

Also from Kynth Studios


Also from Kynth Studios


Also from Kynth Studios
123456789# You MUST use the `new_task` tool: Task Handoff Strategy Guide1011**⚠️ CRITICAL INSTRUCTIONS - YOU MUST FOLLOW THESE GUIDELINES ⚠️**1213This guide provides **MANDATORY** instructions for effectively breaking down complex tasks and implementing a smooth handoff process between tasks. You **MUST** follow these guidelines to ensure continuity, context preservation, and efficient task completion.1415## ⚠️ CONTEXT WINDOW MONITORING - MANDATORY ACTION REQUIRED ⚠️1617You **MUST** monitor the context window usage displayed in the environment details. When usage exceeds 50% of the available context window, you **MUST** initiate a task handoff using the `new_task` tool.1819Example of context window usage over 50% with a 200K context window:2021\`\`\`text22# Context Window Usage23105,000 / 200,000 tokens (53%)24Model: anthropic/claude-3.7-sonnet (200K context window)25\`\`\`2627**IMPORTANT**: When you see context window usage at or above 50%, you MUST:281. Complete your current logical step292. Use the `ask_followup_question` tool to offer creating a new task303. If approved, use the `new_task` tool with comprehensive handoff instructions3132## Task Breakdown in Plan Mode - REQUIRED PROCESS3334Plan Mode is specifically designed for analyzing complex tasks and breaking them into manageable subtasks. When in Plan Mode, you **MUST**:3536### 1. Initial Task Analysis - REQUIRED3738- **MUST** begin by thoroughly understanding the full scope of the user's request39- **MUST** identify all major components and dependencies of the task40- **MUST** consider potential challenges, edge cases, and prerequisites4142### 2. Strategic Task Decomposition - REQUIRED4344- **MUST** break the overall task into logical, discrete subtasks45- **MUST** prioritize subtasks based on dependencies (what must be completed first)46- **MUST** aim for subtasks that can be completed within a single session (15-30 minutes of work)47- **MUST** consider natural breaking points where context switching makes sense4849### 3. Creating a Task Roadmap - REQUIRED5051- **MUST** present a clear, numbered list of subtasks to the user52- **MUST** explain dependencies between subtasks53- **MUST** provide time estimates for each subtask when possible54- **MUST** use Mermaid diagrams to visualize task flow and dependencies when helpful5556\`\`\`mermaid57graph TD58 A[Main Task] --> B[Subtask 1: Setup]59 A --> C[Subtask 2: Core Implementation]60 A --> D[Subtask 3: Testing]61 A --> E[Subtask 4: Documentation]62 B --> C63 C --> D64\`\`\`6566### 4. Getting User Approval - REQUIRED6768- **MUST** ask for user feedback on the proposed task breakdown69- **MUST** adjust the plan based on user priorities or additional requirements70- **MUST** confirm which subtask to begin with71- **MUST** request the user to toggle to Act Mode when ready to implement7273## Task Implementation and Handoff Process - MANDATORY PROCEDURES7475When implementing tasks in Act Mode, you **MUST** follow these guidelines for effective task handoff:7677### 1. Focused Implementation - REQUIRED7879- **MUST** focus on completing the current subtask fully80- **MUST** document progress clearly through comments and commit messages81- **MUST** create checkpoints at logical completion points8283### 2. Recognizing Completion Points - CRITICAL8485You **MUST** identify natural handoff points when:86- The current subtask is fully completed87- You've reached a logical stopping point in a larger subtask88- The implementation is taking longer than expected and can be continued later89- The task scope has expanded beyond the original plan90- **CRITICAL**: The context window usage exceeds 50% (e.g., 100,000+ tokens for a 200K context window)9192### 3. Initiating the Handoff Process - MANDATORY ACTION9394When you've reached a completion point, you **MUST**:95961. Summarize what has been accomplished so far972. Clearly state what remains to be done983. **MANDATORY**: Use the `ask_followup_question` tool to offer creating a new task:99100\`\`\`xml101<ask_followup_question>102<question>I've completed [specific accomplishment]. Would you like me to create a new task to continue with [remaining work]?