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
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.
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill qzcligit clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleepWrote 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/qzcli)<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/qzcli"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/qzcli/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/qzcli"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/qzcli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Privilege Escalation · line 52 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Rogue Agent · line 5 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00082 | $0.02315 |
| Opus 5 | $0.00041 | $0.01157 |
| Sonnet 5 | $0.00016 | $0.00463 |
| Haiku 4.5 | $0.00008 | $0.00231 |
Grade A, and why
qzcli 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qzcli — 启智平台任务管理
A kubectl/docker-style CLI for managing GPU compute jobs on the Qizhi (启智) platform.
GitHub: tianyilt/qzcli_tool
Environment contract
Qizhi is the scheduler-cluster shape of ../shared-references/compute-env-contract.md:
images are built OFF-platform and referenced at submit time, so the declarative
env spec + env:<name>@<specHash> ledger (.aris/compute/qizhi.md) is what
keeps "which image has which stack" answerable. Run the kernel witness inside a
submitted job (not on the login side) before trusting an image for a long run.
Installation
pip install rich requests prompt_toolkit mcp
git clone https://github.com/tianyilt/qzcli_tool
cd qzcli_tool && pip install -e .
MCP Integration (optional)
To use qzcli as an MCP tool directly from Claude Code or Codex:
# Claude Code
claude mcp add qzcli -- qzcli-mcp
# Codex
codex mcp add qzcli -- qzcli-mcp
Configuration
Credentials are read in this priority order:
CLI args > --password-stdin > env vars > QZCLI_ENV_FILE (.env) > ~/.qzcli/config.json > interactive input
# Option A: env file (recommended)
mkdir -p ~/.qzcli
cat > ~/.qzcli/.env <<'EOF'
QZCLI_USERNAME="your_username"
QZCLI_PASSWORD="your_password"
EOF
# Option B: environment variables
export QZCLI_USERNAME="your_username"
export QZCLI_PASSWORD="your_password"
export QZCLI_API_URL="https://qz.yourorg.edu.cn"
Config files are stored in ~/.qzcli/: config.json, .cookie, resources.json, jobs.json.
Quick Start
# 1. Login
qzcli login
# 2. Discover and cache workspaces/compute groups (run once, re-run after joining new workspaces)
qzcli res -u
# 3. Check available nodes
qzcli avail
# 4. List running jobs
qzcli ls -c -r
Authentication
# Interactive login
qzcli login
# With credentials
qzcli login -u YOUR_USERNAME -p 'YOUR_PASSWORD'
# Read password from stdin (for scripts)
echo 'YOUR_PASSWORD' | qzcli login -u YOUR_USERNAME --password-stdin
# Check current cookie
qzcli cookie --show
# Clear cookie
qzcli cookie --clear
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.
- 7d ago First seen · 325 lines · 82 tokens per session scan A 328953e6e4a2
qzcli is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (15,970 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 2,315 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.