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/GoranErhartic/cursor-development-rulesWrote 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/goranerhartic/cursor-development-rules/messaging)<a href="https://agentmods.dev/rules/goranerhartic/cursor-development-rules/messaging"><img src="https://agentmods.dev/badge/rules/goranerhartic/cursor-development-rules/messaging/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/rules/goranerhartic/cursor-development-rules/messaging"><img src="https://agentmods.dev/badge/rules/goranerhartic/cursor-development-rules/messaging.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 | $0.00015 | $0.00513 |
| Opus 5.5 | $0.00006 | $0.00205 |
| Sonnet 5.5 | $0.00003 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
messaging 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 1mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rebus Messaging
Rebus is a free, open-source .NET messaging library (alternative to MassTransit for RabbitMQ/SQL/Azure).
Setup
- AddRebus with Transport (UseRabbitMq, UseSqlServer, or Azure Service Bus); Logging (Serilog); Options: NumberOfWorkers, MaxParallelism, RetryStrategy (maxDeliveryAttempts, errorQueueName).
- Sagas: StoreInSqlServer (or InMemory for dev); table names for Sagas and SagaIndex.
- AutoRegisterHandlersFromAssemblyOf to register IHandleMessages implementations.
Events vs Commands
- Event: Something that happened (past tense); Publish; multiple handlers allowed.
- Command: Request to do something; Send to queue; typically one handler.
- Use records for message types (immutable, serializable).
Handlers
- Implement IHandleMessages; single Handle(TMessage message) async method; inject dependencies via constructor; keep handler idempotent when possible.
- Publish events after commit (e.g. after UnitOfWork.SaveChanges) to avoid publishing on rollback.
Sagas
- Implement Saga; Correlate messages to saga instance (CorrelationConfig); Handle and then MarkAsComplete or Update state; use IHandleMessages for messages that start or continue saga.
- Store saga data in configured store; keep saga data small.
Outbox (Optional)
- Use outbox pattern (e.g. Rebus.Outbox) to publish only after DB commit; prevents lost messages on crash before commit.
- Store outgoing messages in same transaction as domain changes; worker sends from outbox after commit.
Retry and Error Queue
- RetryStrategy: maxDeliveryAttempts; failed messages go to error queue; monitor and replay or dead-letter.
- Do not swallow exceptions in handler; let Rebus retry or move to error queue.
Conventions
- Idempotent handlers where possible; publish after commit; use correlation ID in message or headers; log with message ID for tracing.
- Use outbox for critical publish-after-commit; use sagas for multi-step workflows with state.
Anti-Patterns
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.
- 1mo ago First seen · 51 lines · 15 tokens per session scan A 7aa8d314076e
messaging is a cursor rule published in the GitHub repository GoranErhartic/cursor-development-rules (19 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 513 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other cursor rules, from other repositories
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
python
Python best practices and patterns for modern software development with Flask and SQLite.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
shared-libraries
Shared libraries - condition framework, inventory containers, file-backed DB, itinerary, references.
selectools-providers
Rules for working with LLM provider adapters in selectools.