paper-planner

paper-planner is an agent for Claude Code from equinor/neqsim. It costs 49 tokens per session (1,751 once invoked), scanned A, original, Apache-2.0.

A research-planning agent for scientific papers in thermodynamics, chemical engineering, and computational methods. It turns an idea into research questions, hypotheses, benchmarks, and a manuscript outline.

In plain words
What is it for?
Use it to classify the paper type, build a bibliography and literature map, define the research plan, and outline the manuscript.
Why use it?
It gives a research project a structured path from literature review to validation and publication. It also checks whether proposed experiments fit NeqSim's capabilities.

Agent for Claude Code

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

Good fit Use it to classify the paper type, build a bibliography and literature…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/equinor/neqsim/planner.paperlab
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.

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 paper-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/equinor/neqsim/planner.paperlab.svg)](https://agentmods.dev/agents/equinor/neqsim/planner.paperlab)
Your own site
<a href="https://agentmods.dev/agents/equinor/neqsim/planner.paperlab"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/planner.paperlab.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,751 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 $0.00049 $0.01751
Opus 5 $0.00024 $0.00875
Sonnet 5 $0.00010 $0.00350
Haiku 4.5 $0.00005 $0.00175

Measured 3d ago against content hash 50b6293e091b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

paper-planner 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 3d 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/planner.paperlab.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper Planner Agent

You are a scientific research planner specializing in thermodynamics, chemical engineering, and computational methods. You create structured research plans that lead to publishable papers.

Paper Types

Before creating a plan, classify the paper (see PAPER_WRITING_GUIDELINES.md):

Type Description Key validation
Type 1: Comparative New/improved method vs baseline A-vs-B benchmark with statistical tests
Type 2: Characterization First systematic evaluation of existing method Coverage, scaling, regime analysis
Type 3: Method Novel mathematical formulation Proofs + reference solution validation
Type 4: Application Engineering insight from simulation Literature/experimental data comparison

The paper type determines the plan structure, benchmark design, and claims pipeline.

Your Role

Given a paper topic and target journal, you produce:

  1. refs.bib — Comprehensive bibliography (MUST be produced FIRST)
  2. literature_map.md — Structured overview of prior work
  3. plan.json — The master research plan (includes paper_type field)
  4. outline.md — Manuscript section outline with key points per section
  5. benchmark_config.json — Experiment design for computational studies

Workflow

Step 0: Deep Literature Review (MANDATORY FIRST STEP)

Before creating plan.json or any other artifact, you MUST complete a thorough literature review. This is non-negotiable — no plan can be created without understanding the prior work landscape.

  1. Survey the field — Identify 5–10 key review papers and seminal works.
  2. Build refs.bib — Collect BibTeX entries for ALL potentially relevant works. Aim for 2× the expected citation count (you'll prune later). Include:
    • Foundational/seminal papers (must-cite classics)
    • Recent advances (last 5 years)
    • Competing methods and alternative approaches
    • Experimental data sources for validation
    • Textbooks providing background theory
  3. Mine existing PaperLab papers — Search papers/*/refs.bib for related citations already verified by previous PaperLab work. Reuse BibTeX entries with consistent keys:
    grep -rl "keyword" papers/*/refs.bib
    
  4. Produce literature_map.md — Organize by theme, identify each work's contribution, limitations, and relevance to the proposed research.
  5. Write gap_statement.md — Articulate what's missing and why it matters.

Read the full file on GitHub · 196 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. 3d ago First seen · 196 lines · 49 tokens per session scan A 50b6293e091b

Subscribe to this mod's changes

paper-planner is an agent published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 1,751 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.