session-handoffWHAT: Create comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves long-running agent context exhaustion problem. WHEN: (1) User requests handoff/memory/context save, (2) Context window approaches capacity, (3) Major task milestone completed, (4) Work session ending, (5) Resuming work with existing handoff. KEYWORDS: "save state", "create handoff", "context is full", "I need to pause", "resume from", "continue where we left off", "load handoff", "save progress", "session transfer", "hand off"
Install via ClawdBot CLI:
clawdbot install wpank/session-handoffCreate handoff documents that enable fresh agents to continue work seamlessly.
Creating a handoff? User wants to save state, pause work, or context is full.
ā Follow CREATE Workflow
Resuming from a handoff? User wants to continue previous work or load context.
ā Follow RESUME Workflow
Proactive suggestion? After substantial work (5+ file edits, complex debugging, major decisions):
"Consider creating a handoff document to preserve this context. Say 'create handoff' when ready."
Run the smart scaffold script:
python scripts/create_handoff.py [task-slug]For continuation handoffs (linking to previous work):
python scripts/create_handoff.py "auth-part-2" --continues-from 2024-01-15-auth.mdThe script creates .claude/handoffs/ directory and generates a timestamped file with pre-filled metadata (timestamp, project path, git branch, recent commits, modified files).
Open the generated file and fill all [TODO: ...] sections. Prioritize:
See references/handoff-template.md for full structure.
python scripts/validate_handoff.py <handoff-file>Checks:
[TODO: ...] placeholders remainingDo not finalize handoffs with secrets detected or score below 70.
Report to user:
python scripts/list_handoffs.pypython scripts/check_staleness.py <handoff-file>Staleness levels:
Read the handoff document completely. If part of a chain, also read the previous handoff.
Follow references/resume-checklist.md:
Start with "Immediate Next Steps" item #1.
Reference as you work:
For long-running projects, chain handoffs to maintain context lineage:
handoff-1.md (initial work)
ā
handoff-2.md --continues-from handoff-1.md
ā
handoff-3.md --continues-from handoff-2.mdWhen resuming from a chain, read the most recent handoff first, then reference predecessors as needed.
Location: .claude/handoffs/
Naming: YYYY-MM-DD-HHMMSS-[slug].md
Good handoffs have:
Generated Mar 1, 2026
A development team uses the skill to save context after completing a major feature or fixing a complex bug, ensuring the next agent can seamlessly continue testing or deployment. This prevents context loss during shift changes or when switching between tasks, maintaining productivity in agile workflows.
A support agent employs the skill to document a challenging customer issue before transferring it to a specialist or higher-tier team. The handoff captures troubleshooting steps, customer sentiment, and pending actions, enabling the next agent to resolve the case without repetition.
A researcher utilizes the skill to pause data analysis or literature review sessions, saving key findings, hypotheses, and next steps. This allows collaborators or future sessions to resume work accurately, preserving intellectual context in academic or R&D settings.
A content team applies the skill to save progress on long-form articles or multimedia projects, documenting outlines, sources, and editing notes. This enables different writers or editors to continue production without losing creative direction or consistency.
An IT specialist uses the skill during extended outage resolutions to hand off context between shifts, detailing root cause analysis, mitigation steps, and pending verifications. This ensures incident response continuity and reduces downtime in critical operations.
Offer the skill as part of a premium AI agent platform with tiered pricing based on handoff volume and validation features. Revenue comes from monthly subscriptions, targeting enterprises needing reliable context management for distributed teams.
Provide the skill as a customized solution integrated into client workflows, with revenue from one-time setup fees and ongoing support contracts. This model serves industries like software development or customer support seeking tailored handoff processes.
Distribute the skill as a free open-source tool with basic features, monetizing through paid upgrades for advanced validation, analytics, and team collaboration. Revenue is generated from upsells to professional or enterprise tiers.
š¬ Integration Tip
Integrate the skill into existing project management tools like Jira or Slack to trigger handoffs automatically at milestones, reducing manual effort and ensuring consistency across teams.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection