {item['subcontractor_name']} | "
f"${item['balance_held']:,.0f} | {item['days_held']} |"
)
return "\n".join(lines)
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.
- 8d ago First seen · 478 lines · 31 tokens per session scan A eef66b21aae6
retention-tracker is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (308 stars, last pushed 20d ago), licensed MIT. It adds 31 tokens to every session and 3,834 once invoked, about $0.0002 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
stripe-payments
Add Stripe payments to a web app — Checkout Sessions, Payment Intents, subscriptions, webhooks, customer portal, and pricing pages. Covers the decision of which Stripe API to use, produces working integration code, and handles webhook verification. No MCP server needed — uses Stripe npm package directly. Triggers…
"biz-management-accounting"
"Management accounting toolkit for internal decision support: ABC costing, variance analysis, transfer pricing, and responsibility accounting. Use for product profitability disputes, budget variance diagnosis, inter-division pricing design, and business-unit manager performance evaluation. Triggers…
actuarial-modeling
Analyzes actuarial modeling systems for loss reserving accuracy, premium pricing methodology, mortality/morbidity tables, stochastic modeling, and capital adequacy per SOA and Solvency II standards..
asset-lifecycle
Analyzes asset lifecycle planning systems for capital expenditure forecasting, replacement scheduling, total cost of ownership modeling, depreciation tracking, and facility condition assessments using IFMA standards and Facility Condition Index scoring..
commodity-pricing
Analyze commodity pricing and trading systems including forward curves, option models, position management, risk metrics, and regulatory reporting. Triggers: 'review pricing models', 'audit trading system', 'evaluate VaR implementation', 'check commodity risk management'.
fraud-detection
Analyze fraud detection systems including rule engines, ML scoring models, real-time transaction monitoring, alert triage workflows, false positive management, SAR/CTR regulatory reporting, adversarial robustness testing, and adaptive retraining pipelines for payment fraud, account takeover, identity theft, and AML…