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 pangzhenying2025/hermes-automotive-skills --skill automotive-v2xgit clone --depth 1 https://github.com/pangzhenying2025/hermes-automotive-skillsWrote 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/pangzhenying2025/hermes-automotive-skills/automotive-v2x)<a href="https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/automotive-v2x"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-v2x/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/pangzhenying2025/hermes-automotive-skills/automotive-v2x"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-v2x.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00050 | $0.42164 |
| Opus 5 | $0.00025 | $0.21082 |
| Sonnet 5 | $0.00010 | $0.08433 |
| Haiku 4.5 | $0.00005 | $0.04216 |
Grade A, and why
automotive-v2x 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 9d 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 — 5,636 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automotive V2X
Cv2X 5G Integration
C-V2X and 5G Integration
Overview
C-V2X (Cellular V2X) integration with 5G networks including PC5 sidelink communication modes, network slicing, Multi-access Edge Computing (MEC), Ultra-Reliable Low-Latency Communication (URLLC), and 5G NR V2X features.
C-V2X Communication Modes
Mode 3 vs Mode 4 Comparison
| Feature | Mode 3 (Network Scheduled) | Mode 4 (Autonomous/D2D) |
|---|---|---|
| Infrastructure Required | Yes (eNodeB/gNodeB) | No (direct sidelink) |
| Resource Allocation | Network-scheduled (centralized) | Distributed sensing |
| Coverage Dependency | Requires cellular coverage | Works without network |
| Typical Latency | 20-50 ms (via network) | 10-20 ms (direct) |
| QoS Guarantee | Network-enforced QoS | Best-effort coordination |
| Ideal Use Case | Urban with good coverage | Rural, tunnels, emergencies |
| Handover | Network-managed | Autonomous |
| Power Consumption | Higher (constant network sync) | Lower (periodic only) |
5G NR-V2X Physical Layer
Frequency Bands:
5.9 GHz ITS Band:
- 5.855-5.925 GHz (US, EU, Asia harmonized)
- Channel bandwidth: 10/20 MHz
- Supports both DSRC coexistence and C-V2X
Licensed Spectrum:
- Band n78 (3.5 GHz): High capacity urban
- Band n79 (4.7 GHz): Regional deployments
- Mmwave (28/39 GHz): Ultra-high data rate applications
Numerology:
Subcarrier spacing: 15/30/60 kHz
- 15 kHz: Long range, low mobility
- 30 kHz: Standard V2X (recommended)
- 60 kHz: High mobility scenarios
Symbol duration: 66.7/33.3/16.7 μs
Cyclic prefix: 4.7/2.3/1.2 μs
Network Slicing for V2X
Slice Configuration
# network_slicing.py
"""
5G Network slicing for differentiated V2X services.
"""
from dataclasses import dataclass
from enum import Enum
from typing import List
class SliceServiceType(Enum):
"""Service and Slice Differentiator (SST)"""
URLLC = 1 # Ultra-reliable low-latency
EMBB = 2 # Enhanced mobile broadband
MMTC = 3 # Massive machine-type communications
@dataclass
class NetworkSliceDescriptor:
"""5G Network Slice Selection Assistance Information (NSSAI)"""
sst: SliceServiceType # Slice/Service Type
sd: int # Slice Differentiator (24 bits)
# Performance KPIs
target_latency_ms: int
reliability_percent: float
max_data_rate_mbps: int
connection_density_per_km2: int
# Resource allocation
guaranteed_bit_rate_mbps: int
priority_level: int # 1 (highest) to 15 (lowest)
# V2V Safety Communications Slice
SLICE_V2V_SAFETY = NetworkSliceDescriptor(
sst=SliceServiceType.URLLC,
sd=0x000001, # V2V safety specific
target_latency_ms=5,
reliability_percent=99.9999, # Six nines
max_data_rate_mbps=10,
connection_density_per_km2=10000,
guaranteed_bit_rate_mbps=2,
priority_level=1
)
# V2I Traffic Management Slice
SLICE_V2I_TRAFFIC = NetworkSliceDescriptor(
sst=SliceServiceType.URLLC,
sd=0x000002,
target_latency_ms=20,
reliability_percent=99.99,
max_data_rate_mbps=5,
connection_density_per_km2=5000,
guaranteed_bit_rate_mbps=1,
priority_level=3
)
# V2N Infotainment Slice
SLICE_V2N_INFOTAINMENT = NetworkSliceDescriptor(
sst=SliceServiceType.EMBB,
sd=0x000003,
target_latency_ms=100,
reliability_percent=99.0,
max_data_rate_mbps=100,
connection_density_per_km2=1000,
guaranteed_bit_rate_mbps=10,
priority_level=10
)
class NetworkSliceManager:
"""Manage network slice selection for V2X traffic."""