</question>103<options>["Yes, create a new task", "No, continue in this session", "Let me think about it"]</options>104</ask_followup_question>105\`\`\`106107### 4. Creating a New Task with Context - REQUIRED ACTION108109If the user agrees to create a new task, you **MUST** use the `new_task` tool with comprehensive handoff instructions:110111\`\`\`xml112<new_task>113<context>114# Task Continuation: [Brief Task Title]115116## Completed Work117- [Detailed list of completed items]118- [Include specific files modified/created]119- [Note any important decisions made]120121## Current State122- [Description of the current state of the project]123- [Any running processes or environment setup]124- [Key files and their current state]125126## Next Steps127- [Detailed list of remaining tasks]128- [Specific implementation details to address]129- [Any known challenges to be aware of]130131## Reference Information132- [Links to relevant documentation]133- [Important code snippets or patterns to follow]134- [Any user preferences noted during the current session]135136Please continue the implementation by [specific next action].137</context>138</new_task>139\`\`\`140141### 5. Detailed Context Transfer - MANDATORY COMPONENTS142143When creating a new task, you **MUST** always include:144145#### Project Context - REQUIRED146- **MUST** include the overall goal and purpose of the project147- **MUST** include key architectural decisions and patterns148- **MUST** include technology stack and dependencies149150#### Implementation Details - REQUIRED151- **MUST** list files created or modified in the current session152- **MUST** describe specific functions, classes, or components implemented153- **MUST** explain design patterns being followed154- **MUST** outline testing approach155156#### Progress Tracking - REQUIRED157- **MUST** provide checklist of completed items158- **MUST** provide checklist of remaining items159- **MUST** note any blockers or challenges encountered160161#### User Preferences - REQUIRED162- **MUST** note coding style preferences mentioned by the user163- **MUST** document specific approaches requested by the user164- **MUST** highlight priority areas identified by the user165166## Best Practices for Effective Handoffs - MANDATORY GUIDELINES167168### 1. Maintain Continuity - REQUIRED169170- **MUST** use consistent terminology between tasks171- **MUST** reference previous decisions and their rationale172- **MUST** maintain the same architectural approach unless explicitly changing direction173174### 2. Preserve Context - REQUIRED175176- **MUST** include relevant code snippets in the handoff177- **MUST** summarize key discussions from the previous session178- **MUST** reference specific files and line numbers when applicable179180### 3. Set Clear Next Actions - REQUIRED181182- **MUST** begin the handoff with a clear, actionable next step183- **MUST** prioritize remaining tasks184- **MUST** highlight any decisions that need to be made185186### 4. Document Assumptions - REQUIRED187188- **MUST** clearly state any assumptions made during implementation189- **MUST** note areas where user input might be needed190- **MUST** identify potential alternative approaches191192### 5. Optimize for Resumability - REQUIRED193194- **MUST** structure the handoff so the next session can begin working immediately195- **MUST** include setup instructions if environment configuration is needed196- **MUST** provide a quick summary at the top for rapid context restoration197198## Example Task Handoff199200### Example #1 of an effective task handoff:201202\`\`\`xml203<new_task>204<context>205# Task Continuation: Implement User Authentication System206207## Completed Work208- Created basic Express.js server structure209- Implemented MongoDB connection and user schema210- Completed user registration endpoint with password hashing211- Added input validation using Joi212- Created initial test suite for registration endpoint213214## Current State215- Server runs successfully on port 3000216- MongoDB connection is established217- Registration endpoint (/api/users/register) is fully functional218- Test suite passes for all registration scenarios219220## Next Steps2211. Implement login endpoint (/api/users/login)222 - Use bcrypt to compare passwords223 - Generate JWT token upon successful login224 - Add proper error handling for invalid credentials2252. Create authentication middleware226 - Verify JWT tokens227 - Extract user information228 - Handle expired tokens2293. Add protected routes that require authentication2304. Implement password reset functionality231232## Reference Information233- JWT secret should be stored in .env file234- Follow the existing error handling pattern in routes/users.js235- User schema is defined in models/User.js236- Test patterns are established in tests/auth.test.js237238Please continue by implementing the login endpoint following the same patterns established in the registration endpoint.239</context>240</new_task>241\`\`\`242243### Example #2 of an ineffective task handoff:244245*(Note: The example provided in the original rules showing "YOLO MODE Implementation" seems less like a direct handoff context block and more like a general status update with future considerations. A true ineffective handoff might lack detail in 'Current State' or 'Next Steps').