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 automotive-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/automotive-expert)<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/automotive-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/automotive-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/automotive-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/automotive-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 | $0.00064 | $0.02958 |
| Opus 5 | $0.00032 | $0.01479 |
| Sonnet 5 | $0.00013 | $0.00592 |
| Haiku 4.5 | $0.00006 | $0.00296 |
Grade A, and why
automotive-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 6d 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 — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automotive Expert
Expert guidance for automotive systems, connected vehicles, fleet management, telematics, advanced driver assistance systems (ADAS), and automotive software development.
Core Concepts
Automotive Systems
- Telematics and fleet management
- Connected car platforms
- Advanced Driver Assistance Systems (ADAS)
- Electric Vehicle (EV) management
- Vehicle-to-Everything (V2X) communication
- Infotainment systems
- Diagnostic systems (OBD-II)
Technologies
- CAN bus and automotive networks
- AUTOSAR architecture
- Over-the-air (OTA) updates
- Autonomous driving systems
- Battery management systems
- Computer vision for ADAS
- Edge computing in vehicles
Standards and Protocols
- ISO 26262 (functional safety)
- AUTOSAR (automotive software architecture)
- J1939 (heavy-duty vehicle communication)
- UDS (Unified Diagnostic Services)
- SOME/IP (service-oriented middleware)
- MQTT for telematics
- CAN, LIN, FlexRay protocols
Connected Vehicle Platform
@dataclass
class VehicleTelemetry:
"""Real-time vehicle telemetry data"""
vehicle_id: str
timestamp: datetime
location: tuple
speed_kmh: float
rpm: int
engine_temp_c: float
battery_voltage: float
fuel_level_percent: float
odometer_km: int
dtc_codes: List[str] # Diagnostic Trouble Codes
class ConnectedVehiclePlatform:
"""Connected car platform with OTA updates"""
def __init__(self):
self.vehicles = {}
self.telemetry_buffer = []
self.ota_updates = {}
def process_telemetry(self, telemetry: VehicleTelemetry) -> dict:
"""Process incoming telemetry data"""
self.telemetry_buffer.append(telemetry)
# Analyze telemetry for anomalies
alerts = []
# Check engine temperature
if telemetry.engine_temp_c > 110:
alerts.append({
'type': 'high_engine_temp',
'severity': 'warning',
'value': telemetry.engine_temp_c,
'message': 'Engine temperature above normal'
})
# Check battery voltage
if telemetry.battery_voltage < 12.0:
alerts.append({
'type': 'low_battery',
'severity': 'warning',
'value': telemetry.battery_voltage,
'message': 'Battery voltage low'
})
# Check for diagnostic trouble codes
if telemetry.dtc_codes:
alerts.append({
'type': 'dtc_codes',
'severity': 'critical',
'codes': telemetry.dtc_codes,
'message': f'{len(telemetry.dtc_codes)} diagnostic code(s) detected'
})
# Check for harsh driving
if len(self.telemetry_buffer) >= 2:
prev = self.telemetry_buffer[-2]
if telemetry.vehicle_id == prev.vehicle_id:
time_diff = (telemetry.timestamp - prev.timestamp).total_seconds()
if time_diff > 0:
acceleration = (telemetry.speed_kmh - prev.speed_kmh) / time_diff
if abs(acceleration) > 5: # > 5 km/h per second
alerts.append({
'type': 'harsh_driving',
'severity': 'info',
'acceleration': acceleration,
'message': 'Harsh acceleration/braking detected'
})
return {
'vehicle_id': telemetry.vehicle_id,
'timestamp': telemetry.timestamp.isoformat(),
'alerts': alerts,
'health_score': self._calculate_vehicle_health(telemetry)
}
def deploy_ota_update(self,
vehicle_ids: List[str],
update_package: dict) -> dict:
"""Deploy over-the-air software update"""
update_id = self._generate_update_id()
ota_update = {
'update_id': update_id,
'version': update_package['version'],
'description': update_package['description'],
'package_size_mb': update_package['size_mb'],
'target_vehicles': vehicle_ids,
'deployed_at': datetime.now(),
'status_by_vehicle': {}
}
for vehicle_id in vehicle_ids:
# Schedule update for vehicle
ota_update['status_by_vehicle'][vehicle_id] = {
'status': 'scheduled',
'download_progress': 0,
'install_progress': 0
}
self.ota_updates[update_id] = ota_update
return {
'update_id': update_id,
'vehicles_targeted': len(vehicle_ids),
'estimated_completion': 'Within 48 hours'
}
def diagnose_vehicle(self, vehicle_id: str, dtc_codes: List[str]) -> dict:
"""Diagnose vehicle issues from DTC codes"""
diagnoses = []
for code in dtc_codes:
diagnosis = self._lookup_dtc_code(code)
diagnoses.append(diagnosis)
# Calculate severity
max_severity = max(d['severity'] for d in diagnoses)
return {
'vehicle_id': vehicle_id,
'dtc_codes': dtc_codes,
'diagnoses': diagnoses,
'overall_severity': max_severity,
'service_recommended': max_severity in ['high', 'critical']
}
def _calculate_vehicle_health(self, telemetry: VehicleTelemetry) -> float:
"""Calculate overall vehicle health score"""
score = 100.0
# Engine temperature
if telemetry.engine_temp_c > 110:
score -= 15
elif telemetry.engine_temp_c > 100:
score -= 5
# Battery voltage
if telemetry.battery_voltage < 11.5:
score -= 20
elif telemetry.battery_voltage < 12.0:
score -= 10
# DTC codes
score -= len(telemetry.dtc_codes) * 15
return max(0.0, score)
def _lookup_dtc_code(self, code: str) -> dict:
"""Lookup diagnostic trouble code"""
# Simplified DTC lookup
# In production, would use comprehensive OBD-II code database
dtc_database = {
'P0171': {
'description': 'System Too Lean (Bank 1)',
'severity': 'medium',
'possible_causes': ['Vacuum leak', 'Faulty MAF sensor', 'Fuel filter clogged']
},
'P0300': {
'description': 'Random/Multiple Cylinder Misfire Detected',
'severity': 'high',
'possible_causes': ['Faulty spark plugs', 'Ignition coil failure', 'Fuel injector issue']
}
}
return dtc_database.get(code, {
'description': f'Unknown code: {code}',
'severity': 'medium',
'possible_causes': ['Requires diagnostic scan']
})
def _generate_update_id(self) -> str:
import uuid
return f"OTA-{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.
- 6d ago Changed · -338 lines · +39 tokens per session ef2c6eae1190
- 11d ago First seen · 760 lines · 25 tokens per session scan A 591c99cd1eee
automotive-expert is a skill published in the GitHub repository personamanagmentlayer/pcl (40 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 2,958 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
automotive-telematics
Expert skill in cellular focusing on telematics domain applications. Covers 40 topics across telematics domain. Includes 40 skill files covering ASPICE Level 3, AUTOSAR 4.4, ISO 21434, ISO 26262.
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.