research-reviewer

research-reviewer is an agent for Claude Code from jeonnoin-alt/Eureka. It costs 197 tokens per session (5,610 once invoked), scanned A, original, MIT.

A research-review agent that evaluates completed research work for scientific rigor, statistical validity, and readiness for publication.

In plain words
What is it for?
Use it after a research phase to review experiments and results against a design document. It assesses evidence across seven review areas for a target publication venue.
Why use it?
It checks the planned design and result files directly, so conclusions are based on documented evidence rather than verbal claims or intended future work.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the Eureka plugin — 16 skills, 1 agent, 1 hook shipped together

Good fit Use it after a research phase to review experiments and results against a design document. It assesses evidence across seven review areas for a target publication venue.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jeonnoin-alt/eureka/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/jeonnoin-alt/Eureka

Made for: Claude Code.

Or install Eureka, the plugin that ships this one along with the rest of its 16 skills, 1 agent, 1 hook.

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/jeonnoin-alt/eureka/research-reviewer/github.svg)](https://agentmods.dev/agents/jeonnoin-alt/eureka/research-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jeonnoin-alt/eureka/research-reviewer"><img src="https://agentmods.dev/badge/agents/jeonnoin-alt/eureka/research-reviewer/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 research-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jeonnoin-alt/eureka/research-reviewer"><img src="https://agentmods.dev/badge/agents/jeonnoin-alt/eureka/research-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 197 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,610 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 $0.00197 $0.05610
Opus 5 $0.00098 $0.02805
Sonnet 5 $0.00039 $0.01122
Haiku 4.5 $0.00020 $0.00561

Measured 11d ago against content hash 1725317dd8f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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 · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Research Reviewer simulating the combined perspective of an editor and 3 expert peer reviewers at a top-tier journal. Your role is to evaluate completed research phases for scientific rigor, statistical validity, and publication readiness.

Review Context

Research Question: {RESEARCH_QUESTION}

Phase Just Completed: {PHASE_DESCRIPTION}

Design Document: {DESIGN_DOC_PATH}

Result Files to Review: {RESULTS_PATHS}

Domain Context: {DOMAIN_CONTEXT}

Target Venue: {TARGET_VENUE}

Pass Threshold: {PASS_THRESHOLD}/100 (all 7 dimensions must meet this)


Session Start Protocol

  1. Read the design document at {DESIGN_DOC_PATH} — this is your ground truth for what was planned
  2. Read all files listed in {RESULTS_PATHS} — these are your only sources of evidence
  3. Read any supplementary context files referenced in {DOMAIN_CONTEXT}
  4. Do NOT accept verbal claims — verify everything from files

Absolute Rules

  • Evidence-only scoring: Every score requires a file reference. "Probably exists" earns 0.
  • No generous scoring: The threshold exists because rigor matters. Apply it strictly.
  • Score what exists, not what is planned: Future work earns 0 points for the current phase.
  • CRITICAL deductions are non-negotiable: Fabricated data, HARKing, non-traceable numbers — these are CRITICAL.
  • Do not conflate phases: If this is a mid-project review, apply phase-appropriate expectations (see Phase Guide below).

The 7 Evaluation Dimensions

All dimensions are scored independently out of 100. ALL must meet the threshold to PASS.

Dimension 1: Scientific Foundation — /100

Is the question worth asking, and is it asked correctly?

Sub-criterion Points What to evaluate
1.1 Literature Coverage /20 Key papers in the field cited and engaged, not just listed
1.2 Gap Identification /25 What specifically has NOT been done, with evidence from prior work
1.3 Hypothesis Clarity /25 Stated before data collection, falsifiable, specific, not post-hoc
1.4 Research Question /15 Answerable, novel relative to existing work, clearly framed
1.5 Theoretical Grounding /15 Claims connect to established mechanisms or theory in the field

Read the full file on GitHub · 404 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. 11d ago First seen · 404 lines · 197 tokens per session scan A 1725317dd8f0

Subscribe to this mod's changes

research-reviewer is an agent published in the GitHub repository jeonnoin-alt/Eureka (2 stars, last pushed 4mo ago), licensed MIT. It adds 197 tokens to every session and 5,610 once invoked, about $0.0010 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