handing-off-sessions
Handing Off Sessions
Create a handoff document that lets any agent resume work cold — without access to prior conversation history.
When to create
- End of a work session with meaningful progress
- Context window approaching limits
- Switching between agents or tools
- User explicitly asks to save progress
When NOT to create
- Trivial sessions (quick questions, one-line fixes, informational queries)
- Session where no files were modified and no ongoing work exists
Storage
Save handoff documents to .agent/handoffs/ at the project root. Name files with a timestamp and brief slug: 2025-04-07-auth-middleware.md.
If the project already has an agent state directory (.claude/, .cursor/, etc.), use that instead. Create .agent/ on first use and add to .gitignore unless the team wants shared agent state.
More from beltonk/claude-code-agent-skills
coding-practices
Coding-specific practices for AI agents — scope discipline, read-before-write, simplest approach first, incremental development, verification, comment standards, security awareness, tool preferences, and shell discipline. Use when the agent is writing, editing, or reviewing code. Works alongside agentic-standards (which covers general behavior for all interactions).
4managing-memories
Covers the full memory lifecycle — when to save, what format to use, how to organize and deduplicate, how to recall relevant memories, and what to never persist. Use at natural breakpoints to capture user preferences, corrections, and project conventions, and at session start to load relevant context.
4scaffolding-projects
Provides a structured approach to starting new features or projects. Guides the agent through understanding requirements, exploring existing code, planning, incremental implementation, and verification. Use when asked to build something new — a feature, module, service, or project — to avoid jumping into code without context.
4compacting-context
Provides a structured 9-section summarization template for compressing long conversations while preserving critical details. Use when a session approaches context limits and history must be compressed without losing user intent, file changes, errors, or next steps.
4agentic-standards
Foundational behavioral standards for any AI agent — safety/reversibility framework, output quality, memory conventions, and prompt injection defense. Applies to all agent interactions including chat, analysis, writing, debugging, and coding. Use when setting up an agent, onboarding to a new project, or when behavioral baseline guidance is needed. For coding-specific rules, also load coding-practices.
4receiving-code-review
Enforces rigorous handling of code review feedback. Classifies comments by severity, verifies claims independently, prevents blind implementation of incorrect suggestions, and handles contradictory reviews. Use when receiving review comments on a pull request or code change.
1