# paper-reviewer

paper-reviewer — a reviewer subagent for a co-mathematician setup. It checks reports, citations, proofs and code, and a workstream stays open until it writes an approval file.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 240 repo stars
- Author: franklee16
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/franklee16/academic-research-skills/tree/HEAD/theory-skills/theorist-toolbox-master/agents/paper-reviewer.md
- Updated: 2026-09-18
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/paper-reviewer

## What it does

This agent is built to disagree. It reads `report.md`, `log.md` and the matching part of `paper.tex`, then records `APPROVE`, `REQUEST_CHANGES` or `REJECT` in `.co-math/approvals/<workstream-id>-<round>.md`. No `Verdict: APPROVE` line, no move to `complete`.

What it inspects follows the workstream type. Citations get matched against `references/<id>/note.md`, and at least one per round is fetched with `WebFetch` to see whether the paper sits where the note claims. Proof work is walked step by step; anything waved through as obvious is blocking, and under `strict_mode: true` in `co-math-config.json` phrases like `clearly` or `omitted` are treated the same unless a justification or `\unproven{}` follows. Code work gets `pytest -q tests/` run from the workstream root, plus a look at whether golden values were fitted backwards to whatever the program printed.

Lean results go through plumbing checks rather than a second proof attempt, since the compiler already settled the maths. The agent rebuilds with `lake build`, greps `Main.lean` for a live `sorry`, and compares the formal statement against the claim in `paper.tex`. A formal statement weaker than the paper's is blocking. Tools it can reach for: `Read`, `Write`, `Edit`, `Bash`, `Glob`, `Grep`, `WebFetch`. Citation spot-checks need network access, and a first mathlib build takes a long while before it either passes or fails.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/paper-reviewer.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/paper-reviewer.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/paper-reviewer.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/franklee16/academic-research-skills/tree/HEAD/theory-skills/theorist-toolbox-master/agents/paper-reviewer.md

## When to use it
- keep a workstream open until the reviewer signs off
- catch a citation pointing at a paper that does not exist
- expose a proof step asserted as obvious with nothing behind it
- trace numbers in the paper back to a test run
- confirm a Lean theorem states what the paper claims

## Example prompts
- Review workstream `lit-3`, its status flipped to `review`, then write the approval file.
- Re-check section 4 of `paper.tex` against the prover's report and list the blocking findings.
- The Lean build for `thm-main` is stuck in review, run the check again and give a verdict.

## Similar
- [academic-paper-reviewer](https://affpapa.org/en/nevibecode/skills/academic-paper-reviewer.md) — skill · 10600 installs
- [paper-audit](https://affpapa.org/en/nevibecode/skills/paper-audit.md) — skill · 3600 installs
- [paper-review-pipeline](https://affpapa.org/en/nevibecode/skills/paper-review-pipeline.md) — skill · ★ 475 repo stars
- [paper-editor](https://affpapa.org/en/nevibecode/skills/paper-editor.md) — skill · ★ 165 repo stars
- [ara-rigor-reviewer](https://affpapa.org/en/nevibecode/skills/ara-rigor-reviewer.md) — skill · 953 installs
- [academic-paper-review](https://affpapa.org/en/nevibecode/skills/academic-paper-review.md) — skill · 2800 installs

From the same set: [franklee16/academic-research-skills](https://affpapa.org/en/nevibecode/by/franklee16/academic-research-skills.md) — 98 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
