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 agentscope-ai/QwenPaw-Data --skill qwenpaw-data-cligit clone --depth 1 https://github.com/agentscope-ai/QwenPaw-DataWrote 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/agentscope-ai/qwenpaw-data/qwenpaw-data-cli)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/qwenpaw-data-cli"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/qwenpaw-data-cli/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/agentscope-ai/qwenpaw-data/qwenpaw-data-cli"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/qwenpaw-data-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00109 | $0.01844 |
| Opus 5 | $0.00055 | $0.00922 |
| Sonnet 5 | $0.00022 | $0.00369 |
| Haiku 4.5 | $0.00011 | $0.00184 |
Grade A, and why
qwenpaw-data-cli 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 10d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QwenPaw Data CLI
将 qwenpaw-data 作为外部任务执行入口。若当前 agent 已经运行在 QwenPaw Data 任务内部,不要递归启动另一个 qwenpaw-data 进程。
执行前检查
-
运行
qwenpaw-data --help,确认命令存在且公开子命令为plan、execute、run、chat和datasource。若命令不可用,报告需要先运行项目的scripts/init_local.sh;不要搜索或直接调用.venv/bin/qwenpaw-data,也不要自行安装或改写项目环境。 -
CLI 会自动加载项目根目录
.env或QWENPAW_DATA_ENV_FILE指定的文件。不要读取、打印或手动sourcedotenv 文件。模型命令会优先使用QWENPAW_DATA_MODEL_*,未配置时回退到LLM_MODEL、OPENAI_API_KEY和OPENAI_BASE_URL。 -
使用
QWENPAW_DATA_CM_BASE_URL指定 Data Bridge 地址;未配置时默认使用http://127.0.0.1:8765。 -
需要访问数据源时,先运行:
qwenpaw-data datasource list从返回 JSON 的
items中选择精确的datasource_id。优先使用用户明确指定的 ID;名称或类型只有一个明确匹配时才自动选择;存在多个合理候选时向用户确认。不要从已掩码的凭据推断数据源。 -
假定模型凭据和 MCP 配置已由运行环境提供。不要写入凭据或自行创建、覆盖 MCP 配置。
选择命令
直接完成普通任务
对不需要预先审阅或复用计划的一次性任务使用 run:
qwenpaw-data run --datasource-id "sales-prod" "分析最近 30 天销售额趋势"
需要传递较长、包含多行或容易被 shell 错误解释的请求时,将请求保存到文件并使用 --file:
qwenpaw-data run --file request.md --datasource-id "sales-prod"
位置 prompt 与 --file 互斥,不要同时传递。
审阅或复用计划
当用户要求先看计划、任务需要人工审阅,或 SOP 需要重复执行时,先生成 YAML:
qwenpaw-data plan --file request.md --datasource-id "sales-prod" --output plan.yaml
确认命令成功、plan.yaml 存在且内容符合任务目标后再执行:
qwenpaw-data execute plan.yaml --datasource-id "sales-prod"
在 plan 和 execute 中重复传入同一个 --datasource-id;该参数属于每次 CLI 请求的上下文,不要假定它已写入 SOP。
交互式对话
只在有人值守且终端支持标准输入时使用:
qwenpaw-data chat --datasource-id "sales-prod"
不要在无人值守的自动化流程中使用 chat,因为它会持续等待输入,直至收到 exit、quit 或 EOF。
选择输出模式
run 和 execute 默认启用流式输出。保留默认模式,持续读取文本增量、工具调用和工具结果,直至进程退出:
qwenpaw-data run --file request.md --datasource-id "sales-prod"
qwenpaw-data execute plan.yaml --datasource-id "sales-prod"
不要仅因短时间没有新输出就判定任务失败;使用支持长超时或会话轮询的命令执行工具,并确认进程是否仍在运行。
仅在同时满足以下条件时使用 --no-stream:
- 需要干净的最终回复以及
Execution summary; - 调用方允许任务期间没有 stdout;
- 调用方提供足够长的超时或能够轮询进程状态。
qwenpaw-data run --no-stream --file request.md --datasource-id "sales-prod"
qwenpaw-data execute plan.yaml --no-stream --datasource-id "sales-prod"
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.
- 10d ago First seen · 130 lines · 109 tokens per session scan A d4d0ab31a283
qwenpaw-data-cli is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (71 stars, last pushed yesterday), licensed Apache-2.0. It adds 109 tokens to every session and 1,844 once invoked, about $0.0005 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
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
status
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
connect-recommend
Use this skill when the user asks about Stripe Connect configuration, charge patterns, Dashboard access, or how to get started with Connect, is building a marketplace, platform, multi-vendor store, gig platform, or subscription platform, needs to pay out sellers, vendors, or providers, mentions split payments, revenue…
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.