Borrowing it
Nothing to install: this file belongs to 222wcnm/BiliStalkerMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/222wcnm/BiliStalkerMCP/main/AGENTS.mdgit clone --depth 1 https://github.com/222wcnm/BiliStalkerMCPWrote 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/instructions/222wcnm/bilistalkermcp/agents-md)<a href="https://agentmods.dev/instructions/222wcnm/bilistalkermcp/agents-md"><img src="https://agentmods.dev/badge/instructions/222wcnm/bilistalkermcp/agents-md/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/instructions/222wcnm/bilistalkermcp/agents-md"><img src="https://agentmods.dev/badge/instructions/222wcnm/bilistalkermcp/agents-md.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 | $0.00882 | $0.00882 |
| Opus 5.5 | $0.00353 | $0.00353 |
| Sonnet 5.5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
BiliStalkerMCP AGENTS.md 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 today.
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
BiliStalkerMCP 项目规范
1. 核心理念:以用户为中心的数据采集
BiliStalkerMCP 为 AI 模型提供专注、深入的 B 站数据采集能力。开发工作应遵循以下原则。
1.1. 用户焦点原则
- 定位:围绕特定 B 站用户及其相关内容获取数据,帮助建立有依据的用户画像和内容理解。优先提高信息的深度与完整性。
- 功能边界:新增功能应服务于定位目标用户、了解该用户及分析相关内容。用户查找可以作为确定目标的入口;平台级的内容搜索、发现和推荐不属于本项目范围。
1.2. 只读操作原则
- 业务工具:只读取 B 站数据,不提供点赞、发表评论、发布内容、关注等改变账号或内容状态的功能。
- 凭据维护:凭据初始化与刷新可以执行必要的鉴权请求和本地凭据写入。维护凭据时应保护秘密值,并保证写入失败后能够安全恢复。
1.3. 数据时效性与准确性原则
- 数据质量:以准确、完整且具有明确时间含义的数据支持分析。缓存应具有合理的有效期,避免把过期结果当作实时状态。
- 结果表达:返回利于机器解析、结构稳定且有文档说明的数据。获取失败、部分成功、分页未取完或内容截断时,应明确表达结果的范围,不将缺失误报为不存在。
2. 开发准则
- 理解现状:修改相关功能前,检查当前代码、工具输入输出约定,以及所用 MCP、FastMCP 和 Bilibili API 的实际行为。
- 信息获取:需要补充依据时,使用可用的文档、源码、社区反馈和实际验证;区分已经验证的事实与推测。
- 验证范围:根据改动选择相关检查。涉及数据采集和解析时,使用有代表性的输入验证完整性与错误处理;不以本机通过代替其他环境的验证。
3. 运行环境与命令示例
- 跨平台:支持 Windows 和 Linux。共享代码、配置模板与文档不应依赖开发者的盘符、用户名、目录布局或本机代理端口;需要的路径和网络配置由运行环境提供。
- 终端语法:普通命令尽量通用。环境变量、管道和文件读取等存在终端差异时,分别提供 Bash 与 PowerShell 写法,并标明适用环境。
- 环境配置:明确路径相对于哪个工作目录解析、环境变量由哪个进程读取。凭据、本机配置和缓存不纳入版本控制或发布产物。
4. 文档标准
- README:
README.md与README_zh.md保持简洁,重点说明核心功能、配置和运行方法;版本历史放在发布记录中。 - 一致性:行为变更时同步相关文档。示例应能按说明替换配置后使用,避免把个人开发环境写成项目要求。
5. 核心功能开发注意事项
5.1. 图文动态解析
- 问题背景:项目早期曾出现上游库返回的图文动态无法直接取得完整正文、导致信息丢失的问题。不同动态结构需要对应的解析处理。
- 当前实现:动态获取与分页主要位于
bili_stalker_mcp/services/dynamic_service.py,内容解析主要位于bili_stalker_mcp/parsers/dynamic_parser.py。 - 回归要求:修改动态获取、过滤或解析时,验证受影响类型的正文、图片、转发原文及分页行为,确保已有内容不会因上游结构变化或字段精简而丢失。
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.
- today First seen · 46 lines · 882 tokens per session scan A bf124c6b96cc
BiliStalkerMCP AGENTS.md is an instructions file published in the GitHub repository 222wcnm/BiliStalkerMCP (11 stars, last pushed yesterday), licensed MIT. It adds 882 tokens to every session, about $0.0035 per session on Opus 5.5. 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 2026-11-07.
BiliStalkerMCP AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| BiliStalkerMCP AGENTS.md222wcnm/BiliStalkerMCP | Instructions file | 11 | yesterday | MIT | A | 882 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |