websocket-patterns

A set of rules for WebSocket connections, which keep a live two-way link between an application and a browser or other client.

In plain words
What is it for?
Use it when adding or changing session updates, user updates, connection limits, or background workflow notifications.
Why use it?
It defines where authentication tokens may be sent, how many connections are allowed, and how updates must be broadcast.

Cursor rule for Claude Code

Install

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.

agentmods
npx agentmods add rules/eliornl/rolemule/websocket-patterns
Clone the repo
git clone --depth 1 https://github.com/eliornl/rolemule

Made for: Claude Code.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02816
Opus 5 $0.00000 $0.01408
Sonnet 5 $0.00000 $0.00563
Haiku 4.5 $0.00000 $0.00282

Measured yesterday against content hash 47b131eab24e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

websocket-patterns 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 yesterday.

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.

.claude/rules/websocket-patterns.mdc · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WebSocket Patterns

Endpoints

WS /api/v1/ws/workflow/{session_id}?token=JWT   # session-scoped updates
WS /api/v1/ws/user?token=JWT                    # all updates for a user

Token goes in the query string. This is the only place in the codebase where a JWT is allowed in a URL parameter — the WebSocket protocol has no concept of custom request headers, so there is no alternative. extract_token_from_request in utils/auth.py enforces this: query-param tokens are accepted only for paths starting with /api/ws/. All regular HTTP endpoints require Authorization: Bearer <token>.

Connection Limits

  • Max 5 connections per user
  • Max 3 connections per session

Complete Broadcast Function Reference

All broadcast functions live in api/websocket.py and follow the same signature:

  • Always send to both session-scoped subscribers and general user subscribers.
  • Always safe to await from any background task — they swallow send errors gracefully.

Main Workflow Broadcasts (called by workflows/job_application_workflow.py)

from api.websocket import (
    broadcast_agent_update,
    broadcast_phase_change,
    broadcast_workflow_complete,
    broadcast_workflow_error,
    broadcast_gate_decision,
)

await broadcast_agent_update(
    user_id=user_id,
    session_id=session_id,
    agent_name="job_analyzer",
    status="running",           # running | completed | failed
    message="Analyzing job posting...",
)

await broadcast_phase_change(
    user_id=user_id,
    session_id=session_id,
    phase="profile_matching",
    progress_percentage=60,
)

await broadcast_workflow_complete(user_id=user_id, session_id=session_id, result_summary=result)
await broadcast_workflow_error(user_id=user_id, session_id=session_id, error_message=error_msg, failed_agent="job_analyzer")
await broadcast_gate_decision(user_id=user_id, session_id=session_id, match_score=0.82, recommendation="Strong match")

Workflow Control Broadcasts (called by api/workflow.py background tasks)

from api.websocket import (
    broadcast_workflow_resumed,
    broadcast_document_generation_started,
)

# Sent at the start of _continue_workflow_background (after gate confirmation)
await broadcast_workflow_resumed(user_id=user_id, session_id=session_id)

# Sent at the start of _generate_documents_background
await broadcast_document_generation_started(user_id=user_id, session_id=session_id)

Read the full file on GitHub · 284 lines

Changes

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.

  1. yesterday First seen · 284 lines · 0 tokens per session scan A 47b131eab24e

Subscribe to this mod's changes

websocket-patterns is a cursor rule published in the GitHub repository eliornl/rolemule (37 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,816 tokens. 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.