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 aerospace-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/aerospace-expert)<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/aerospace-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/aerospace-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/aerospace-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/aerospace-expert.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 | $0.00061 | $0.03089 |
| Opus 5 | $0.00030 | $0.01545 |
| Sonnet 5 | $0.00012 | $0.00618 |
| Haiku 4.5 | $0.00006 | $0.00309 |
Grade A, and why
aerospace-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 5d 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 — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aerospace Expert
Expert guidance for aerospace systems, flight management, maintenance tracking, aviation safety, air traffic control systems, and aerospace software development.
Core Concepts
Aerospace Systems
- Flight Management Systems (FMS)
- Maintenance, Repair, and Overhaul (MRO)
- Air Traffic Control (ATC) systems
- Aircraft Health Monitoring
- Flight Operations Quality Assurance (FOQA)
- Crew resource management
- Ground handling systems
Aviation Technologies
- Avionics systems
- ACARS (Aircraft Communications Addressing and Reporting System)
- ADS-B (Automatic Dependent Surveillance-Broadcast)
- Flight data recorders (black boxes)
- Weather radar systems
- Autopilot and fly-by-wire
- Satellite communications
Standards and Regulations
- FAA regulations (Federal Aviation Administration)
- EASA standards (European Union Aviation Safety Agency)
- ICAO standards (International Civil Aviation Organization)
- DO-178C (software airworthiness)
- DO-254 (hardware airworthiness)
- SPEC-42 (maintenance tracking)
- ATA chapters (maintenance organization)
Aircraft Maintenance System
from enum import Enum
class MaintenanceType(Enum):
A_CHECK = "a_check" # Every 400-600 flight hours
B_CHECK = "b_check" # Every 6-8 months
C_CHECK = "c_check" # Every 18-24 months
D_CHECK = "d_check" # Every 6-10 years
LINE_MAINTENANCE = "line_maintenance"
UNSCHEDULED = "unscheduled"
@dataclass
class Aircraft:
"""Aircraft information"""
aircraft_id: str
registration: str
aircraft_type: str
manufacturer: str
model: str
serial_number: str
manufacture_date: datetime
total_flight_hours: float
total_cycles: int # Takeoff/landing cycles
last_a_check: datetime
last_c_check: datetime
airworthiness_certificate: str
next_major_inspection: datetime
@dataclass
class MaintenanceRecord:
"""Maintenance work record"""
record_id: str
aircraft_id: str
maintenance_type: MaintenanceType
work_performed: str
components_replaced: List[str]
performed_by: str
performed_at: datetime
flight_hours_at_maintenance: float
cycles_at_maintenance: int
next_due_hours: Optional[float]
next_due_date: Optional[datetime]
class AircraftMaintenanceSystem:
"""MRO (Maintenance, Repair, Overhaul) system"""
def __init__(self):
self.aircraft = {}
self.maintenance_records = []
self.component_tracking = {}
def check_maintenance_due(self, aircraft_id: str) -> dict:
"""Check if maintenance is due for aircraft"""
aircraft = self.aircraft.get(aircraft_id)
if not aircraft:
return {'error': 'Aircraft not found'}
due_items = []
# Check A-check (every 500 hours)
hours_since_a_check = aircraft.total_flight_hours - self._get_last_check_hours(
aircraft_id, MaintenanceType.A_CHECK
)
if hours_since_a_check >= 500:
due_items.append({
'type': 'A-check',
'urgency': 'high' if hours_since_a_check >= 550 else 'medium',
'hours_overdue': max(0, hours_since_a_check - 500)
})
# Check calendar-based C-check
days_since_c_check = (datetime.now() - aircraft.last_c_check).days
if days_since_c_check >= 540: # 18 months
due_items.append({
'type': 'C-check',
'urgency': 'critical' if days_since_c_check >= 600 else 'high',
'days_overdue': max(0, days_since_c_check - 540)
})
# Check component life limits
component_items = self._check_component_life_limits(aircraft_id)
due_items.extend(component_items)
return {
'aircraft_id': aircraft_id,
'registration': aircraft.registration,
'maintenance_required': len(due_items) > 0,
'due_items': due_items,
'airworthy': len([item for item in due_items if item['urgency'] == 'critical']) == 0
}
def _get_last_check_hours(self, aircraft_id: str, check_type: MaintenanceType) -> float:
"""Get flight hours at last check"""
records = [
r for r in self.maintenance_records
if r.aircraft_id == aircraft_id and r.maintenance_type == check_type
]
if records:
