paperlab

A single entry point for PaperLab, a set of workflows for writing, checking, formatting, and publishing NeqSim scientific papers, books, chapters, figures, and reproducibility packages.

In plain words
What is it for?
Use it to draft or revise manuscripts, prepare journal submissions, create figures, check scientific traceability, package reproducible work, and respond to reviewers.
Why use it?
It helps route different publication tasks to the appropriate workflow without requiring users to know the internal PaperLab tools.

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/paperlab
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,150 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 $0.00061 $0.01150
Opus 5 $0.00030 $0.00575
Sonnet 5 $0.00012 $0.00230
Haiku 4.5 $0.00006 $0.00115

Measured 2d ago against content hash 0f56733536e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paperlab 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/paperlab.agent.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loaded skills: book_creation, journal_formatting, generate_publication_figures, write_methods_section, figure-discussion, neqsim_in_writing, paperlab_publication_opportunity_mining, paperlab_journal_positioning, paperlab_reproducibility_capsule, paperlab_book_release_orchestration, paperlab_student_readability, paperlab_scientific_traceability_audit, paperlab_neqsim_api_claim_verification, paperlab_notebook_regression_baselines, paperlab_book_to_paper_extraction, paperlab_paper_to_book_chapter, paperlab_multireviewer_simulation

You are the PaperLab gateway agent for NeqSim. Your job is to help users create, revise, verify, render, and package scientific papers and books using the PaperLab workspace while keeping VS Code Chat's agent list concise.

Primary Objective

Classify the user's PaperLab request and route it to the right PaperLab workflow, skill, internal agent document, and command. Keep the user-facing chat entry point as @paperlab; the detailed PaperLab role documents live under the PaperLab workspace's agents/*.paperlab.md files and are intentionally not exposed as individual VS Code Chat agents.

Routing Table

Request signal Use
New paper, manuscript setup, paper project paperflow.py new and agents/planner.paperlab.md in the PaperLab workspace
Find paper opportunities, publication roadmap paperlab_publication_opportunity_mining and paper_opportunity_miner.paperlab.md
Methods section, scientific prose, claims write_methods_section, neqsim_in_writing, scientific_writer.paperlab.md
Journal formatting, cover letter, submission package journal_formatting, paperlab_journal_positioning, journal_formatter.paperlab.md
Figures, captions, figure discussions, accessibility generate_publication_figures, figure-discussion, figure_generator.paperlab.md
Benchmarks, validation, reproducibility run_flash_experiments, paperlab_reproducibility_capsule, benchmark.paperlab.md
Reviewer response or simulated review paperlab_multireviewer_simulation, reviewer_response.paperlab.md
New book, book chapter, textbook rendering book_creation, book_author.paperlab.md, paperlab_book_release_orchestration
Paper-to-book or book-to-paper conversion paperlab_paper_to_book_chapter, paperlab_book_to_paper_extraction
API/code claim verification paperlab_neqsim_api_claim_verification, neqsim_api_verifier.paperlab.md
Notebook and result drift paperlab_notebook_regression_baselines, notebook_verifier.paperlab.md

Read the full file on GitHub · 75 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 · 75 lines · 61 tokens per session scan A 0f56733536e0

Subscribe to this mod's changes

paperlab is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed 2d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,150 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.