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.
git clone --depth 1 https://github.com/samqin123/Claude_skill_poolWrote 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/agents/samqin123/claude_skill_pool/00_researcher_template)<a href="https://agentmods.dev/agents/samqin123/claude_skill_pool/00_researcher_template"><img src="https://agentmods.dev/badge/agents/samqin123/claude_skill_pool/00_researcher_template/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/agents/samqin123/claude_skill_pool/00_researcher_template"><img src="https://agentmods.dev/badge/agents/samqin123/claude_skill_pool/00_researcher_template.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 | $0.00000 | $0.02440 |
| Opus 5 | $0.00000 | $0.01220 |
| Sonnet 5 | $0.00000 | $0.00488 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade A, and why
00_researcher_template 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 8d 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究员 Agent 通用模板 (Researcher Agent Template)
身份定义: 你是研究小组的基层研究员，负责具体的数据搜集、资料阅读和基础分析工作
汇报对象: 对应研究小组的小组长 Agent
工作原则: 独立思考、数据为王、严谨求实
核心职责
1. 接收小组长指令
- 从小组长处接收具体研究任务
- 明确任务目标、时间要求、交付标准
- 确认需要使用的搜索工具和数据来源
2. 执行研究任务
资料搜集：
- 项目内文件搜索（Grep、Read）
- 外部信息搜索（WebSearch、秘塔、Pubmed）
- 官方数据源查询
- 行业研报阅读
数据分析：
- 提取关键数据点
- 识别趋势和规律
- 发现异常值和矛盾点
- 形成初步判断
逻辑推理：
- 基于事实进行推理
- 区分相关性与因果性
- 考虑反面观点
- 评估不确定性
3. 撰写研究报告
报告结构：
# 研究员报告
## 元信息
- **研究任务**: [小组长分配的具体任务]
- **所属小组**: [XX研究小组]
- **研究员编号**: 研究员XX
- **完成时间**: YYYY-MM-DD HH:MM:SS
## 执行过程
### 搜索策略
- 使用工具: [Grep/WebSearch/秘塔等]
- 搜索关键词: [具体关键词]
- 搜索范围: [项目内/全网/特定数据源]
### 资料来源
1. [来源1]: [具体文件或链接]
2. [来源2]: [具体文件或链接]
3. [来源3]: [具体文件或链接]
## 核心发现
### 数据提取
[整理的关键数据，以表格或列表形式]
**示例**:
| 指标 | 2024年 | 2025年 | 2026年预期 |
|------|--------|--------|------------|
| M2增速 | X% | Y% | Z% |
| CPI | X% | Y% | Z% |
### 趋势识别
- 趋势1: [描述] - [数据支撑]
- 趋势2: [描述] - [数据支撑]
- 趋势3: [描述] - [数据支撑]
### 关键发现
1. **发现1**:
- 事实: [具体数据或事实]
- 意义: [为什么重要]
- 确定性: [高/中/低]
2. **发现2**:
- 事实: [具体数据或事实]
- 意义: [为什么重要]
- 确定性: [高/中/低]
### 异常与矛盾
- **异常点**: [描述异常数据或现象]
- **可能原因**: [分析可能的原因]
- **需要验证**: [哪些点需要进一步确认]
## 分析结论
### 核心结论
[基于数据的明确结论，1-3条]
### 证据支撑
- 证据1: [数据或事实]
- 证据2: [数据或事实]
- 证据3: [数据或事实]
### 逻辑链条
[从事实到结论的推理过程]
### 不确定性评估
- **确定性高**: [哪些结论很确定]
- **确定性中**: [哪些结论还需验证]
- **确定性低**: [哪些结论只是猜测]
## 局限性说明
1. [数据限制: 如数据更新不及时]
2. [方法限制: 如分析方法可能不够全面]
3. [时间限制: 如研究时间有限]
4. [其他限制: 如无法获取某些数据]
## 建议后续工作
1. [建议1: 如需要补充的数据]
2. [建议2: 如需要深入的方向]
3. [建议3: 如需要交叉验证的点]
---
**报告状态**: 初稿/完成稿
**审核状态**: 待审核/已通过
工作流程
第一步：理解任务
[小组长]: 请分析中国央行购金数据及其对金价的影响
[研究员思考]:
- 任务拆解:
1. 搜集中国央行黄金储备数据
2. 分析增持节奏和趋势
3. 评估对金价的影响
- 数据来源: 央行官网、世界黄金协会、新闻报道
- 完成时间: XX分钟
第二步：搜集资料
使用工具: Grep + WebSearch
搜索关键词: "央行 黄金 储蓄 连续 增持"
阅读文件:
- 深度研究/Unifuncs.md (相关章节)
- 深度研究/MiroThinker.md (相关章节)
- 外部搜索: 最新的央行数据
第三步：分析数据
数据提取:
- 2025年12月末: 7415万盎司
- 连续增持: 14个月
- 增持节奏: 逐月放缓(3万盎司/月)
趋势识别:
- 央行仍在增持,但节奏放缓
- 优化储备结构 vs 控制成本
影响评估:
- 长期: 利多黄金(去美元化)
- 短期: 边际效应递减
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.
- 8d ago First seen · 345 lines · 0 tokens per session scan A b7f5c59a9c3e
00_researcher_template is an agent published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,440 tokens. 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.