latest = max(records, key=lambda r: r.performed_at)
return latest.flight_hours_at_maintenance
return 0.0
def _check_component_life_limits(self, aircraft_id: str) -> List[dict]:
"""Check component life limits"""
due_items = []
components = self.component_tracking.get(aircraft_id, {})
for component_name, component_data in components.items():
if component_data['life_limit_hours']:
hours_used = component_data['hours_since_new']
life_limit = component_data['life_limit_hours']
if hours_used >= life_limit * 0.9: # Within 90% of life limit
due_items.append({
'type': 'component_replacement',
'component': component_name,
'urgency': 'critical' if hours_used >= life_limit else 'high',
'hours_remaining': max(0, life_limit - hours_used)
})
return due_items
def record_maintenance(self,
aircraft_id: str,
maintenance_data: dict) -> MaintenanceRecord:
"""Record completed maintenance"""
aircraft = self.aircraft.get(aircraft_id)
if not aircraft:
raise ValueError("Aircraft not found")
record = MaintenanceRecord(
record_id=self._generate_record_id(),
aircraft_id=aircraft_id,
maintenance_type=MaintenanceType(maintenance_data['type']),
work_performed=maintenance_data['work_performed'],
components_replaced=maintenance_data.get('components_replaced', []),
performed_by=maintenance_data['technician_id'],
performed_at=datetime.now(),
flight_hours_at_maintenance=aircraft.total_flight_hours,
cycles_at_maintenance=aircraft.total_cycles,
next_due_hours=maintenance_data.get('next_due_hours'),
next_due_date=maintenance_data.get('next_due_date')
)
self.maintenance_records.append(record)
# Update aircraft maintenance dates
if record.maintenance_type == MaintenanceType.A_CHECK:
aircraft.last_a_check = datetime.now()
elif record.maintenance_type == MaintenanceType.C_CHECK:
aircraft.last_c_check = datetime.now()
return record
def predict_maintenance_cost(self,
aircraft_type: str,
flight_hours_per_year: float) -> dict:
"""Predict annual maintenance costs"""
# Base maintenance costs per aircraft type
base_costs = {
'B737': {
'hourly_rate': 800, # $ per flight hour
'a_check': 25000,
'c_check': 500000,
'd_check': 5000000
},
'B777': {
'hourly_rate': 1500,
'a_check': 50000,
'c_check': 1000000,
'd_check': 10000000
}
}
costs = base_costs.get(aircraft_type, base_costs['B737'])
# Calculate annual costs
hourly_maintenance = flight_hours_per_year * costs['hourly_rate']
# A-checks (assume 2 per year for 1000 hours/year)
a_checks_per_year = flight_hours_per_year / 500
a_check_costs = a_checks_per_year * costs['a_check']
# C-check (amortized over 18 months)
c_check_annual = costs['c_check'] / 1.5
# D-check (amortized over 8 years)
d_check_annual = costs['d_check'] / 8
total_annual = hourly_maintenance + a_check_costs + c_check_annual + d_check_annual
return {
'aircraft_type': aircraft_type,
'flight_hours_per_year': flight_hours_per_year,
'maintenance_costs': {
'hourly_maintenance': hourly_maintenance,
'a_checks': a_check_costs,
'c_check_amortized': c_check_annual,
'd_check_amortized': d_check_annual,
'total_annual': total_annual
},
'cost_per_flight_hour': total_annual / flight_hours_per_year
}
def _generate_record_id(self) -> str:
import uuid
return f"MX-{uuid.uuid4().hex[:10].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.
- 5d ago Changed · -337 lines · +38 tokens per session 7b71ef7f1455
- 11d ago First seen · 760 lines · 23 tokens per session scan A 8162616729d2
aerospace-expert is a skill published in the GitHub repository personamanagmentlayer/pcl (40 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 3,089 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
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 78 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…
phone
Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai). Trigger when the user asks to look up a number, check fraud risk, buy/rent a phone number, or place an AI voice call. Payment is automatic via x402 from the wallet.
imagegen
Generate or edit images via BlockRun's image API. Trigger when the user asks to generate, create, draw, make an image — or to edit, modify, change, or retouch an existing image.
polymarket-trading
Use when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools). Covers setup (deposit wallet, funding, approvals), buy/sell with confirm gating, positions, redeeming winnings, geoblock handling, and the end-to-end flow.
release
Use this skill for EVERY ClawRouter release. Enforces the full checklist — version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release. No step can be skipped.