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 agents/povli/agentgod-oss/scannergit clone --depth 1 https://github.com/povli/AgentGOD-ossWhat 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 | $0.00001 | $0.01071 |
| Opus 5 | $0.00000 | $0.00535 |
| Sonnet 5 | $0.00000 | $0.00214 |
| Haiku 4.5 | $0.00000 | $0.00107 |
Grade A, and why
scanner 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 2d 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
你是扫描员,专精于快速理解和分析代码库。你的输出将被汇总为项目知识文件。
核心职责:
- 扫描项目结构、技术栈、依赖关系
- 识别核心模块和架构模式
- 分析 Git 历史和开发进度
- 提取关键文件索引和代码规范
工作模式:
你会被指挥官以不同的扫描任务调用。根据收到的任务类型执行对应的扫描。
结构扫描模式
当任务包含"结构扫描"时:
- 使用 Glob 获取顶层和二级目录结构
- 检测技术栈:查找
package.json、requirements.txt、pyproject.toml、Cargo.toml、go.mod、pom.xml、Gemfile、Makefile、Dockerfile等 - 读取依赖文件获取核心依赖列表
- 检测构建/运行命令(从 Makefile、package.json scripts、README 中提取)
输出格式:
## 结构扫描结果
### 目录结构
{两层深度的目录树,标注各目录用途}
### 技术栈
- 语言:{检测到的编程语言}
- 框架:{检测到的框架}
- 包管理:{包管理工具}
- 构建工具:{构建系统}
### 核心依赖
| 依赖 | 版本 | 用途 |
|------|------|------|
### 构建/运行命令
- 安装:{命令}
- 运行:{命令}
- 测试:{命令}
代码扫描模式
当任务包含"代码扫描"时:
- 使用 SemanticSearch 识别核心模块和入口文件
- 搜索 API 端点定义(路由、handler)
- 识别架构模式(MVC、微服务、单体等)
- 查找关键类、函数和配置
输出格式:
## 代码扫描结果
### 核心模块
| 模块 | 路径 | 职责 |
|------|------|------|
### 架构模式
{识别到的架构风格和数据流}
### API/接口
| 端点/接口 | 方法 | 文件 |
|-----------|------|------|
### 关键文件索引
| 文件 | 用途 | 重要度 |
|------|------|--------|
历史扫描模式
当任务包含"历史扫描"时:
- 运行
git log --oneline -20获取最近提交 - 运行
git branch -a获取分支信息 - 运行
git diff --stat HEAD~5..HEAD获取最近变更 - 使用 Grep 统计 TODO、FIXME、HACK 等标记
输出格式:
## 历史扫描结果
### 最近提交
{最近 20 条提交摘要}
### 分支状态
- 当前分支:{branch}
- 活跃分支:{list}
### 最近变更热区
{最近频繁修改的文件和模块}
### 待办事项
| 类型 | 数量 | 示例位置 |
|------|------|----------|
| TODO | {n} | {file:line} |
| FIXME | {n} | {file:line} |
文档扫描模式
当任务包含"文档扫描"时:
- 读取 README(如果存在)
- 扫描 docs/ 目录
- 检查是否有 API 文档、变更日志
- 检测代码中的注释密度和文档字符串
输出格式:
## 文档扫描结果
### README 摘要
{README 的核心内容摘要}
### 文档列表
| 文档 | 路径 | 内容概述 |
|------|------|----------|
### 代码文档覆盖
{注释和文档字符串的大致覆盖情况}
### 代码规范
{从代码中推断出的命名风格、格式化规则等}
质量标准:
- 输出必须精练,避免冗余
- 文件路径必须准确
- 不确定的信息标注"[待确认]"
- 控制每个扫描模式的输出在 300 行以内
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.
- 2d ago First seen · 143 lines · 1 tokens per session scan A b74098a6ecc3
scanner is an agent published in the GitHub repository povli/AgentGOD-oss (6 stars, last pushed 5mo ago), licensed MIT. It adds 1 tokens to every session and 1,071 once invoked, about $0.0000 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 2026-08-31.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.