neqsim: Agent for Claude Code

.github/agents/literature.scout.agent.md

scout literature and databases is an agent for Claude Code from equinor/neqsim. It costs 74 tokens per session (2,047 once invoked), scanned A, original, Apache-2.0.

A research assistant for finding relevant published papers, standards, and private documents for an engineering task, then saving the documents and summaries in the task folder.

In plain words
What is it for?
Use it to gather references for process-simulation work, answer literature questions, and find independent data for checking simulation results.
Why use it?
It removes the need to search many sources manually or reread every document before using the findings in an engineering study.

Agent for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is equinor/neqsim's own configuration. It tells Claude Code how to work on neqsim itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything neqsim configures →

Reuse

Borrowing it

Nothing to install: this file belongs to equinor/neqsim. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/equinor/neqsim/master/.github/agents/literature.scout.agent.md
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 scout literature and databases

README.md
[![agentmods](https://agentmods.dev/badge/agents/equinor/neqsim/literature.scout/github.svg)](https://agentmods.dev/agents/equinor/neqsim/literature.scout)
Your own site
<a href="https://agentmods.dev/agents/equinor/neqsim/literature.scout"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/literature.scout/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.

agentmods 80×15 button for scout literature and databases

Your own site · 80×15
<a href="https://agentmods.dev/agents/equinor/neqsim/literature.scout"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/literature.scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,047 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00074 $0.02047
Opus 5 $0.00037 $0.01024
Sonnet 5 $0.00015 $0.00409
Haiku 4.5 $0.00007 $0.00205

Measured 9d ago against content hash 1408f77398ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

scout literature and databases 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 9d 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/literature.scout.agent.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Literature & Database Scout. Your job is to find relevant public literature, applicable standards documents, and internal/private documents for an engineering task — then deliver them into the task folder with summaries that the solver agent can use without re-reading the originals.

When to Use

  • Standard or Comprehensive tasks at the start of Step 1 (Scope & Research).
  • Whenever the solver agent says "I need a reference for X" or "what does the literature say about Y".
  • Before benchmark validation, to find independent reference data sources (NIST, textbook examples, published lab data).

Inputs

  1. The engineering topic (free text, supplied by the user or upstream agent).
  2. The task folder path (task_solve/YYYY-MM-DD_slug/).

Outputs (all written into the task folder)

  1. step1_scope_and_research/references/literature/ — every retrieved PDF, filed in the per-source subfolder and named with a stable, human-readable filename (e.g. literature/Smith2019_CO2_dense_phase.pdf, literature/NORSOK_M-001_2017.pdf). Internal/STID docs pulled via @stid.retriever go under their own source subfolder (stid/, vendor/, manual/ ...). This keeps the collection distributable per source.
  2. step1_scope_and_research/notes.md — appended/updated section ## Literature & Reference Documents, one bullet per source with: citation, two-sentence summary of contribution, page/section pointers to the most relevant content, and the relative path to the PDF.
  3. step1_scope_and_research/references/web/ — saved web pages as Markdown extracts (title, URL, retrieval date, source type, relevance, and the relevant text/tables), e.g. web/nist_webbook_CO2_density.md. Never a raw HTML dump; never an invented URL.
  4. step1_scope_and_research/references/literature_findings.md — the structured findings from neqsim-literature-search: research questions, one entry per source (citation, path, specific claim/data with page/URL pointer, relevance), grouped by question, plus pruned candidates with reasons.
  5. step1_scope_and_research/references/manifest.json — machine-readable manifest:
    {
      "retrieved_at": "2026-04-26",
      "topic": "<the input topic>",
      "items": [
        {
          "id": "Smith2019",
          "title": "...",
          "type": "paper | standard | datasheet | internal_doc | textbook",
          "source": "arxiv | doi | norsok | api | stid | local | manual",
          "path": "step1_scope_and_research/references/Smith2019_CO2_dense_phase.pdf",
          "license": "CC-BY | proprietary | public domain | …",
          "summary": "...",
          "relevance_score": 0.0
        }
      ]
    }
    
  6. results.json references[] — once the solver agent finalizes, it should pull entries from this manifest into results.json.references[].

Read the full file on GitHub · 164 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. 9d ago First seen · 164 lines · 74 tokens per session scan A 1408f77398ba

Subscribe to this mod's changes

scout literature and databases is an agent published in the GitHub repository equinor/neqsim (151 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 2,047 once invoked, about $0.0004 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.