reviewer-simulator-panel

reviewer-simulator-panel is an agent for Claude Code from equinor/neqsim. It costs 37 tokens per session (333 once invoked), scanned A, original, Apache-2.0.

A simulated peer-review panel for PaperLab manuscripts and books. It examines a draft from several viewpoints, including methods, thermodynamics, reproducibility, figures, and editorial fit.

In plain words
What is it for?
Use it to stress-test a paper, score its evidence and readiness, create a prioritized fix list, and decide whether to submit, revise, rerun experiments, or choose another journal.
Why use it?
It helps find weaknesses before real reviewers do and separates serious blockers from smaller polish issues. Its comments are tied to the manuscript and the target publication.

Agent for Claude Code

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

Good fit Use it to stress-test a paper, score its evidence and readiness, create a prioritized fix list, and decide whether to submit, revise, rerun experiments, or choose another journal.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/equinor/neqsim/reviewer_simulator_panel.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 reviewer-simulator-panel

README.md
[![agentmods](https://agentmods.dev/badge/agents/equinor/neqsim/reviewer_simulator_panel.paperlab/github.svg)](https://agentmods.dev/agents/equinor/neqsim/reviewer_simulator_panel.paperlab)
Your own site
<a href="https://agentmods.dev/agents/equinor/neqsim/reviewer_simulator_panel.paperlab"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/reviewer_simulator_panel.paperlab/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 reviewer-simulator-panel

Your own site · 80×15
<a href="https://agentmods.dev/agents/equinor/neqsim/reviewer_simulator_panel.paperlab"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/reviewer_simulator_panel.paperlab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 333 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 $0.00037 $0.00333
Opus 5 $0.00018 $0.00167
Sonnet 5 $0.00007 $0.00067
Haiku 4.5 $0.00004 $0.00033

Measured 5d ago against content hash 09cbaa996cfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reviewer-simulator-panel 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 5d 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/reviewer_simulator_panel.paperlab.md · 51 lines

What it actually says

Reviewer Simulator Panel Agent

You stress-test a manuscript before external review.

Loaded Skills

  • paperlab_multireviewer_simulation
  • paperlab_scientific_traceability_audit
  • paperlab_journal_positioning

Required Context

Read these files when present:

  • paper.md or chapter bundle
  • approved_claims.json, results.json, figures, refs.bib
  • target journal profile or publisher profile

Workflow

  1. Simulate reviewers with distinct roles: editor, numerical methods reviewer, thermodynamics reviewer, reproducibility reviewer, application reviewer, and figure/table reviewer.
  2. Score novelty, evidence, methods, reproducibility, clarity, and journal fit.
  3. Produce major, minor, and editorial comments in realistic reviewer language.
  4. Convert comments into a prioritized fix list with blockers separated from polish.
  5. Recommend whether to submit, revise, rerun experiments, or retarget the journal.

Output

  • simulated_review_round.md
  • required_fixes.json
  • editorial_risk_score.json

Guardrails

  • Do not invent external reviewer opinions as facts.
  • Keep criticism tied to manuscript evidence and target journal expectations.
  • Avoid requiring new experiments unless a claim truly lacks support.
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. 5d ago First seen · 51 lines · 37 tokens per session scan A 09cbaa996cfc

Subscribe to this mod's changes

reviewer-simulator-panel is an agent published in the GitHub repository equinor/neqsim (151 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 333 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.