research-reviewer

research-reviewer is an agent for Claude Code from llv22/AutoResearchWithEyes. It costs 48 tokens per session (952 once invoked), scanned A, original, MIT.

A research assistant that gives critical feedback on research ideas, papers, and experiment results by asking an external language model to review them.

In plain words
What is it for?
Use it to prepare research context, run several review rounds, and assess whether the work is strong enough for a major machine-learning conference.
Why use it?
It helps find unsupported claims, missing experiments, weak explanations, and problems that may be missed during self-review.

Agent for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; mentions Codex.

Part of the auto-research-with-eyes plugin — 10 skills, 5 commands, 2 agents, 1 MCP server shipped together

Good fit Use it to prepare research context, run several review rounds, and assess…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/llv22/autoresearchwitheyes/research-reviewer
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/llv22/AutoResearchWithEyes

Made for: Claude Code.

Or install auto-research-with-eyes, the plugin that ships this one along with the rest of its 10 skills, 5 commands, 2 agents, 1 MCP server.

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 research-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/llv22/autoresearchwitheyes/research-reviewer.svg)](https://agentmods.dev/agents/llv22/autoresearchwitheyes/research-reviewer)
Your own site
<a href="https://agentmods.dev/agents/llv22/autoresearchwitheyes/research-reviewer"><img src="https://agentmods.dev/badge/agents/llv22/autoresearchwitheyes/research-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 952 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 $0.00048 $0.00952
Opus 5 $0.00024 $0.00476
Sonnet 5 $0.00010 $0.00190
Haiku 4.5 $0.00005 $0.00095

Measured 6d ago against content hash e120b9a3dccc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

research-reviewer 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.

agents/research-reviewer.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Review via Codex MCP (xhigh reasoning)

Get a multi-round critical review of research work from an external LLM with maximum reasoning depth.

Constants

REVIEWER_MODEL is defined in the project's CLAUDE.md. Read it from there before proceeding. Codex MCP is auto-configured via .mcp.json.

Context: $ARGUMENTS

Workflow

Step 1: Gather Research Context

Before calling the external reviewer, compile a comprehensive briefing:

  1. Read project narrative documents (e.g., STORY.md, README.md, paper drafts)
  2. Read any memory/notes files for key findings and experiment history
  3. Identify: core claims, methodology, key results, known weaknesses

Step 2: Initial Review (Round 1)

Send a detailed prompt with xhigh reasoning:

mcp__codex__codex:
  model: REVIEWER_MODEL
  config: {"model_reasoning_effort": "xhigh"}
  prompt: |
    [Full research context + specific questions]
    Please act as a senior ML reviewer (NeurIPS/ICML level). Identify:
    1. Logical gaps or unjustified claims
    2. Missing experiments that would strengthen the story
    3. Narrative weaknesses
    4. Whether the contribution is sufficient for a top venue
    Please be brutally honest.

Step 3: Iterative Dialogue (Rounds 2-N)

Use mcp__codex__codex-reply with the returned threadId to continue the conversation:

For each round:

  1. Respond to criticisms with evidence/counterarguments
  2. Ask targeted follow-ups on the most actionable points
  3. Request specific deliverables: experiment designs, paper outlines, claims matrices

Key follow-up patterns:

  • "If we reframe X as Y, does that change your assessment?"
  • "What's the minimum experiment to satisfy concern Z?"
  • "Please design the minimal additional experiment package (highest acceptance lift per GPU week)"
  • "Please write a mock NeurIPS/ICML review with scores"
  • "Give me a results-to-claims matrix for possible experimental outcomes"

Step 4: Convergence

Stop iterating when:

  • Both sides agree on the core claims and their evidence requirements
  • A concrete experiment plan is established
  • The narrative structure is settled

Read the full file on GitHub · 98 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 · 98 lines · 48 tokens per session scan A e120b9a3dccc

Subscribe to this mod's changes

research-reviewer is an agent published in the GitHub repository llv22/AutoResearchWithEyes (5 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 952 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 2026-08-31.

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