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 telecommunications-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/telecommunications-expert)<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/telecommunications-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/telecommunications-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/telecommunications-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/telecommunications-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 | $0.00067 | $0.03081 |
| Opus 5 | $0.00034 | $0.01541 |
| Sonnet 5 | $0.00013 | $0.00616 |
| Haiku 4.5 | $0.00007 | $0.00308 |
Grade A, and why
telecommunications-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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telecommunications Expert
Expert guidance for telecommunications systems, network management, billing systems, 5G networks, SDN/NFV, and telecom infrastructure management.
Core Concepts
Telecommunications Systems
- Operations Support Systems (OSS)
- Business Support Systems (BSS)
- Network Management Systems (NMS)
- Service Assurance
- Inventory Management
- Provisioning systems
- Customer care platforms
Network Technologies
- 5G/4G/LTE networks
- Fiber optic networks
- Software-Defined Networking (SDN)
- Network Functions Virtualization (NFV)
- Edge computing
- IoT connectivity
- Satellite communications
Standards and Protocols
- 3GPP standards
- TM Forum Frameworx
- ETSI specifications
- ITU-T recommendations
- SIP (Session Initiation Protocol)
- Diameter protocol
- SNMP for network management
Billing System
from decimal import Decimal
@dataclass
class Subscriber:
"""Telecom subscriber"""
subscriber_id: str
account_number: str
name: str
phone_number: str
email: str
address: dict
plan_id: str
status: str # 'active', 'suspended', 'terminated'
activation_date: datetime
@dataclass
class ServicePlan:
"""Service plan/package"""
plan_id: str
name: str
description: str
monthly_fee: Decimal
data_allowance_gb: float
voice_minutes: int
sms_count: int
overage_rates: dict
@dataclass
class UsageRecord:
"""Usage record for billing"""
record_id: str
subscriber_id: str
usage_type: str # 'voice', 'sms', 'data'
timestamp: datetime
quantity: float
unit: str
destination: Optional[str]
charged: bool
class BillingSystem:
"""Telecom billing and charging system"""
def __init__(self):
self.subscribers = {}
self.service_plans = {}
self.usage_records = []
self.invoices = []
def process_usage(self, usage: UsageRecord) -> dict:
"""Process usage record for charging"""
subscriber = self.subscribers.get(usage.subscriber_id)
if not subscriber:
return {'error': 'Subscriber not found'}
if subscriber.status != 'active':
return {'error': 'Subscriber not active'}
plan = self.service_plans.get(subscriber.plan_id)
if not plan:
return {'error': 'Service plan not found'}
# Check if usage is within plan allowance
current_usage = self._get_current_month_usage(usage.subscriber_id, usage.usage_type)
charge = Decimal('0')
if usage.usage_type == 'data':
if current_usage > plan.data_allowance_gb:
# Overage charges
overage_gb = usage.quantity
charge = Decimal(str(overage_gb)) * plan.overage_rates['data_per_gb']
elif usage.usage_type == 'voice':
if current_usage > plan.voice_minutes:
# Overage charges
overage_minutes = usage.quantity
charge = Decimal(str(overage_minutes)) * plan.overage_rates['voice_per_minute']
elif usage.usage_type == 'sms':
if current_usage > plan.sms_count:
# Overage charges
overage_sms = usage.quantity
charge = Decimal(str(overage_sms)) * plan.overage_rates['sms_per_message']
usage.charged = True
self.usage_records.append(usage)
return {
'subscriber_id': usage.subscriber_id,
'usage_type': usage.usage_type,
'quantity': usage.quantity,
'charge': float(charge),
'within_allowance': charge == 0
}
def generate_invoice(self, subscriber_id: str, billing_period: tuple) -> dict:
"""Generate monthly invoice"""
subscriber = self.subscribers.get(subscriber_id)
if not subscriber:
return {'error': 'Subscriber not found'}
plan = self.service_plans.get(subscriber.plan_id)
start_date, end_date = billing_period
# Base charges
monthly_fee = plan.monthly_fee
# Usage charges
period_usage = [
u for u in self.usage_records
if u.subscriber_id == subscriber_id and
start_date <= u.timestamp <= end_date
]
usage_charges = self._calculate_usage_charges(period_usage, plan)
# Taxes (simplified)
subtotal = monthly_fee + usage_charges['total']
tax_rate = Decimal('0.10') # 10%
taxes = subtotal * tax_rate
total = subtotal + taxes
invoice = {
'invoice_id': self._generate_invoice_id(),
'subscriber_id': subscriber_id,
'account_number': subscriber.account_number,
'billing_period': {
'start': start_date.isoformat(),
'end': end_date.isoformat()
},
'charges': {
'monthly_fee': float(monthly_fee),
'data_charges': float(usage_charges['data']),
'voice_charges': float(usage_charges['voice']),
'sms_charges': float(usage_charges['sms']),
'other_charges': float(usage_charges['other'])
},
'subtotal': float(subtotal),
'taxes': float(taxes),
'total': float(total),
'due_date': (end_date + timedelta(days=15)).isoformat()
}
self.invoices.append(invoice)
return invoice
def _get_current_month_usage(self, subscriber_id: str, usage_type: str) -> float:
"""Get current month usage for subscriber"""
current_month_start = datetime.now().replace(day=1, hour=0, minute=0, second=0)
usage = [
u for u in self.usage_records
if u.subscriber_id == subscriber_id and
u.usage_type == usage_type and
u.timestamp >= current_month_start
]
total = sum(u.quantity for u in usage)
return total
def _calculate_usage_charges(self,
usage_records: List[UsageRecord],
plan: ServicePlan) -> dict:
"""Calculate usage charges"""
charges = {
'data': Decimal('0'),
'voice': Decimal('0'),
'sms': Decimal('0'),
'other': Decimal('0'),
'total': Decimal('0')
}
# Group usage by type
data_usage = sum(u.quantity for u in usage_records if u.usage_type == 'data')
voice_usage = sum(u.quantity for u in usage_records if u.usage_type == 'voice')
sms_usage = sum(u.quantity for u in usage_records if u.usage_type == 'sms')
# Calculate overage charges
if data_usage > plan.data_allowance_gb:
overage = data_usage - plan.data_allowance_gb
charges['data'] = Decimal(str(overage)) * plan.overage_rates['data_per_gb']
if voice_usage > plan.voice_minutes:
overage = voice_usage - plan.voice_minutes
charges['voice'] = Decimal(str(overage)) * plan.overage_rates['voice_per_minute']
if sms_usage > plan.sms_count:
overage = sms_usage - plan.sms_count
charges['sms'] = Decimal(str(overage)) * plan.overage_rates['sms_per_message']
charges['total'] = sum([charges['data'], charges['voice'], charges['sms'], charges['other']])
return charges
def _generate_invoice_id(self) -> str:
import uuid
return f"INV-{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 · -267 lines · +42 tokens per session 998e68608ac7
- 7d ago First seen · 709 lines · 25 tokens per session scan A 7546a6bfdfed
telecommunications-expert is a skill published in the GitHub repository personamanagmentlayer/pcl (40 stars, last pushed 3d ago), licensed Apache-2.0. It adds 67 tokens to every session and 3,081 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
telecom-networks
Architect Telecom interfaces using TM Forum ODA, GSMA CAMARA, and eSIM standards.
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.