auto-review-loop

auto-review-loop is a skill for Claude Code, Codex from raja21068/AutoResearch. It costs 57 tokens per session (5,042 once invoked), scanned A, original, MIT.

A workflow that repeatedly reviews a research document, applies fixes, and reviews it again. It stops when the review is positive or when it reaches the allowed number of rounds.

In plain words
What is it for?
It helps improve research papers or reports through several review-and-revision cycles, with an optional human checkpoint between rounds.
Why use it?
It reduces the manual effort of sending a document for review, making changes, and checking the result repeatedly.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also runs codex exec. Also seen: reads .claude/ paths; mentions Codex.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - **[Output Versioning Protocol](../shared-references/output-versioning.md)** — write timestamped file first, then copy to fixed name.

Good fit It helps improve research papers or reports through several review-and-revision cycles, with an optional human checkpoint between rounds.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/raja21068/AutoResearch
agentmods
npx agentmods add skills/raja21068/autoresearch/auto-review-loop

Made for: Claude Code, Codex.

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/raja21068/autoresearch/auto-review-loop"><img src="https://agentmods.dev/badge/skills/raja21068/autoresearch/auto-review-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,042 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00057 $0.05042
Opus 5 $0.00028 $0.02521
Sonnet 5 $0.00011 $0.01008
Haiku 4.5 $0.00006 $0.00504

Measured 5d ago against content hash 24beb955482c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

auto-review-loop scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

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

- **Anti-hallucination citations**: When adding references during fixes, NEVER fabricate BibTeX. Use the same DBLP → CrossRef → `[VERIFY]` chain as `/paper-write`: (1) `curl -s "https://dblp.org/search/publ/api?q=TITLE&f
skills/aris/auto-review-loop/SKILL.md · 462 lines

How it starts

The opening of the file, as written. The whole thing — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Review Loop: 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)
  • REVIEWER_MODEL = gpt-5.4 — Model used via Codex MCP. Must be an OpenAI model (e.g., gpt-5.4, o3, gpt-4o)
  • REVIEWER_BACKEND = codex — Default: Codex MCP (xhigh). Override with — reviewer: oracle-pro for GPT-5.4 Pro via Oracle MCP. See shared-references/reviewer-routing.md.
  • OUTPUT_DIR = review-stage/ — All review-stage outputs go here. Create the directory if it doesn't exist.
  • HUMAN_CHECKPOINT = false — When true, pause after each round's review (Phase B) and present the score + weaknesses to the user. Wait for user input before proceeding to Phase C. The user can: approve the suggested fixes, provide custom modification instructions, skip specific fixes, or stop the loop early. When false (default), the loop runs fully autonomously.
  • COMPACT = false — When true, (1) read EXPERIMENT_LOG.md and findings.md instead of parsing full logs on session recovery, (2) append key findings to findings.md after each round.
  • REVIEWER_DIFFICULTY = medium — Controls how adversarial the reviewer is. Three levels:
    • medium (default): Current behavior — MCP-based review, Claude controls what context GPT sees.
    • hard: Adds Reviewer Memory (GPT tracks its own suspicions across rounds) + Debate Protocol (Claude can rebut, GPT rules).
    • nightmare: Everything in hard + GPT reads the repo directly via codex exec (Claude cannot filter what GPT sees) + Adversarial Verification (GPT independently checks if code matches claims).

💡 Override: /auto-review-loop "topic" — compact: true, human checkpoint: true, difficulty: hard

Read the full file on GitHub · 462 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. 5d ago First seen · 462 lines · 57 tokens per session scan A 24beb955482c

Subscribe to this mod's changes

auto-review-loop is a skill published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 5,042 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

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

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

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