peer-reviewer

peer-reviewer is an agent for Claude Code from HirogaKatageri/hirokata. It costs 94 tokens per session (1,149 once invoked), scanned A, original, MIT.

An agent that performs an adversarial review of a research briefing and its supporting material before it is trusted or shared.

In plain words
What is it for?
It is for checking facts against live sources, reviewing research quality across several dimensions, and assigning a reliability grade.
Why use it?
It helps detect unsupported claims, fabricated or mismatched citations, bias, missing viewpoints, and unfair treatment of disagreement.

Agent for Claude Code

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

Part of the research plugin — 4 skills, 8 agents shipped together

Good fit It is for checking facts against live sources, reviewing research quality across several dimensions, and assigning a reliability grade.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hirogakatageri/hirokata/peer-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/HirogaKatageri/hirokata

Made for: Claude Code.

Or install research, the plugin that ships this one along with the rest of its 4 skills, 8 agents.

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 peer-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hirogakatageri/hirokata/peer-reviewer/github.svg)](https://agentmods.dev/agents/hirogakatageri/hirokata/peer-reviewer)
Your own site
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/peer-reviewer"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/peer-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 peer-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/peer-reviewer"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/peer-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,149 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 $0.00094 $0.01149
Opus 5 $0.00047 $0.00575
Sonnet 5 $0.00019 $0.00230
Haiku 4.5 $0.00009 $0.00115

Measured 9d ago against content hash 83e78ffaa727, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

peer-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 9d 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.

plugins/research/agents/peer-reviewer.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Peer Reviewer — STORM Phase 4 Agent

You are the Peer Reviewer: the rigorous, slightly unfriendly reviewer who takes apart a piece of research before the world does. STORM's documented weakness is that it does not self-critique — source bias and fact misassociation slip through. You are the fix. Your loyalty is to the reader and the truth, not to the author (even though the author is the same system). Be direct. Be specific. Praise sparingly and only when earned.

Your Job

You will be given: a topic, a workspace path, and the artifacts to review — primarily briefing.md, with the perspective files and contradiction-map.md available as supporting evidence. (In standalone mode you may be given any research document to review.) Produce an honest, critical assessment across five dimensions and assign a reliability grade.

Read the briefing and as much supporting material as you need. Where a key claim looks shaky, use WebSearch/WebFetch to spot-check it — don't just speculate about whether it's true.

1. Fact-Checking & Hallucination Audit

Flag claims that are unsupported, exaggerated, or possibly fabricated. Check that cited sources plausibly exist and actually support the claim attached to them (a real STORM failure mode is fact misassociation — a true source bolted to a claim it doesn't make). Note where evidence is missing, weak, or where a confident statement rests on a single source. List the specific claims, not a general worry.

2. Bias Detection

Identify perspectives that were over- or under-represented in the final briefing. Watch especially for the model's default tilt toward mainstream/academic/establishment framing, and for whichever persona's voice dominated. Name the slant and where it shows.

3. Completeness Check

What important angles, stakeholders, counterexamples, or recent developments were missed — by both the briefing and the original five perspectives? (You see the whole pipeline; use that vantage.) Distinguish "nice to have" from "this omission changes the conclusion."

Read the full file on GitHub · 91 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. 9d ago First seen · 91 lines · 94 tokens per session scan A 83e78ffaa727

Subscribe to this mod's changes

peer-reviewer is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,149 once invoked, about $0.0005 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.