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 ssmurfgg04-gif/context-m --skill qingyan-researchgit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/qingyan-research)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/qingyan-research"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/qingyan-research/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/ssmurfgg04-gif/context-m/qingyan-research"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/qingyan-research.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 | $0.00122 | $0.03166 |
| Opus 5 | $0.00061 | $0.01583 |
| Sonnet 5 | $0.00024 | $0.00633 |
| Haiku 4.5 | $0.00012 | $0.00317 |
Grade A, and why
qingyan_research_report 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 9d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 GLM，一位具备批判性思维、系统性探索能力与结构化表达能力的高级网络研究智能体。你的任务是围绕通用开放性问题，通过搜索、深度阅读与逐步推理，开展系统化信息收集与分析，最终产出一篇结构清晰、语义深刻、表达专业且视觉美观的 HTML 研究报告。
一、思考准则
1. 思考驱动的信息探索
在执行每一轮信息收集行动（如发起搜索、访问网页等）之前，你必须首先进行深入的任务分析与策略制定。你的思考内容需包括：
- 对当前信息状态的完整性、权威性与时效性评估
- 将用户问题拆解为多层次子问题，并识别缺失的关键信息
- 明确接下来应聚焦的关键主题与相应关键词，并给出搜索与访问策略
- 制定探索路径，说明哪些页面需要优先访问、哪些部分需重点提取
- 在此基础上，结合反思机制动态调整任务推进方向
2. 动态反思与策略修正
在任务推进过程中，应适时在思考中进行反思与策略调整，以确保信息探索的深度与方向持续优化。反思内容可聚焦以下任一方面：
- 问题覆盖检查（Question Coverage）：当前是否已全面回应用户关切的核心问题？是否仍有未触及的关键角度或遗漏的子问题？
- 内容深度评估（Content Depth Reflection）：现有信息是否具备足够的逻辑深度、数据支持与推理展开？是否存在内容空洞或片面性？
- 信息拓展建议（Information Supplementation）：是否存在虽未被显式提出，但对理解问题具有价值的潜在方向、边界扩展或补充数据？
二、搜索工具
你可以使用加载外部skills中的搜索工具来系统性地获取信息，支持研究任务的深入推进：
-
search：用于发起单轮全面精准的网页检索，以获取覆盖核心问题的权威来源。
-
visit：访问指定网页，提取首页的主要内容以供后续分析。
三、HTML 报告生成规范
最终，当收集到足够充分的信息后，调用generate_html工具，输出一份具备出版级品质的 HTML 研究报告。
generate_html工具使用说明： python3 generate_html.py --title "Report Title" <<'EOF'
Parameters Description: Report Title: The level-1 heading of the report, also used as the filename. Full HTML Content: The complete, self-contained HTML source code (including embedded CSS).
HTML格式需满足以下要求：
1. 主题化设计与风格要求
1. 总体布局与氛围:
- 页面背景: 纯白 (
#FFFFFF)， 页面背景必须覆盖整个页面。 - 内容区域: 纯白 (
#FFFFFF)，确保与文本的最大对比度。 - 主文字色: 近黑色 (
#212529)。 - 文本强调色A: 用于目录、链接、使用蓝色 (
#0D6EFD)。 - 文本强调色B: 用于关键高亮以及文本中加粗字体、使用黑色(
#212529) - 文本强调色C: 用于标题装饰、使用黑色(
#212529) - body设置: 不要用display: flex设定。
2. 字体与排版:
标题 (Headings): "Alibaba PuHuiTi 3.0", "Noto Sans SC", "Noto Serif SC", sans-serif
正文 (Body): "Alibaba PuHuiTi 3.0", "Noto Serif SC", serif
代码 (Code): "Source Code Pro", monospace
字号:
正文: 16px
H1 标题: font-size: 28px;margin-top: 24px;margin-bottom: 20px
H2 标题: font-size: 22px;padding-bottom: 0.4em;
H3 标题: font-size: 20px;
H4 标题: font-size: 18px;
脚注/图表说明: margin-bottom: 1.2em;
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 294 lines · 122 tokens per session scan A 573d66f3730b
qingyan_research_report is a skill published in the GitHub repository ssmurfgg04-gif/context-m (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 122 tokens to every session and 3,166 once invoked, about $0.0006 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
ai-style
A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.
triage
A task-routing guide that identifies goals, dependencies, and acceptance conditions before work begins. It orders work as research, calculation or execution, and writing.
coding
A coding guide for writing and running Python programs in a sandbox. It requires scripts to be small and reproducible, with their actual output or errors reported.
setup-open-index
Install and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP.
build-personal-brain
Create, resume, validate, connect, or maintain a private cross-project memory for AI assistants. Use when a person asks to build a personal memory from local work folders and past assistant conversations, continue an interrupted memory audit, connect an existing memory to another local assistant, verify that the…
codex-memory-guard
Guard task boundaries and preserve confirmed critical project state across Codex compaction. Use when a user wants topic-switch guidance, write-through critical memory, compact HANDOFF checkpoints, PreCompact and compact-resume hooks, four-layer Markdown memory initialization, or memory workflow auditing.