Auto Review Loop

What it does

When your agent uses it

• User says auto review loop
• Review until it passes
• Wants autonomous iterative improvement

Example prompts

• “auto review loop”
• “review until it passes”
• “/auto-review-loop”

Requirements

• Pre-approved tools (allowed-tools): Bash(*), Read, Grep, Glob, Write, Edit, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Check for review-stage/REVIEW_STATE.json *(fall back to ./REVIEW_STATE.json if not found — legacy path)*
2. 2Read project narrative documents, memory files, and any prior review documents. When COMPACT = true and compact files exist: read…
3. 3Read recent experiment results (check output directories, logs)
4. 4Identify current weaknesses and open TODOs from prior reviews
5. 5Initialize round counter = 1 (unless recovered from state file)
6. 6Create/update review-stage/AUTO_REVIEW.md with header and timestamp

What it can do on your machine

Read from SKILL.md and the folder at commit 7132192. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash(*)
  • Read
  • Grep
  • Glob
  • Write
  • Edit
  • Agent
  • Skill
  • mcp__codex__codex
  • mcp__codex__codex-reply

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • codex
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • dblp.org
  • doi.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Auto Review Loop loads about 5.1k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 1,688 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~71

When it runs · the whole SKILL.md, loaded when a task matches

~5.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:425

  t << 'EOF' > file`) to write in chunks. Do NOT ask the user for permission — just do it silently.

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash(*), Read, Grep, Glob, Write, Edit, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,688 words (~5,055 tokens).

name

auto-review-loop

allowed-tools

Bash(*), Read, Grep, Glob, Write, Edit, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply

argument-hint

topic-or-scope

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/auto-review-loop of AI4Scientist/nano-scientist.

Open the folder on GitHubat commit 7132192

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in AI4Scientist/nano-scientist, which our catalogue first saw on October 7, 2026.

• OpenLAIR/dr-clawskills/aris-auto-review-loop
• brycewang-stanford/Auto-Empirical-Research-Skillsskills/42-wanshuiyin-ARIS/skills/auto-review-loop