Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Cursor Rules for NeqSim
> This file is read automatically by Cursor AI.
> It mirrors the content in `AGENTS.md` — see that file for the full reference.
Please read and follow the instructions in AGENTS.md.
All code MUST compile with Java 8. See AGENTS.md for forbidden features,
build commands, code patterns, skills, and the task-solving workflow.
## Critical Constraints
- Java 8 ONLY — no `var`, `List.of()`, `Map.of()`, `String.repeat()`, text blocks, records
- Use `Arrays.asList()`, `StringUtils.repeat()`, explicit types
- Build: `./mvnw install` (Linux/Mac), `mvnw.cmd install` (Windows)
- Test: `./mvnw test -Dtest=ClassName`
- Static analysis: `./mvnw checkstyle:check spotbugs:check pmd:check`
- After flash: call `fluid.initProperties()` before reading transport properties
- Always set mixing rule: `fluid.setMixingRule("classic")`
## Agent & Skill System
- 25 agents in `.github/agents/*.agent.md`
- 28 skills in `.github/skills/*/SKILL.md`
- Full patterns in `AGENTS.md`, quick overview in `CONTEXT.md`
- Code patterns in `docs/development/CODE_PATTERNS.md`
- Past solved tasks in `docs/development/TASK_LOG.md`
The line at the top of this page pins the label git:20260418.119a3f4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_ygduugworvlojfq5
GET https://markdownregistry.com/api/v1/resolve?ref=equinor/neqsim/.cursorrules
GET https://markdownregistry.com/api/v1/blob/5eb70cde27bfd2c9cb979f24b8b3a35c79e0293f137979e91275a4cf2bd9f6d6
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
equinor/neqsim · .github/skills/neqsim-acid-gas-treating/SKILL.md · Guides NeqSim agents through acid-gas and contaminant removal with SimpleAmineAbsorber, SimpleAmineRegenerator…
equinor/neqsim · .github/skills/neqsim-agent-handoff/SKILL.md · Agent-to-agent communication schema for NeqSim. USE WHEN: composing multi-agent pipelines where one agent's output…
equinor/neqsim · .github/skills/neqsim-agentic-process-optimization/SKILL.md · Agentic closed-loop optimization of large multi-area NeqSim ProcessModel plants with convergence gating and equipment…
