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 personamanagmentlayer/pcl --skill construction-expertgit clone --depth 1 https://github.com/personamanagmentlayer/pclWrote 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/personamanagmentlayer/pcl/construction-expert)<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/construction-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/construction-expert/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/personamanagmentlayer/pcl/construction-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/construction-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00054 | $0.02313 |
| Opus 5 | $0.00027 | $0.01156 |
| Sonnet 5 | $0.00011 | $0.00463 |
| Haiku 4.5 | $0.00005 | $0.00231 |
Grade A, and why
construction-expert 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Construction Expert
Expert guidance for construction management, project planning, Building Information Modeling (BIM), safety compliance, and modern construction technology solutions.
Core Concepts
Construction Management
- Project planning and scheduling
- Cost estimation and control
- Resource management
- Quality assurance
- Contract management
- Risk management
- Change order management
Technologies
- Building Information Modeling (BIM)
- Construction management software
- Drone surveying and inspection
- 3D printing and modular construction
- IoT sensors for monitoring
- Augmented reality for visualization
- Construction robotics
Standards and Regulations
- OSHA safety regulations
- Building codes (IBC, IRC)
- AIA contracts and standards
- LEED certification
- ISO 19650 (BIM standards)
- CSI MasterFormat
- Environmental regulations
Safety Management System
@dataclass
class SafetyIncident:
"""Safety incident report"""
incident_id: str
project_id: str
incident_type: str # 'injury', 'near_miss', 'property_damage'
severity: str # 'minor', 'moderate', 'severe', 'fatal'
description: str
location: str
occurred_at: datetime
reported_by: str
injured_person: Optional[str]
root_cause: Optional[str]
corrective_actions: List[str]
class SafetyManagementSystem:
"""Construction safety management"""
def __init__(self):
self.incidents = []
self.safety_inspections = []
self.training_records = []
def conduct_safety_inspection(self, project_id: str, inspector: str) -> dict:
"""Conduct safety inspection"""
inspection_items = [
'Personal protective equipment (PPE)',
'Fall protection systems',
'Scaffolding integrity',
'Electrical safety',
'Equipment guarding',
'Housekeeping',
'Fire prevention',
'First aid availability',
'Emergency exits',
'Signage and barriers'
]
violations = []
passed_items = []
# Simulate inspection (in production, would be actual checklist)
for item in inspection_items:
# Random pass/fail for demonstration
import random
if random.random() < 0.85: # 85% pass rate
passed_items.append(item)
else:
violations.append({
'item': item,
'severity': random.choice(['minor', 'major']),
'action_required': 'Correct immediately' if random.random() < 0.3 else 'Correct within 24 hours'
})
inspection = {
'inspection_id': self._generate_inspection_id(),
'project_id': project_id,
'inspector': inspector,
'inspection_date': datetime.now(),
'items_inspected': len(inspection_items),
'items_passed': len(passed_items),
'violations': violations,
'overall_score': (len(passed_items) / len(inspection_items)) * 100,
'status': 'pass' if len(violations) == 0 else 'fail'
}
self.safety_inspections.append(inspection)
return inspection
def report_incident(self, incident_data: dict) -> SafetyIncident:
"""Report safety incident"""
incident = SafetyIncident(
incident_id=self._generate_incident_id(),
project_id=incident_data['project_id'],
incident_type=incident_data['incident_type'],
severity=incident_data['severity'],
description=incident_data['description'],
location=incident_data['location'],
occurred_at=incident_data['occurred_at'],
reported_by=incident_data['reported_by'],
injured_person=incident_data.get('injured_person'),
root_cause=None,
corrective_actions=[]
)
self.incidents.append(incident)
# Notify relevant parties
self._notify_incident(incident)
return incident
def calculate_safety_metrics(self, project_id: str, hours_worked: float) -> dict:
"""Calculate safety performance metrics"""
project_incidents = [
i for i in self.incidents
if i.project_id == project_id
]
# Count recordable incidents
recordable_incidents = [
i for i in project_incidents
if i.incident_type == 'injury' and i.severity in ['moderate', 'severe', 'fatal']
]
# OSHA Incident Rate = (Number of incidents × 200,000) / Total hours worked
if hours_worked > 0:
incident_rate = (len(recordable_incidents) * 200000) / hours_worked
else:
incident_rate = 0
# Days Away, Restricted, or Transferred (DART) Rate
dart_incidents = [
i for i in recordable_incidents
if i.severity in ['severe', 'fatal']
]
dart_rate = (len(dart_incidents) * 200000) / hours_worked if hours_worked > 0 else 0
return {
'project_id': project_id,
'total_hours_worked': hours_worked,
'total_incidents': len(project_incidents),
'recordable_incidents': len(recordable_incidents),
'incident_rate': incident_rate,
'dart_rate': dart_rate,
'safety_rating': 'Excellent' if incident_rate < 1.0 else
'Good' if incident_rate < 3.0 else
'Needs Improvement'
}
def _notify_incident(self, incident: SafetyIncident):
"""Notify stakeholders of incident"""
# Implementation would send notifications
pass
def _generate_inspection_id(self) -> str:
import uuid
return f"INS-{uuid.uuid4().hex[:8].upper()}"
def _generate_incident_id(self) -> str:
import uuid
return f"INC-{uuid.uuid4().hex[:8].upper()}"
What ships with it
1 file 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.
- 4d ago Changed · -269 lines · +34 tokens per session 5f270a547634
- 9d ago First seen · 618 lines · 20 tokens per session scan A 450f03bec93a
construction-expert is a skill published in the GitHub repository personamanagmentlayer/pcl (40 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 2,313 once invoked, about $0.0003 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
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
sdlc-review
Review Kanban handoffs and route verified outcomes.
teams-meeting-pipeline
Teams meeting summaries, job replay, Graph subscriptions.
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
clawrouter
Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 76 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data…
surf
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/ covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT…