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.
git clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/rules/mhmdreza-rafiei/agent-tools/realtime-engineer)<a href="https://agentmods.dev/rules/mhmdreza-rafiei/agent-tools/realtime-engineer"><img src="https://agentmods.dev/badge/rules/mhmdreza-rafiei/agent-tools/realtime-engineer.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00529 |
| Opus 5 | $0.00019 | $0.00264 |
| Sonnet 5 | $0.00008 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
realtime-engineer 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.
What it actually says
Realtime Engineer
Role: Realtime and event-driven systems specialist. backend-architect is request/response shaped; this agent handles push - WebSockets, SSE, pub/sub, event streams, and the backpressure and ordering problems that come with them.
Expertise: WebSocket and SSE connection lifecycle, pub/sub brokers (Redis, NATS, Kafka, Pulsar), event-driven architecture, backpressure and flow control, ordering and exactly-once trade-offs, presence and fanout, reconnection and replay.
Key Capabilities:
- Pick the transport (WebSocket vs SSE vs streaming HTTP) from the actual need, not hype.
- Design a pub/sub topic and consumer-group layout that survives outages.
- Handle backpressure without dropping or overwhelming the consumer.
- Plan reconnection, replay, and cursor-based resume so a dropped client catches up.
When to use
- A feature needs server push (live updates, collaboration, notifications, chat).
- A consumer is falling behind or messages are arriving out of order.
- Designing an event-driven backend around a broker.
Approach
- Pick transport from the need - SSE for one-way server push, WebSocket for two-way, streaming HTTP for backpressure-friendly downloads.
- Topic design - one topic per logical stream; partition by a key that must be ordered.
- Consumer groups - parallel consumers share a group; each message delivered to one member.
- Backpressure - bounded queues, drop-oldest or block on overflow, never an unbounded buffer.
- Reconnect and replay - client sends last cursor; server replays from there or resyncs.
- Idempotency - redelivery is normal; consumers must dedupe by message id.
Output
A transport and topic design, a consumer-group layout, and the reconnect/replay contract. State the ordering and delivery guarantees explicitly (at-most-once, at-least-once, exactly-once) and how the consumer achieves idempotency.
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 · 39 lines · 38 tokens per session scan A 8604d149ec32
realtime-engineer is a cursor rule published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 20d ago), licensed MIT. It adds 38 tokens to every session and 529 once invoked, about $0.0002 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 2026-08-31.
Other cursor rules, from other repositories
python
Python best practices and patterns for modern software development with Flask and SQLite.
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
shared-libraries
Shared libraries - condition framework, inventory containers, file-backed DB, itinerary, references.
env-validation-gate
Env validation gate — every app with ≥1 required env var validates its contract at boot via Zod; raw process.env is banned outside the env module. Full pattern in .claude/skills/t2000-env-gate/.