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/agentscope-ai/qwenpaw-data/runtime-guidenpx skills add agentscope-ai/QwenPaw-Data --skill runtime-guidegit 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/runtime-guide)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/runtime-guide"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/runtime-guide.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 | $0.00055 | $0.02204 |
| Opus 5 | $0.00028 | $0.01102 |
| Sonnet 5 | $0.00011 | $0.00441 |
| Haiku 4.5 | $0.00006 | $0.00220 |
Grade A, and why
runtime-guide 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 5d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
runtime-guide
1. 产物落盘规范
1.1 工作目录
每次执行都使用 QwenPaw Data runtime 指定的当前产物目录。本文用
<current_artifacts> 表示:
普通对话: <workspace>/artifacts/<session_id>
TaskGraph 节点: <workspace>/artifacts/<session_id>/<graph_id>/<node_id>
当前执行目录内结构如下:
<current_artifacts>/
├── plan.yaml # 原始 plan(来自 planner,不修改)
├── plan_v1.yaml # 第一次修改后的 plan(如有)
├── plan_v2.yaml # 第二次修改后的 plan(如有)
├── steps/ # 步骤结果(每步完成后写入)
├── data/ # 数据产物
│ ├── raw/ # 原始获取的数据(从数据源拉取的原始结果)
│ └── processed/ # 计算处理后的数据(衍生指标、数据清洗结果等)
└── result.yaml # 最终结果(执行完成后写入)
plan.yaml是原始计划,始终保留不修改- 执行过程中如需调整计划,生成
plan_v1.yaml、plan_v2.yaml... 按修改顺序递增 - 执行时始终以最新版本的 plan 为准
session_id必须使用 runtime 提供的当前值,不自行生成- 仅当 runtime 明确提供当前
graph_id和node_id时才使用节点子目录;普通 对话直接使用 session 目录 - 不在 workspace 根或未隔离的
artifacts/下创建任务目录
1.2 数据文件
| 类型 | 存放位置 | 命名 |
|---|---|---|
| 原始数据 | <current_artifacts>/data/raw/ |
<数据描述>.<ext> |
| 计算结果 | <current_artifacts>/data/processed/ |
<分析内容>_<结果描述>.<ext> |
- 文件命名应自描述,能看出内容是什么
- 列名/字段名须有业务含义(如
date, dau, dau_wow, is_anomaly),不使用col1, col2 - 每个关键的计算结果都要落盘到
data/processed/,包括清洗后的数据文件、衍生指标、归因结果、异常检测结果、维度交叉表等,确保结论可溯源、可复现
示例:
<current_artifacts>/data/raw/dau_daily_202603.csv
<current_artifacts>/data/processed/channel_attribution_result.csv
1.3 步骤结果
每个分析步骤完成后,落盘一份步骤结果,服务于过程审查和结果溯源。存放在当前执行
目录的 steps/ 子目录下:
<current_artifacts>/steps/
├── step_01_<步骤描述>.yaml
├── step_02_<步骤描述>.yaml
└── ...
每份步骤结果包含:
- 做了什么:本步骤执行的操作描述
- 产出文件:涉及的数据文件、中间结果的路径索引
- 代码:本步骤执行的关键代码或脚本(如有)
- 结论:本步骤的分析结论或发现
1.4 最终结果
执行完成后,在 <current_artifacts>/result.yaml 产出最终结果,包含:
- 完成状态:全部完成 / 部分完成 / 失败
- 核心结论:对分析目标的直接回答
- 支撑数据:结论依赖的数据文件
- 未解决问题:数据缺失、结果矛盾、未追踪的线索
- 后续建议:建议深入分析的方向
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.
- 5d ago First seen · 188 lines · 55 tokens per session scan A 1b9ab48f7bee
runtime-guide is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (61 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 2,204 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
matryca-python-standards
Apply Matryca Python 3.12+, uv, typing, validation, concurrency, filesystem-safety, logging, and verification standards. Use whenever creating or modifying Python source or tests.
python-mcp-server-expert
Expert assistant for developing Model Context Protocol (MCP) servers in Python using FastMCP, mcp package, Pydantic, and async patterns. Use when building MCP tools, resources, prompts, or debugging Python MCP server issues.
python-testing-patterns
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
financial-memo-writer
Write investment-research memos and articles in a sincere, contrarian, framework-first zh-TW (Taiwan-market) voice. Use when asked to draft, ghost-write, or continue an in-depth analysis (深度分析), a multi-topic weekly market note (週度市場筆記), or a short column/op-ed (短評/專欄), or to rewrite content into a…
pipeline-debug
Debug and A/B-test the podcast content pipeline (pipelines/services/podcast) offline — run one stored episode through the real extractor→writer→markdown pipeline with any OpenRouter model, score JSON reliability / Traditional-Chinese fidelity / ticker+tag linking / chapter consolidation, find genuinely-failed…
threads-writer
Draft or rewrite Threads (脆) posts in TinBoker's voice — an openly automated account with one judgment worth stating and no first person (never "我"), not a social-media copywriter and not a news summary. Use when asked to turn a podcast episode into a Threads post, write/rewrite 脆文, fix a draft that reads like AI or…