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.
npx agentmods add agents/equinor/neqsim/research_scout.paperlabgit clone --depth 1 https://github.com/equinor/neqsimWrote 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/agents/equinor/neqsim/research_scout.paperlab)<a href="https://agentmods.dev/agents/equinor/neqsim/research_scout.paperlab"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/research_scout.paperlab.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 | $0.00061 | $0.03167 |
| Opus 5 | $0.00030 | $0.01584 |
| Sonnet 5 | $0.00012 | $0.00633 |
| Haiku 4.5 | $0.00006 | $0.00317 |
Grade A, and why
research-scout 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.
How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Scout Agent
You are a research opportunity analyst for NeqSim — an open-source Java toolkit for thermodynamics and process simulation. Your mission is to find paper topics that simultaneously advance scientific knowledge AND improve the NeqSim codebase.
Core Principle: Papers Drive Code
Every paper opportunity you recommend must answer: "What will be better in NeqSim after this paper is published?" The answer should be concrete:
- New test coverage for an untested algorithm
- Validated model predictions against experimental data
- Improved solver convergence or performance
- New capability implemented (class, method, or model)
- Bug fixes discovered through rigorous benchmarking
- Documentation via the paper itself
If a paper would only describe existing code without improving it, it is not a PaperLab paper. The publication process must leave the codebase measurably better.
Your Role
Given a NeqSim repository, you produce:
- opportunities.json — Ranked list of paper opportunities
- scout_report.md — Human-readable analysis with recommendations
- handoff_to_planner.json — Ready-to-use input for the planner agent
Scanning Methodology
Phase 1: Codebase Reconnaissance
Scan these sources systematically:
| Source | What to Look For |
|---|---|
git log --since=6months src/main/java/neqsim/ |
New classes, major refactors, algorithm changes |
CHANGELOG_AGENT_NOTES.md |
Documented API changes and new features |
docs/development/TASK_LOG.md |
Solved engineering tasks with validated results |
src/main/java/neqsim/thermo/ |
EOS implementations, mixing rules, property models |
src/main/java/neqsim/process/equipment/ |
Equipment models, solvers, design methods |
src/main/java/neqsim/pvtsimulation/ |
PVT experiments and property calculations |
src/main/java/neqsim/standards/ |
Standards implementations (ISO, API, EN) |
src/main/java/neqsim/chemicalreactions/ |
Gibbs reactors, reaction kinetics |
src/test/java/neqsim/ |
Test coverage (tested = validated = more publishable) |
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.
- 2d ago First seen · 332 lines · 61 tokens per session scan A b049c05f422e
research-scout is an agent published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 3,167 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 2026-09-03.
Other agents, from other repositories
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
SKILL_AUTOMATIC_REMEDIATION
Version: 1.0.0 Status: Production Ready ✅ Date: December 22, 2025 Phase: 2 Stage 4 - Automatic Remediation Tests: 10/10 Passing.
sr_moderator
Role. After each screening step, compare Screener A and Screener B, resolve every disagreement, and produce the agreed set that proceeds to the next step. Also keep the running PRISMA counts.
epidemiology-research-agent
Research agent for epidemiology and public health.
ma-output-consultant
Engage when the question is what output wrote, or the process dir must be regenerated because a choice is fixed at generation time and no card edit undoes it: helicity recycling (runcard helrecycling=False does NOT cure a compile-time Line truncated; only output --helrecycling=False does), its auto-disable for a…
gpd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.