cursor-agent-tracking
A repository that provides a structured system for maintaining context and tracking changes in Cursor's AGENT mode conversations through template files, enabling better continuity and organization of AI interactions.
Install / Use
npx skills add TechMitten/cursor-agent-trackingInstalls into whichever agent you are using.
.cursorrules
Cursor IDE rules (legacy)
Quality Score
Category
Content & MediaSupported Platforms
Skill content
View source on GitHubCursor Agent History Tracking System
Overview
A simple system to maintain context and track changes in conversations with Cursor when it's in AGENT mode, ensuring continuity even if the AI 'forgets' previous interactions. This workaround isn't necessary for regular chat mode, as Cursor implements native tracking.
Quick Start
-
Copy all
.mdfiles from thetemplatesdirectory into your project's root directory:CHANGELOG.mdPROJECT_SCOPE.mdPROMPT.md
-
Begin every new chat with the AI by copying the contents of
PROMPT.md- This ensures the AI has proper context about your project
- The AI will maintain consistent formatting for changes
- Track all significant changes in
CHANGELOG.md - Keep
PROJECT_SCOPE.mdupdated with current status
File Purposes
PROMPT.md: Your template for starting each new chat sessionCHANGELOG.md: Tracks all significant changes to your projectPROJECT_SCOPE.md: Maintains current project status and goals
Best Practices
- Always start new chats with the
PROMPT.mdtemplate (this means every time you click the + symbol) - Update
CHANGELOG.mdafter significant changes - Keep
PROJECT_SCOPE.mdcurrent - Include relevant file paths in your prompts
- Save important code snippets and explanations
Template Maintenance
Feel free to modify the templates to better suit your specific needs while maintaining the core structure for consistency.
Need Help?
Refer to the individual template files for detailed formatting and usage instructions.
Related Skills
siyuan
46.4kAn open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间,让人与智能体在此协作
humanizer
50.9kAgent skill that removes signs of AI-generated writing from text
oh-story-claudecode
7.0kClaude Code / Codex / OpenCode agent skills for writing Chinese web novels (网文): 扫榜、拆文、写作、去AI味、封面全流程,长篇短篇都支持 | 13 skills for novel writing and long-form fiction with file-based continuity tracking. MIT.
iPolloWork
6.5kEnterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.
Security Score
Audited on Jan 1, 2025
