auto-review-loop

auto-review-loop is a skill for Claude Code from appleweiping/WEIPING_WIKI. It costs 56 tokens per session (805 once invoked), scanned A, original, MIT.

A repeated paper-review workflow that simulates several strict academic peer reviewers. It scores areas such as novelty, clarity, soundness, significance, reproducibility, completeness, and presentation.

In plain words
What is it for?
Use it to review a LaTeX paper draft, summarize reviewer concerns, score its quality, and revise it until it meets the required quality gates.
Why use it?
It exposes weaknesses in a paper before submission, including unsupported claims, missing baselines, unclear methods, and insufficient ablations.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

Part of the aris plugin — 8 skills shipped together

Good fit Use it to review a LaTeX paper draft, summarize reviewer concerns, score its quality, and revise it until it meets the required quality gates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/appleweiping/weiping_wiki/auto-review-loop
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.

Any agent
npx skills add appleweiping/WEIPING_WIKI --skill auto-review-loop
Clone the repo
git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKI

Made for: Claude Code.

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

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 auto-review-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/auto-review-loop.svg)](https://agentmods.dev/skills/appleweiping/weiping_wiki/auto-review-loop)
Your own site
<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/auto-review-loop"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/auto-review-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00056 $0.00805
Opus 5 $0.00028 $0.00402
Sonnet 5 $0.00011 $0.00161
Haiku 4.5 $0.00006 $0.00081

Measured 8d ago against content hash 32c373d78463, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

auto-review-loop 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.

.claude/skills/aris/skills/auto-review-loop/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Review Loop

Simulate a hostile peer review. Iterate until the paper would survive top-venue reviewers.

Decision Gate

Before running:

  • Paper draft exists (paper/main.tex compiles)
  • paper/CLAIM_MAP.md exists
  • Experiment audit passed

Phase 1 — Structured Review (Codex as Reviewer 1)

Invoke Codex with the paper and this rubric using an explicit context pack through agentmemory signals/actions, or by handing the same context to the current Codex session:

Review Rubric (score 1-10 each)

Dimension Question
Novelty Is this a genuine new insight, or incremental/stitching?
Clarity Can a PhD student in the field understand the method in one read?
Soundness Are claims supported by evidence? Any logical gaps?
Significance Would this change how people think about the problem?
Reproducibility Could someone reimplement from the paper alone?
Completeness Are baselines comprehensive? Ablations sufficient?
Presentation Figures clear? Tables readable? Writing concise?

Required Output

## Review Summary
Overall: Accept / Weak Accept / Borderline / Weak Reject / Reject

## Strengths (3-5 bullets)
## Weaknesses (3-5 bullets, ranked by severity)
## Questions for Authors
## Minor Issues (typos, formatting, unclear sentences)

## Scores
Novelty: X/10
Clarity: X/10
...

Phase 2 — Kill Argument (Codex as Adversary)

Ask Codex to write the strongest possible rejection argument:

  • "Why should this paper be rejected?"
  • "What's the fatal flaw?"
  • "What experiment would disprove the main claim?"

If the kill argument is valid and unanswerable → the paper needs fundamental revision.

Phase 3 — Sonnet Quick Scan (Reviewer 2)

Invoke Sonnet for a fast second opinion using agentmemory signals/actions or an explicit current-session handoff:

  • Focus on: clarity, missing references, presentation issues
  • Sonnet is cost-effective for surface-level review

Phase 4 — Author Response & Revision

Read the full file on GitHub · 96 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 · 96 lines · 56 tokens per session scan A 32c373d78463

Subscribe to this mod's changes

auto-review-loop is a skill published in the GitHub repository appleweiping/WEIPING_WIKI (122 stars, last pushed 12d ago), licensed MIT. It adds 56 tokens to every session and 805 once invoked, about $0.0003 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.