def __init__(self):
self.available_slices = [
SLICE_V2V_SAFETY,
SLICE_V2I_TRAFFIC,
SLICE_V2N_INFOTAINMENT
]
self.current_slice = None
def select_slice_for_message(self, message_type: str, qos_requirement: str) -> NetworkSliceDescriptor:
"""
Select appropriate network slice based on message type and QoS.
Args:
message_type: "BSM", "DENM", "CAM", "SPaT", "MAP", etc.
qos_requirement: "critical", "high", "medium", "low"
Returns:
NetworkSliceDescriptor
"""
# Safety-critical messages
if message_type in ["BSM", "CAM", "DENM", "EEBL"] or qos_requirement == "critical":
return SLICE_V2V_SAFETY
# Infrastructure messages
elif message_type in ["SPaT", "MAP", "TIM"] or qos_requirement == "high":
return SLICE_V2I_TRAFFIC
# Non-critical services
else:
return SLICE_V2N_INFOTAINMENT
def request_slice_activation(self, nssai: NetworkSliceDescriptor) -> bool:
"""
Request slice activation from 5G core.
In production: NGAP signaling to AMF (Access and Mobility Management Function)
"""
print(f"Requesting slice activation:")
print(f" SST: {nssai.sst.name}")
print(f" SD: {nssai.sd:#08x}")
print(f" Latency: {nssai.target_latency_ms} ms")
print(f" Reliability: {nssai.reliability_percent}%")
# Simulate AMF response
self.current_slice = nssai
return True
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.
- 9d ago First seen · 5,636 lines · 50 tokens per session scan A a4332fdf732c
automotive-v2x is a skill published in the GitHub repository pangzhenying2025/hermes-automotive-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 42,164 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 2026-09-03.
Other skills, from other repositories
iso26262
ISO 26262 functional-safety expert that operates in two modes: (1) HARA / ASIL determination — enumerate hazardous events from item malfunctions × driving situations, rate Severity (S0–S3), Exposure (E0–E4), Controllability (C0–C3), look up ASIL from ISO 26262-3:2018 Table 4, and produce a HARA report with Safety…
automotive-syseng
When the user wants to analyze automotive requirements, check INCOSE/EARS compliance, review MISRA-C code, assess ADAS levels, or verify ISO 26262/AUTOSAR/SOTIF conformance. Also use when the user says 'check requirements', 'EARS check', 'INCOSE analysis', 'MISRA check', 'ASIL assessment', 'V-model check'…
automotive-expert
Expert-level automotive systems, connected vehicles, fleet management, telematics, ADAS, and automotive software. Use when the user mentions connected car, fleet, telematics, ADAS, or vehicle, or when the task involves Automotive Systems, Technologies, Standards and Protocols, or Fleet Management.
codebase-analysis
First-run skill that walks the entire repository, auto-detects Classic vs Adaptive AUTOSAR, and maps it accordingly. For Classic (default): identifies features and SWCs and documents referenced requirement IDs (SW-REQ-, REQ-, FSR-, SYS-REQ-), port interfaces (S/R, C/S, Mode Switch, Parameter), dependencies on other…
autosar-bsw
AUTOSAR BSW expert. Defaults to Classic AUTOSAR (BSW/MCAL/RTE, static config, C, AUTOSAR OS) and operates in six modes: (1) BSW configuration — Com, NvM, Dem, Dcm, Os, MemIf with dependency chain and EB Tresos / DaVinci container paths; (2) ARXML debugging — classify, locate, and fix consistency errors with a…
autosar-swc
AUTOSAR SWC expert. Defaults to Classic AUTOSAR (SWCs, RTE, ARXML, C) and operates in five modes: (1) Component design — decompose a feature into SWC types, define port interfaces, specify runnables and ExclusiveAreas, produce a plain-text composition diagram; (2) Interface definition — SenderReceiver / ClientServer /…