*246247## When to Use Task Handoffs - MANDATORY TRIGGERS248249You **MUST** initiate task handoffs in these scenarios:2502511. **CRITICAL**: When context window usage exceeds 50% (e.g., 100,000+ tokens for a 200K context window)2522. **Long-running projects** that exceed a single session2533. **Complex implementations** with multiple distinct phases2544. **When context window limitations** are approaching2555. **When switching focus areas** within a larger project2566. **When different expertise** might be beneficial for different parts of the task257258**⚠️ FINAL REMINDER - CRITICAL INSTRUCTION ⚠️**259260You **MUST** monitor the context window usage in the environment details section. When it exceeds 50% (e.g., "105,000 / 200,000 tokens (53%)"), you **MUST** proactively initiate the task handoff process using the `ask_followup_question` tool followed by the `new_task` tool. You MUST use the `new_task` tool.261262By strictly following these guidelines, you'll ensure smooth transitions between tasks, maintain project momentum, and provide the best possible experience for users working on complex, multi-session projects.263```markdown264265## User Interaction & Workflow Considerations266267* **Linear Flow:** Currently, using `new_task` creates a linear sequence. The old task ends, and the new one begins. The old task history remains accessible for backtracking.268* **User Approval:** You always have control, approving the handoff and having the chance to modify the context Cline proposes to carry forward.269* **Flexibility:** The core `new_task` tool is a flexible building block. Experiment with `.clinerules` to create workflows that best suit your needs, whether for strict context management, task decomposition, or other creative uses.270271```
One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| cline/prompts.clinerules/ai-dlc-adaptive-workflow.md · 1.2k | Cline rules | agent-behaviour | 54/100 | today | |
| cline/prompts.clinerules/audio-plugin-developer.md · 1.2k | Cline rules | styleperformancedo-notagent-behaviour | 57/100 | today | |
| cline/prompts.clinerules/ba.md · 1.2k | Cline rules | archgitagent-behaviour | 50/100 | today | |
| cline/prompts.clinerules/baby-steps.md · 1.2k | Cline rules | do-notagent-behaviour | 50/100 | today | |
| cline/prompts.clinerules/c#-guide.md · 1.2k | Cline rules | style | 27/100 | today | |
| cline/prompts.clinerules/claude-code-subagents.md · 1.2k | Cline rules | testarchdo-notagent-behaviour | 77/100 | today | |
| cline/prompts.clinerules/cline-architecture.md · 1.2k | Cline rules | archtypesapi | 54/100 | today | |
| cline/prompts.clinerules/cline-continuous-improvement-protocol.md · 1.2k | Cline rules | testgitperformance | 58/100 | today | |
| cline/prompts.clinerules/cline-for-research.md · 1.2k | Cline rules | agent-behaviour | 34/100 | today | |
| cline/prompts.clinerules/cline-for-slides.md · 1.2k | Cline rules | setupbuildstylearch+1 | 86/100 | today | |
| cline/prompts.clinerules/cline-for-webdev-ui.md · 1.2k | Cline rules | archagent-behaviour | 58/100 | today | |
| cline/prompts.clinerules/code-review.md · 1.2k | Cline rules | lint-formatgitsecurityperformance | 48/100 | today | |
| cline/prompts.clinerules/codebase-onboarding.md · 1.2k | Cline rules | lint-formatstylearchdependencies | 56/100 | today | |
| cline/prompts.clinerules/comprehensive-slide-dev-guide.md · 1.2k | Cline rules | buildarchtypesui | 62/100 | today | |
| cline/prompts.clinerules/create-documentation.md · 1.2k | Cline rules | apidocs | 44/100 | today | |
| cline/prompts.clinerules/gemini-comprehensive-software-engineering-guide.md · 1.2k | Cline rules | buildstyletesting-strategysecurity+4 | 36/100 | today | |
| cline/prompts.clinerules/general-development-rules.md · 1.2k | Cline rules | stylegitdeploymentdo-not | 73/100 | today | |
| cline/prompts.clinerules/google-apps-script-developer.md · 1.2k | Cline rules | setupstylegitsecurity+3 | 66/100 | today | |
| cline/prompts.clinerules/helm-chart-developer.md · 1.2k | Cline rules | setuplint-formatstylearch+6 | 81/100 | today | |
| cline/prompts.clinerules/mcp-development-protocol.md · 1.2k | Cline rules | setupteststyle | 73/100 | today |
A badge carrying the measured quality of the strongest agent config file in this repository, out of 100. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://rulestack.kynth.studio/configs/cline-prompts-clinerules-new-task-automation)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.