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 Ghosteken/agent-harness --skill azure-messaging-webpubsubservice-pygit clone --depth 1 https://github.com/Ghosteken/agent-harnessWrote 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/ghosteken/agent-harness/azure-messaging-webpubsubservice-py)<a href="https://agentmods.dev/skills/ghosteken/agent-harness/azure-messaging-webpubsubservice-py"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/azure-messaging-webpubsubservice-py/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/ghosteken/agent-harness/azure-messaging-webpubsubservice-py"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/azure-messaging-webpubsubservice-py.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 | $0.00034 | $0.01405 |
| Opus 5 | $0.00017 | $0.00702 |
| Sonnet 5 | $0.00007 | $0.00281 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
azure-messaging-webpubsubservice-py 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 8d 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.
This is a copy
86% identical to azure-messaging-webpubsubservice-py — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Web PubSub Service SDK for Python
Real-time messaging with WebSocket connections at scale.
Installation
# Service SDK (server-side)
pip install azure-messaging-webpubsubservice
# Client SDK (for Python WebSocket clients)
pip install azure-messaging-webpubsubclient
Environment Variables
AZURE_WEBPUBSUB_CONNECTION_STRING=Endpoint=https://<name>.webpubsub.azure.com;AccessKey=...
AZURE_WEBPUBSUB_HUB=my-hub
Service Client (Server-Side)
Authentication
from azure.messaging.webpubsubservice import WebPubSubServiceClient
# Connection string
client = WebPubSubServiceClient.from_connection_string(
connection_string=os.environ["AZURE_WEBPUBSUB_CONNECTION_STRING"],
hub="my-hub"
)
# Entra ID
from azure.identity import DefaultAzureCredential
client = WebPubSubServiceClient(
endpoint="https://<name>.webpubsub.azure.com",
hub="my-hub",
credential=DefaultAzureCredential()
)
Generate Client Access Token
# Token for anonymous user
token = client.get_client_access_token()
print(f"URL: {token['url']}")
# Token with user ID
token = client.get_client_access_token(
user_id="user123",
roles=["webpubsub.sendToGroup", "webpubsub.joinLeaveGroup"]
)
# Token with groups
token = client.get_client_access_token(
user_id="user123",
groups=["group1", "group2"]
)
Send to All Clients
# Send text
client.send_to_all(message="Hello everyone!", content_type="text/plain")
# Send JSON
client.send_to_all(
message={"type": "notification", "data": "Hello"},
content_type="application/json"
)
Send to User
client.send_to_user(
user_id="user123",
message="Hello user!",
content_type="text/plain"
)
Send to Group
client.send_to_group(
group="my-group",
message="Hello group!",
content_type="text/plain"
)
Send to Connection
client.send_to_connection(
connection_id="abc123",
message="Hello connection!",
content_type="text/plain"
)
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.
- 8d ago First seen · 254 lines · 34 tokens per session scan A 5bc19767ab1b
azure-messaging-webpubsubservice-py is a skill published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,405 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to azure-messaging-webpubsubservice-py, differing in 11 lines, and is treated as a copy.
Other skills, from other repositories
composio
Build AI agents and apps with Composio - access 200+ external tools with Tool Router or direct execution.
skill-google-workspace-sync
Use for Google Workspace integrations with OAuth, Calendar, Meet, FreeBusy, Drive, Sheets, webhooks, least-privilege scopes, encrypted refresh tokens, idempotent writes, reconciliation jobs, consent revocation, validation, and sync audit trails.
skill-saas-factory
Build, refactor, review, or plan SaaS products with React/Vite, dashboards, admin panels, Supabase, payments, subscriptions, tenant limits, webhooks, security, infrastructure, and production readiness. Use as the top-level SaaS construction skill when work may need routing to payment, RLS, dashboard, limits, security…
skill-evolution-api
Use for WhatsApp automation with Evolution API, including instance lifecycle, QR pairing, inbound and outbound messages, webhooks, consent, tenant isolation, queues, idempotency, rate limits, retries, audit logs, and reliable delivery.
skill-live-processing
Use for live stream and VOD ingestion pipelines, including YouTube, Twitch, uploads, capture jobs, queues, transcription, clip generation, media storage, retries, idempotent workers, consent, validation, observability, and safe server-side provider credentials.
skill-manual-video-processing
Use for manual video or audio uploads in SaaS apps, including upload UX, direct storage, validation, malware checks, quota enforcement, asynchronous processing jobs, transcription, clip extraction, review flows, signed URLs, consent, and secure media access.