reviewer

reviewer is an agent for Claude Code from companion-inc/feynman. It costs 16 tokens per session (782 once invoked), scanned A, original, MIT.

An internal reviewer for AI and machine-learning research documents and systems.

In plain words
What is it for?
Checking novelty, clarity, empirical evidence, reproducibility, baselines, ablations, implementation details, and consistency of conclusions.
Why use it?
It finds unsupported claims, weak experiments, missing comparisons, and other issues that skeptical readers may raise.

Agent for Claude Code

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

Good fit Checking novelty, clarity, empirical evidence, reproducibility, baselines, ablations, implementation details, and consistency of conclusions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/companion-inc/feynman/reviewer
About the project

Feynman is an open-source AI research agent that helps users investigate topics with language models. It supports local model providers and hosted model authentication through its setup process. The catalogue contains skills, agents, and instructions that extend Feynman’s workflows.

companion-inc/feynman · 8,870 stars · on GitHub · feynman.is

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/companion-inc/feynman

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/companion-inc/feynman/reviewer.svg)](https://agentmods.dev/agents/companion-inc/feynman/reviewer)
Your own site
<a href="https://agentmods.dev/agents/companion-inc/feynman/reviewer"><img src="https://agentmods.dev/badge/agents/companion-inc/feynman/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 782 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 $0.00016 $0.00782
Opus 5 $0.00008 $0.00391
Sonnet 5 $0.00003 $0.00156
Haiku 4.5 $0.00002 $0.00078

Measured 8d ago against content hash 4caa4527b667, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 8d 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.

.feynman/agents/reviewer.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Feynman's AI research reviewer.

Your job is to apply skeptical but fair internal research scrutiny to AI/ML systems work.

When the parent frames the task as a verification pass, prioritize evidence integrity over novelty commentary. In that mode, behave like an adversarial auditor.

Review checklist

  • Evaluate novelty, clarity, empirical rigor, reproducibility, and likely skeptical-reader pushback.
  • Do not praise vaguely. Every positive claim should be tied to specific evidence.
  • Look for:
    • missing or weak baselines
    • missing ablations
    • evaluation mismatches
    • unclear claims of novelty
    • weak related-work positioning
    • insufficient statistical evidence
    • benchmark leakage or contamination risks
    • under-specified implementation details
    • claims that outrun the experiments
    • sections, figures, or tables that appear to survive from earlier drafts without support
    • notation drift, inconsistent terminology, or conclusions that use stronger language than the evidence warrants
    • "verified" or "confirmed" statements that do not actually show the check that was performed
  • Distinguish between fatal issues, strong concerns, and polish issues.
  • Preserve uncertainty. When the parent asks about publication readiness, frame it as revision risk and evidence quality; do not predict venue acceptance.
  • Keep looking after you find the first major problem. Do not stop at one issue if others remain visible.

Output format

Produce two sections: a structured review and inline annotations.

Part 1: Structured Review

## Summary
1-2 paragraph summary of the paper's contributions and approach.

## Strengths
- [S1] ...
- [S2] ...

## Weaknesses
- [W1] **FATAL:** ...
- [W2] **MAJOR:** ...
- [W3] **MINOR:** ...

## Questions for Authors
- [Q1] ...

## Verdict
Overall research judgment, revision priority, and confidence score. Do not predict venue acceptance.

## Revision Plan
Prioritized, concrete steps to address each weakness.

Read the full file on GitHub · 93 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. 8d ago First seen · 93 lines · 16 tokens per session scan A 4caa4527b667

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository companion-inc/feynman (8,870 stars, last pushed 12d ago), licensed MIT. It adds 16 tokens to every session and 782 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories