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 raja21068/AutoResearch --skill qzcligit clone --depth 1 https://github.com/raja21068/AutoResearchWrote 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/raja21068/autoresearch/qzcli)<a href="https://agentmods.dev/skills/raja21068/autoresearch/qzcli"><img src="https://agentmods.dev/badge/skills/raja21068/autoresearch/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/raja21068/autoresearch/qzcli"><img src="https://agentmods.dev/badge/skills/raja21068/autoresearch/qzcli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02210 |
| Opus 5.5 | $0.00033 | $0.00884 |
| Sonnet 5.5 | $0.00016 | $0.00442 |
| Haiku 4.5 | $0.00008 | $0.00221 |
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 1mo 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 — 317 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
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
Note: qzcli avail auto-refreshes the cookie if it expires and credentials are configured.
Resource Discovery
# List cached workspaces
qzcli res --list
# Refresh all workspace resource cache (run this first!)
qzcli res -u
# Refresh a specific workspace
qzcli res -w MY_WORKSPACE -u
# Set a human-readable alias for a workspace
qzcli res -w ws-xxxxxxxx --name "My Workspace"
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.
- 1mo ago First seen · 317 lines · 82 tokens per session scan A 6828b19a73b2
qzcli is a skill published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 5mo ago), licensed MIT. It adds 82 tokens to every session and 2,210 once invoked, about $0.0003 per session on Opus 5.5. 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
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
distributed-training-deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.
mcore-run-on-slurm
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDADEVICEMAXCONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.