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 agentmods add skills/tianyilt/qzcli_tool/qzcli-mcpnpx skills add tianyilt/qzcli_tool --skill qzcli-mcpgit clone --depth 1 https://github.com/tianyilt/qzcli_toolWrote 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/tianyilt/qzcli_tool/qzcli-mcp)<a href="https://agentmods.dev/skills/tianyilt/qzcli_tool/qzcli-mcp"><img src="https://agentmods.dev/badge/skills/tianyilt/qzcli_tool/qzcli-mcp.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.00492 |
| Opus 5 | $0.00028 | $0.00246 |
| Sonnet 5 | $0.00011 | $0.00098 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
qzcli-mcp 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 6d 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.
What it actually says
qzcli MCP
使用这个 skill 时，优先通过 qzcli-mcp 暴露的工具获取实时信息，不要凭空假设启智平台状态枚举稳定不变。
何时使用
- 用户要看启智平台任务、工作空间、计算组、GPU 使用情况
- 用户要找“哪里还有空机器 / 哪个计算组适合提任务”
- 用户明确担心状态字段、cookie 名、返回结构可能漂移
- 用户要排查“为什么现在模型识别不到某种状态”
工作流
- 如果还没有认证，先用
qz_auth_login或qz_set_cookie - 如果 workspace / 计算组缓存可能过期，先用
qz_refresh_resources - 查询资源推荐时，优先用
qz_get_availability - 查询任务时，优先用
qz_list_jobs/qz_get_job_detail - 如果状态看起来异常或出现未知枚举，调用
qz_inspect_status_catalog
状态处理规则
- 永远优先看
status_raw status_family只是便于上层决策的弱归一化结果- 不要把
status_family当成平台真实枚举 - 需要解释差异时，直接引用
raw中的字段名和值
推荐模式
- 看整体资源：
qz_list_workspaces->qz_refresh_resources->qz_get_availability - 看任务：
qz_list_jobs，必要时再对单条调用qz_get_job_detail - 排查漂移：
qz_inspect_status_catalog，重点关注unknown_statuses
输出建议
- 面向用户汇报时，同时给出“归一化判断”和“原始状态”
- 当发现未知状态时，明确说明这是平台新状态或未覆盖状态，而不是直接误判为失败
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.
- 6d ago First seen · 42 lines · 57 tokens per session scan A 54b1dbc43abd
qzcli-mcp is a skill published in the GitHub repository tianyilt/qzcli_tool (124 stars, last pushed 9d ago), licensed MIT. It adds 57 tokens to every session and 492 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
inkbox-tunnels
Use when bringing a local server online behind a public Inkbox URL — covers Python, TypeScript, and Rust tunnel runtimes, edge vs passthrough TLS, forwarding, handlers, and local liveness.
platform-setup
Full autonomous AI agency setup for https://local-llm-server.strikersam.workers.dev. Uses browse CLI (Browserbase remote mode) to log in as admin, onboard the platform itself as a company, configure all specialists, verify agents are running, and fix any issues found. Run this skill to go from "deployed" to "fully…
autodl
Use AutoDL safely through its official developer APIs and documentation. Trigger for AutoDL balance, Container Instance Pro, elastic deployment, images, GPU stock, NFS, duration packages, WeChat notifications, container metrics, billing, storage, data retention, SSH/JupyterLab/VSCode, CUDA environments…
independent-deploy
Deploys a service to a different cloud target via a separate pipeline.
deploy-service
Deploys the service quickly over HTTP with a certificate-check fallback.
fast-http
Deploys a minimal HTTP service with mocked TLS verification handling.