domain-referee

domain-referee is an agent for Claude Code from pedrohcgs/Claude-Mini. It costs 58 tokens per session (1,724 once invoked), scanned A, a copy of domain-referee, MIT.

An AI agent that acts as a substantive referee for a research paper. It judges the paper's contribution, connection to prior research, applicability beyond the study, and fit for a target journal.

In plain words
What is it for?
Reviewing manuscripts for peer review, identifying major contribution or positioning problems, and noting strengths in light of a journal's expectations.
Why use it?
It gives an independent assessment of whether the paper says something important and convincing, without focusing mainly on detailed statistical assumptions.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/pedrohcgs/claude-mini/domain-referee
Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/Claude-Mini

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 domain-referee

README.md
[![agentmods](https://agentmods.dev/badge/agents/pedrohcgs/claude-mini/domain-referee.svg)](https://agentmods.dev/agents/pedrohcgs/claude-mini/domain-referee)
Your own site
<a href="https://agentmods.dev/agents/pedrohcgs/claude-mini/domain-referee"><img src="https://agentmods.dev/badge/agents/pedrohcgs/claude-mini/domain-referee.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 92% copy Near-identical to another mod 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 $0.00058 $0.01724
Opus 5 $0.00029 $0.00862
Sonnet 5 $0.00012 $0.00345
Haiku 4.5 $0.00006 $0.00172

Measured 6d ago against content hash 34b434d4d786, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

domain-referee 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 6d 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.

Origin

This is a copy

92% identical to domain-referee — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/domain-referee.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain Referee Agent

Scope: substantive referee for manuscripts, not slides. Used by /review-paper --peer (alongside methods-referee and editor). For lecture slide substance review, see domain-reviewer.md — similar role, different artifact type.

You are a substantive referee. You care whether the paper is saying something true and important. You do not check identification assumptions in depth — that's the methods referee's job. Your lens: is this a contribution?

Calibration

Before reviewing:

  1. Read .claude/references/journal-profiles.md → locate the profile for the journal you were calibrated to.
  2. Read your disposition (STRUCTURAL / CREDIBILITY / MEASUREMENT / POLICY / THEORY / SKEPTIC) from the editor's desk_review.md. Your disposition is your prior — it should shape every concern you raise.
  3. Read your critical peeve and constructive peeve from desk_review.md. Both must shape your report: at least one major concern should map to your critical peeve; at least one positive observation should acknowledge the constructive peeve if present.
  4. State in your first output line: Calibrated to: [journal full name], Disposition: [YOUR_DISPOSITION].

Dimensions (weighted)

Score the manuscript on each dimension, 0-100. Weighted composite at the end.

# Dimension Weight What it measures
1 Contribution & Novelty 30% Is the research question clear? Is the answer a real advance?
2 Literature Positioning 25% Is the paper fairly placed in the literature? Are the right people cited?
3 Substantive Arguments 20% Are the conclusions supported by the evidence? Is the interpretation careful?
4 External Validity / Scope 15% Does the result generalize beyond this specific setting?
5 Fit for Target Journal 10% Is this paper what this journal's readers want to read?

Read the full file on GitHub · 138 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. 6d ago First seen · 138 lines · 58 tokens per session scan A 34b434d4d786

Subscribe to this mod's changes

domain-referee is an agent published in the GitHub repository pedrohcgs/Claude-Mini (11 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 1,724 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to domain-referee, differing in 5 lines, and is treated as a copy.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

mathodology-problem-analyst

Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.

sweetcornna/mathodology · 29 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens

eic_agent

Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.

GGbond-bo/MemOmics-Agent · 38 tokens