auto-review-loop-llm

auto-review-loop-llm is a skill for Claude Code from raja21068/AutoResearch. It costs 47 tokens per session (2,032 once invoked), scanned B, a copy of auto-review-loop-llm, MIT.

An automated research-review loop that uses a configurable language model to review work, apply fixes, and review the updated version again.

In plain words
What is it for?
Use it to run review-and-improvement rounds through an OpenAI-compatible language-model API and keep a cumulative review record.
Why use it?
It provides repeated outside feedback for research projects when a single model pass is not enough to uncover problems.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/yourname/.claude/mcp-servers/llm-chat/server.py.

Good fit Use it to run review-and-improvement rounds through an OpenAI-compatible language-model API and keep a cumulative review record.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 auto-review-loop-llm

README.md
[![agentmods](https://agentmods.dev/badge/skills/raja21068/autoresearch/auto-review-loop-llm/github.svg)](https://agentmods.dev/skills/raja21068/autoresearch/auto-review-loop-llm)
Your own site
<a href="https://agentmods.dev/skills/raja21068/autoresearch/auto-review-loop-llm"><img src="https://agentmods.dev/badge/skills/raja21068/autoresearch/auto-review-loop-llm/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 auto-review-loop-llm

Your own site · 80×15
<a href="https://agentmods.dev/skills/raja21068/autoresearch/auto-review-loop-llm"><img src="https://agentmods.dev/badge/skills/raja21068/autoresearch/auto-review-loop-llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 89% copy Near-identical to another mod 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 $0.00047 $0.02032
Opus 5 $0.00023 $0.01016
Sonnet 5 $0.00009 $0.00406
Haiku 4.5 $0.00005 $0.00203

Measured 8d ago against content hash 01da65516b19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

auto-review-loop-llm scanned grade B with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Add to `~/.claude/settings.json`:

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Fallback: curl**
Origin

This is a copy

89% identical to auto-review-loop-llm — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/aris/auto-review-loop-llm/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Review Loop (Generic LLM): Autonomous Research Improvement

Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.

Context: $ARGUMENTS

Constants

  • MAX_ROUNDS = 4
  • POSITIVE_THRESHOLD: score >= 6/10, or verdict contains "accept", "sufficient", "ready for submission"
  • REVIEW_DOC: review-stage/AUTO_REVIEW.md (cumulative log) (fall back to ./AUTO_REVIEW.md for legacy projects)

LLM Configuration

This skill uses any OpenAI-compatible API for external review via the llm-chat MCP server.

Configuration via MCP Server (Recommended)

Add to ~/.claude/settings.json:

{
  "mcpServers": {
    "llm-chat": {
      "command": "/usr/bin/python3",
      "args": ["/Users/yourname/.claude/mcp-servers/llm-chat/server.py"],
      "env": {
        "LLM_API_KEY": "your-api-key",
        "LLM_BASE_URL": "https://api.deepseek.com/v1",
        "LLM_MODEL": "deepseek-chat"
      }
    }
  }
}

Supported Providers

Provider LLM_BASE_URL LLM_MODEL
OpenAI https://api.openai.com/v1 gpt-4o, o3
DeepSeek https://api.deepseek.com/v1 deepseek-chat, deepseek-reasoner
MiniMax https://api.minimax.io/v1 MiniMax-M2.7
Kimi (Moonshot) https://api.moonshot.cn/v1 moonshot-v1-8k, moonshot-v1-32k
ZhiPu (GLM) https://open.bigmodel.cn/api/paas/v4 glm-4, glm-4-plus
SiliconFlow https://api.siliconflow.cn/v1 Qwen/Qwen2.5-72B-Instruct
阿里云百炼 https://dashscope.aliyuncs.com/compatible-mode/v1 qwen-max
零一万物 https://api.lingyiwanwu.com/v1 yi-large

API Call Method

Primary: MCP Tool

mcp__llm-chat__chat:
  prompt: |
    [Review prompt content]
  model: "deepseek-chat"
  system: "You are a senior ML reviewer..."

Fallback: curl

curl -s "${LLM_BASE_URL}/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${LLM_API_KEY}" \
  -d '{
    "model": "${LLM_MODEL}",
    "messages": [
      {"role": "system", "content": "You are a senior ML reviewer..."},
      {"role": "user", "content": "[review prompt]"}
    ],
    "max_tokens": 4096
  }'

Read the full file on GitHub · 250 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 · 250 lines · 47 tokens per session scan B 01da65516b19

Subscribe to this mod's changes

auto-review-loop-llm is a skill published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 2,032 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). It is 89% identical to auto-review-loop-llm, differing in 20 lines, and is treated as a copy.

Related

Other skills, from other repositories

literature-review-agent

Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), cross-corroborate against Crossref + OpenAlex to…

Ar9av/PaperOrchestra · 149 tokens

agent-research-aggregator

Pre-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimentallog.md). TRIGGER when the user says…

Ar9av/PaperOrchestra · 177 tokens

content-refinement-agent

Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate…

Ar9av/PaperOrchestra · 145 tokens

paper-orchestra

Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper…

Ar9av/PaperOrchestra · 143 tokens

section-writing-agent

Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimentallog.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges…

Ar9av/PaperOrchestra · 125 tokens

plotting-agent

Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimentallog.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER…

Ar9av/PaperOrchestra · 102 tokens