ARIS is a collection of Markdown-based skills that define a workflow for autonomous machine-learning research, including idea discovery, experiment automation, and review loops. Researchers and AI coding agents use it across tools such as Claude Code, Codex, Cursor, and OpenClaw without depending on a single framework. The catalogue entries are ARIS workflow skills and agents.
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.
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleepnpx agentmods add skills/wanshuiyin/auto-claude-code-research-in-sleep/auto-review-loop-minimaxWrote 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.
[](https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/auto-review-loop-minimax)<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/auto-review-loop-minimax"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/auto-review-loop-minimax/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.
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/auto-review-loop-minimax"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/auto-review-loop-minimax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 65 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Data Exfiltration · line 47 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 52 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 126 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 278 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 229 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 276 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.03247 |
| Opus 5 | $0.00025 | $0.01623 |
| Sonnet 5 | $0.00010 | $0.00649 |
| Haiku 4.5 | $0.00005 | $0.00325 |
Grade B, and why
auto-review-loop-minimax 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 13d 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.
**API Key**: Read from `~/.claude/settings.json` under `env.MINIMAX_API_KEY`, or from environment variable. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
### Method 2: curl (Fallback) Copies of this mod
1 near-identical copy found in the catalogue:
- auto-review-loop-minimax — 86% identical, 32 lines differ
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Review Loop (MiniMax Version): Autonomous Research Improvement
🔒 Do not wrap this skill in
/loop,/schedule, orCronCreate. Like/auto-review-loop, it already loops internally (review → fix → re-review), feeding each round's prior-round summary into the next review prompt (the backend is a stateless per-round API call, not a shared thread). An external timer re-enters from the top each tick, dropping that accumulated context and firing the verdict on wall-clock time instead of on artifact change — zero new signal, full token cost. Schedule the external wait that precedes it, not the verdict. Seeshared-references/external-cadence.md.
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 AND verdict ∈ {"ready", "almost"} — both must hold, matching the operative STOP CONDITION below. Verdict vocabulary is {"ready", "almost", "not ready"}. (Earlier wording used
orand a stale verdict set; theANDform is authoritative.) - REVIEW_DOC:
review-stage/AUTO_REVIEW.md(cumulative log) (fall back to./AUTO_REVIEW.mdfor legacy projects) - REVIEWER_MODEL =
MiniMax-M3— Model used via MiniMax API
API Configuration
This skill uses MiniMax API for external review. Two methods are supported:
Method 1: MCP Tool (Primary)
If mcp__minimax-chat__minimax_chat is available, use it:
mcp__minimax-chat__minimax_chat:
prompt: |
[Review prompt content]
model: "MiniMax-M3"
system: "You are a senior machine learning researcher..."
Method 2: curl (Fallback)
If MCP is not available, use curl directly:
curl -s "https://api.minimax.io/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $MINIMAX_API_KEY" \
-d '{
"model": "MiniMax-M3",
"messages": [
{"role": "system", "content": "You are a senior ML researcher..."},
{"role": "user", "content": "[Review prompt]"}
],
"max_tokens": 4096
}'
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.
- 13d ago First seen · 303 lines · 50 tokens per session scan B 70f495252274
auto-review-loop-minimax is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (16,030 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 3,247 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
code-review
Perform structured code reviews with actionable feedback. Use when a user asks to review code, check code quality, find bugs, audit security, improve performance, or assess maintainability. Trigger when user says things like "review this code", "check for bugs", "is this code secure", "any issues with this", "code…
codex
Multi-AI adversarial fallback chain — three tiers: Codex CLI (primary), OpenCode/GLM5 (fallback), Claude subagent (last resort). Three modes: review (code review with pass/fail gate), challenge (adversarial — tries to break your code), consult (ask anything with session continuity). Use when asked to "codex review"…
code-review
Performs structured code review on a file or directory.
chimera-list-exemptions-not-obligations
A gate that lists what to check fails open — the site nobody remembered to add is the one that breaks. List the exemptions instead, each with a written reason, and the default becomes fail.
chimera-state-what-you-did-not-check
A ranking built from part of the system reads as a ranking of the system — write the scope and the exclusions next to the findings, not after them.
punch
Punch list — completeness and residue check before delivery. Finds what's missing that should exist (omission) and what's left behind that shouldn't (refactor residue). Reconstructs intent, overlays domain checklist, scans for stale references.