Resume work from handoff document with context analysis and validation
You are tasked with resuming work from a handoff document through an interactive process. These handoffs contain critical context, learnings, and next steps from previous work sessions that need to be understood and continued.
When this command is invoked:
If the path to a handoff document was provided:
thoughts/shared/plans or thoughts/shared/research. do NOT use a sub-agent to read these critical files.If a ticket number (like ENG-XXXX) was provided:
thoughts/shared/handoffs/ENG-XXXX where ENG-XXXX is the ticket number. e.g. for ENG-2124 the handoffs would be in thoughts/shared/handoffs/ENG-2124/. List this directory's contents.YYYY-MM-DD_HH-MM-SS in 24-hour time format), proceed with the most recent handoff document.thoughts/shared/plans or thoughts/shared/research; do NOT use a sub-agent to read these critical files.If no parameters provided, respond with:
I'll help you resume work from a handoff document. Let me find the available handoffs.
Which handoff would you like to resume from?
Tip: You can invoke this command directly with a handoff path: `/resume_handoff `thoughts/shared/handoffs/ENG-XXXX/YYYY-MM-DD_HH-MM-SS_ENG-XXXX_description.md`
or using a ticket number to resume from the most recent handoff for that ticket: `/resume_handoff ENG-XXXX`
Then wait for the user's input.
Read handoff document completely:
Spawn focused research tasks: Based on the handoff content, spawn parallel research tasks to verify current state:
Task 1 - Gather artifact context:
Read all artifacts mentioned in the handoff.
1. Read feature documents listed in "Artifacts"
2. Read implementation plans referenced
3. Read any research documents mentioned
4. Extract key requirements and decisions
Use tools: Read
Return: Summary of artifact contents and key decisions
Wait for ALL sub-tasks to complete before proceeding
Read critical files identified:
Present comprehensive analysis:
I've analyzed the handoff from [date] by [researcher]. Here's the current situation:
**Original Tasks:**
- [Task 1]: [Status from handoff] → [Current verification]
- [Task 2]: [Status from handoff] → [Current verification]
**Key Learnings Validated:**
- [Learning with file:line reference] - [Still valid/Changed]
- [Pattern discovered] - [Still applicable/Modified]
**Recent Changes Status:**
- [Change 1] - [Verified present/Missing/Modified]
- [Change 2] - [Verified present/Missing/Modified]
**Artifacts Reviewed:**
- [Document 1]: [Key takeaway]
- [Document 2]: [Key takeaway]
**Recommended Next Actions:**
Based on the handoff's action items and current state:
1. [Most logical next step based on handoff]
2. [Second priority action]
3. [Additional tasks discovered]
**Potential Issues Identified:**
- [Any conflicts or regressions found]
- [Missing dependencies or broken code]
Shall I proceed with [recommended action 1], or would you like to adjust the approach?
Get confirmation before proceeding
Use TodoWrite to create task list:
Present the plan:
I've created a task list based on the handoff and current analysis:
[Show todo list]
Ready to begin with the first task: [task description]?
CRITICAL: Do NOT implement directly. Always spawn via Task tool.
Analyze task type and select specialist agent:
Leads (can spawn workers):
| Agent | Domain | Use For |
|---|---|---|
kraken | implement | Large features, new systems, major components |
architect | plan | Feature design, system architecture, implementation planning |
phoenix | plan | Refactoring plans, migrations, codebase restructuring |
herald | deploy | Releases, deployments, publishing |
maestro | orchestrate | Complex multi-agent workflows |
Workers (focused specialists):
| Agent | Domain | Use For |
|---|---|---|
spark | implement | Quick fixes, patches, minor tweaks |
scribe | document | Documentation, guides, explanations |
sleuth | debug | Bug investigation, tracing, root cause analysis |
aegis | debug | Security audits, vulnerability scanning |
profiler | debug | Performance optimization, bottleneck analysis |
arbiter | validate | Unit tests |
atlas | validate | E2E/integration tests |
oracle | research | External docs, best practices, how-to |
scout | research | Codebase exploration, finding existing code |
pathfinder | research | Repository structure analysis |
plan-reviewer | review | Feature plan review, design validation |
plan-reviewer | review | Migration review, refactoring validation |
chronicler | session | Session analysis, history summaries |
Spawn the specialist via Task tool:
Use Task tool with:
- subagent_type: [selected agent from above]
- prompt: [task description + relevant handoff context + learnings]
Include handoff context in the prompt:
Wait for agent completion, then proceed to next task
Be Thorough in Analysis:
Be Interactive:
Leverage Handoff Wisdom:
Track Continuity:
Validate Before Acting:
User: /resume_handoff specification/feature/handoffs/handoff-0.md
Assistant: Let me read and analyze that handoff document...
[Reads handoff completely]
[Spawns research tasks]
[Waits for completion]
[Reads identified files]
I've analyzed the handoff from [date]. Here's the current situation...
[Presents analysis]
Shall I proceed with implementing the webhook validation fix, or would you like to adjust the approach?
User: Yes, proceed with the webhook validation
Assistant: This is a bugfix task, so I'll route to the `spark` agent.
[Uses Task tool with subagent_type="spark" and prompt containing:
- The webhook validation fix task
- Key learnings from handoff
- Relevant file:line references
- Patterns to follow]
[Waits for spark agent to complete]
The spark agent has completed the webhook validation fix. Moving to the next task...