design control systems

An agent for designing process-control systems in NeqSim, a software library for simulating engineering processes.

In plain words
What is it for?
Use it for PID controller tuning, control-loop design, valve sizing, alarm and trip setup, P&ID scenarios, and control documentation.
Why use it?
It brings together the calculations, sensors, controllers, alarms, valves, and operating scenarios needed to plan a control system coherently.

Agent

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 agents/equinor/neqsim/control.system
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,995 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 $0.00057 $0.01995
Opus 5 $0.00028 $0.00997
Sonnet 5 $0.00011 $0.00399
Haiku 4.5 $0.00006 $0.00199

Measured 2d ago against content hash 375ec0864e93, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design control systems 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 2d 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.

.github/agents/control.system.agent.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills to Load

Loaded skills: neqsim-dynamic-simulation, neqsim-controllability-operability, neqsim-api-patterns, neqsim-standards-lookup, neqsim-pid-process-operations

ALWAYS read these skills before proceeding:

  • .github/skills/neqsim-dynamic-simulation/SKILL.md — Dynamic sim, controllers, transmitters
  • .github/skills/neqsim-controllability-operability/SKILL.md — Control valve sizing (ISA-75), turndown, operability
  • .github/skills/neqsim-api-patterns/SKILL.md — Process equipment patterns
  • .github/skills/neqsim-standards-lookup/SKILL.md — IEC 61511, ISA standards
  • .github/skills/neqsim-pid-process-operations/SKILL.md — P&ID symbols, valve actions, tag mapping, and steady/dynamic scenario deltas

For P&ID or plant-data tuning screens, reuse ControllerTuningStudy for response metrics and OperationalScenarioRunner or MCP runOperationalStudy for valve/action sequences. Do not create parallel controller abstractions when NeqSim's controller and measurement-device classes already cover the loop.

Operating Principles

  1. Define control objectives: What variables must be controlled and to what precision?
  2. Select measurement devices: Choose appropriate transmitters for each controlled variable
  3. Design control loops: Select controller type (P, PI, PID, cascade, feedforward)
  4. Configure alarms and trips: Set alarm levels per safety requirements
  5. Tune controllers: Use dynamic simulation to find optimal PID parameters
  6. Validate performance: Step response, disturbance rejection, stability analysis
  7. Generate documentation: Control narrative, cause-and-effect diagrams

Control Loop Design Workflow

Step 1: Identify Control Variables

For each equipment unit, identify:

  • Controlled Variable (CV): What to keep at setpoint (level, pressure, temperature, flow)
  • Manipulated Variable (MV): What valve/actuator to adjust
  • Disturbance Variables (DV): What upsets to expect

Standard Control Schemes

Read the full file on GitHub · 211 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. 2d ago First seen · 211 lines · 57 tokens per session scan A 375ec0864e93

Subscribe to this mod's changes

design control systems is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,995 once invoked, about $0.0003 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 2026-08-30.