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 commands/funiq-lab/your-mind/collectgit clone --depth 1 https://github.com/funiq-lab/your-mindWhat 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 | $0.00011 | $0.01173 |
| Opus 5 | $0.00005 | $0.00587 |
| Sonnet 5 | $0.00002 | $0.00235 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade A, and why
collect 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
资讯收集命令
用户提供了一条资讯，请按以下步骤处理。
输入解析
用户输入可能包含以下元素（灵活组合）：
| 元素 | 识别方式 | 必需性 |
|---|---|---|
| 网址 | 以 http:// 或 https:// 开头 | 可选 |
| 内容 | 文字描述（无网址时必需） | 条件必需 |
| 感想 | 用户的评论/思考 | 必需 |
| 标签 | 以 # 开头的词 | 可选 |
处理步骤
1. 解析输入
从用户消息中提取：
- 网址：如有 URL，提取出来
- 标签：如有 #开头 的词，提取为标签
- 内容与感想：剩余文字，根据语义判断哪部分是内容描述，哪部分是个人感想
2. 获取内容（如有网址）
如果用户提供了网址，按以下顺序尝试获取内容：
方式一：WebFetch（首选）
使用 WebFetch 获取：
- 文章标题
- 主要内容摘要（3-5 个要点）
方式二：Playwright（备选）
如果 WebFetch 失败（返回错误、无法访问、内容为空），使用 Playwright 模拟浏览器访问：
1. 使用 mcp__playwright__browser_navigate 打开网址
2. 等待页面加载完成
3. 使用 mcp__playwright__browser_snapshot 获取页面内容
4. 从快照中提取标题和主要内容
5. 使用 mcp__playwright__browser_close 关闭浏览器
常见需要 Playwright 的网站：
- X/Twitter (x.com, twitter.com)
- 需要登录的社交媒体
- 动态加载内容的 SPA 网站
- 有反爬虫机制的网站
方式三：用户描述（兜底）
如果以上方式都失败，使用用户提供的内容描述作为摘要。
3. 判断来源类型
根据输入判断来源类型：
- 有 URL →
网络文章 - 提到书籍/阅读 →
书籍摘录 - 提到播客/视频/听 →
播客/视频 - 提到聊天/对话/朋友说 →
对话记录 - 其他 →
个人观察
4. 智能打标签
如果用户没有提供标签，根据内容智能生成 2-4 个标签：
常用标签参考：
- 技术：
#AI#编程#产品#工具#开源 - 商业：
#金融#创业#投资#商业模式#市场 - 成长：
#思维#效率#习惯#认知#学习 - 生活：
#健康#阅读#旅行#生活方式
如果用户提供了标签，可以在此基础上补充建议（但以用户指定的为主）。
5. 确定归档文件
计算当前日期所属的周（周一到周日）：
- 文件名格式：
YYYYMMDD-YYYYMMDD.md - 文件路径：
news/YYYYMMDD-YYYYMMDD.md
6. 写入资讯
有链接格式：
## [标题](URL)
**标签**：#标签1 #标签2
**来源**：网络文章
**收录时间**：YYYY-MM-DD HH:mm
### 内容摘要
> 要点1
> 要点2
> 要点3
### 个人感想
{用户的感想}
---
无链接格式：
## 标题（根据内容生成简短标题）
**标签**：#标签1 #标签2
**来源**：{来源类型}
**收录时间**：YYYY-MM-DD HH:mm
### 内容
{用户提供的内容}
### 个人感想
{用户的感想}
---
7. 更新标签索引
检查 news/tags.md 是否存在：
- 不存在则创建
- 存在则更新
标签索引格式：
# 标签索引
## #AI
- [[20251223-20251229#标题1]]
- [[20251223-20251229#标题2]]
## #投资
- [[20251223-20251229#标题3]]
8. 确认反馈
完成后告知用户：
- 资讯标题
- 归档文件
- 应用的标签
- 简短概述（如从网页获取了内容）
- 内容获取方式（WebFetch / Playwright / 用户描述）
注意事项
- 周文件不存在时，先创建并添加头部
- 新条目追加到文件末尾
- 标签索引按字母/拼音排序
- 尊重用户指定的标签，智能标签为补充
- Playwright 访问后记得关闭浏览器，避免资源占用
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 · 165 lines · 11 tokens per session scan A 407072d166fc
collect is a command published in the GitHub repository funiq-lab/your-mind (11 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 1,173 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.