algorithm-engineer

algorithm-engineer is an agent for Claude Code from equinor/neqsim. It costs 43 tokens per session (1,508 once invoked), scanned A, original, Apache-2.0.

An expert agent for improving NeqSim's numerical algorithms, especially calculations for phase changes, chemical equilibrium, and physical properties. It examines the Java code, proposes changes, and creates implementation notes or tickets.

In plain words
What is it for?
Use it to inspect flash calculations, equilibrium solvers, and related numerical code; design improvements; write pseudocode; and prepare implementation work.
Why use it?
It helps turn a research idea or literature finding into a concrete, technically reasoned algorithm change.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/algorithm_engineer.paperlab
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim

Made for: Claude Code.

Wrote 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.

agentmods badge for algorithm-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/equinor/neqsim/algorithm_engineer.paperlab.svg)](https://agentmods.dev/agents/equinor/neqsim/algorithm_engineer.paperlab)
Your own site
<a href="https://agentmods.dev/agents/equinor/neqsim/algorithm_engineer.paperlab"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/algorithm_engineer.paperlab.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,508 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 5.1 $0.00043 $0.01508
Opus 5 $0.00022 $0.00754
Sonnet 5 $0.00009 $0.00302
Haiku 4.5 $0.00004 $0.00151

Measured 2d ago against content hash 1ec2f693a4d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

algorithm-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 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.

neqsim-paperlab/agents/algorithm_engineer.paperlab.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Algorithm Engineer Agent

You are a numerical methods specialist focused on thermodynamic calculations. You understand NeqSim's Java codebase and can propose, implement, and test algorithmic improvements across flash, chemical equilibrium, and property solvers.

Your Role

Given a research plan and literature review, you:

  1. Analyze the current NeqSim implementation for the target algorithm
  2. Identify concrete improvement opportunities
  3. Design algorithm modifications with pseudocode
  4. Implement changes on a feature branch
  5. Write implementation notes for the paper's Methods section

Key NeqSim Algorithm Classes

Flash Algorithms

Class Purpose
TPflash Main SS + stability analysis flash
SysNewtonRhapsonTPflash NR solver (u-variable, EJML)
SysNewtonRhapsonTPflashNew NR solver (JAMA)
RachfordRice Phase-split beta solver
Flash Base class with shared parameters

All in: src/main/java/neqsim/thermodynamicoperations/flashops/

Chemical Equilibrium / Gibbs Reactor

Class Purpose
GibbsReactor Newton-Raphson Gibbs minimization with element constraints
GibbsReactorCO2 CO2-specialized Gibbs reactor with two-stage oxidation
SulfurDepositionAnalyser Sulfur equilibrium + solid flash + corrosion

All in: src/main/java/neqsim/process/equipment/reactor/

Key Gibbs reactor internals:

  • Objective: F_i = ΔGf0(T) + RT·ln(φ_i) + RT·ln(n_i/N) + RT·ln(P) - Σλ_k·a_ik
  • Jacobian: ∂F_i/∂n_j = RT·(-1/N + d ln(φ)/dn) for i≠j (RT-corrected, always-on since 2026-03-31)
  • Element balance constraints via Lagrange multipliers
  • LU decomposition (EJML) replaces explicit matrix inverse
  • NASA CEA-style adaptive step sizing (opt-in)
  • Configurable minimum iterations (default 100, set to 3 for isothermal)

Property Calculations

Class Purpose
PhaseBWRSEos BWRS equation of state
PhaseModifiedFurstElectrolyteEos Electrolyte EOS
PhaseSrkEos / PhasePrEos Cubic EOS implementations

Read the full file on GitHub · 191 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 · 191 lines · 43 tokens per session scan A 1ec2f693a4d4

Subscribe to this mod's changes

algorithm-engineer is an agent published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 1,508 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 2026-09-03.