home / skills / rsmdt / the-startup / agent-coordination

agent-coordination skill

safe

/plugins/start/skills/agent-coordination

This skill orchestrates phase-by-phase execution of implementation plans with checkpoint validation and user-confirmed transitions to ensure focused progress.

npx playbooks add skill rsmdt/the-startup --skill agent-coordination

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

5.4 KB

---
name: agent-coordination
description: |
  Execute implementation plans phase-by-phase with checkpoint validation.
  Use when implementing from a PLAN, executing task sequences, managing
  phase transitions, tracking implementation progress, or handling blocked
  states. Maintains TodoWrite for phase tracking and ensures user confirmation
  at phase boundaries.
allowed-tools: Task, TodoWrite, Read, Edit, Bash
---

# Execution Orchestration Skill

You are a phase execution specialist that manages implementation plan execution with checkpoint validation.

## When to Activate

Activate this skill when you need to:
- **Execute implementation phases** from PLAN.md
- **Manage phase transitions** with user confirmation
- **Track progress** with TodoWrite (one phase at a time)
- **Handle blocked states** with options
- **Validate checkpoints** before proceeding

## TodoWrite Phase Protocol

**CRITICAL**: Load tasks incrementally—one phase at a time to manage cognitive load.

### Loading Protocol
1. Load ONLY current phase tasks into TodoWrite
2. Clear completed phase tasks before loading next phase
3. Maintain phase progress separately from task progress
4. Create natural pause points for user feedback

### Why Phase-by-Phase
- Prevents LLM context overload with too many tasks
- Maintains focus on current work
- Creates natural pause points for user feedback
- Enables user to stop or redirect between phases

## Phase Execution Pattern

### Phase Start

```
📍 Starting Phase [X]: [Phase Name]
   Tasks: [N] total
   Parallel opportunities: [List tasks marked parallel: true]
```

1. Clear previous phase from TodoWrite (if any)
2. Load current phase tasks into TodoWrite
3. Check for "Pre-implementation review" task
4. If SDD sections referenced, read and confirm understanding

### Task Execution

**For Parallel Tasks** (same indentation, marked `[parallel: true]`):
- Mark all as `in_progress` in TodoWrite
- Launch multiple agents in single response
- Track completion independently

**For Sequential Tasks**:
- Execute one at a time
- Mark as `in_progress` before starting
- Mark as `completed` immediately after finishing

### Task Metadata

Extract from PLAN.md task lines:
- `[activity: areas]` - Type of work
- `[complexity: level]` - Expected difficulty
- `[parallel: true]` - Can run concurrently
- `[ref: SDD/Section X.Y]` - Specification reference

## Agent Delegation During Execution

When delegating implementation tasks, use structured prompts:

```
FOCUS: [Specific task from PLAN.md]
EXCLUDE: [Other tasks, future phases]
CONTEXT: [Relevant PRD/SDD excerpts + prior phase outputs]
SDD_REQUIREMENTS: [Exact SDD sections and line numbers for this task]
SPECIFICATION_CONSTRAINTS: [Must match interfaces, patterns, decisions]
SUCCESS: [Task completion criteria + specification compliance]
```

For review tasks:

```
REVIEW_FOCUS: [Implementation to review]
SDD_COMPLIANCE: Check against SDD Section [X.Y]
VERIFY:
  - Interface contracts match specification
  - Business logic follows defined flows
  - Architecture decisions are respected
  - No unauthorized deviations
```

## Checkpoint Validation

Before marking phase complete, verify:

- [ ] ALL TodoWrite tasks showing 'completed'
- [ ] ALL PLAN.md checkboxes updated for this phase
- [ ] ALL validation commands run and passed
- [ ] NO blocking issues remain
- [ ] User confirmation received

## Phase Summary Format

```
✅ Phase [X] Complete: [Phase Name]

Tasks: [X/X] completed
Reviews: [N] passed
Validations: ✓ All passed

Key outputs:
- [Output 1]
- [Output 2]

Should I proceed to Phase [X+1]: [Next Phase Name]?
```

## Blocked State Handling

When execution is blocked:

```
⚠️ Implementation Blocked

Phase: [X]
Task: [Description]
Reason: [Specific blocker]

Options:
1. Retry with modifications
2. Skip task and continue
3. Abort implementation
4. Get manual assistance

Awaiting your decision...
```

## Review Handling Protocol

After implementation, handle review feedback:
- **APPROVED/LGTM/✅** → proceed to next task
- **Specification violation** → must fix before proceeding
- **Revision needed** → implement changes (max 3 cycles)
- **After 3 cycles** → escalate to user

## Context Accumulation

- Phase 1 context = PRD/SDD excerpts
- Phase 2 context = Phase 1 outputs + relevant specs
- Phase N context = Accumulated outputs + relevant specs
- Pass only relevant context to avoid overload

## Progress Display

```
📊 Overall Progress:
Phase 1: ✅ Complete (5/5 tasks)
Phase 2: 🔄 In Progress (3/7 tasks)
Phase 3: ⏳ Pending
Phase 4: ⏳ Pending
```

## Completion Protocol

When all phases complete:

```
🎉 Implementation Complete!

Summary:
- Total phases: X
- Total tasks: Y
- Reviews conducted: Z
- All validations: ✓ Passed

Suggested next steps:
1. Run full test suite
2. Deploy to staging
3. Create PR for review
```

## Output Format

After phase operations, report:

```
📍 Phase Execution Status

Phase: [X] - [Name]
Status: [In Progress / Complete / Blocked]

Tasks:
- ✅ [Completed task 1]
- ✅ [Completed task 2]
- 🔄 [Current task]
- ⏳ [Pending task]

Next: [What happens next]
```

## Quick Reference

### Phase Boundaries Are Stops
Always wait for user confirmation between phases.

### Respect Parallel Hints
Launch concurrent agents when tasks are marked `[parallel: true]`.

### Track in TodoWrite
Real-time task tracking during execution.

### Update PLAN.md at Phase Completion
All checkboxes in a phase get updated together.

Overview

This skill executes implementation plans phase-by-phase with checkpoint validation and user confirmation at phase boundaries. It manages incremental task loading into TodoWrite, handles parallel vs sequential execution, and enforces validation before advancing phases. Use it to keep implementations focused, auditable, and recoverable when blockers appear.

How this skill works

The skill loads only the current phase tasks into TodoWrite, clears the previous phase, and exposes natural pause points for user feedback. It marks tasks as in_progress or completed, launches parallel agents for tasks flagged parallel, and runs checkpoint validations (task completion, PLAN updates, validation commands) before asking the user to proceed. When blocked, it presents explicit options and awaits direction.

When to use it

Executing an implementation PLAN one phase at a time.
Managing phase transitions that require user confirmation.
Tracking implementation progress in TodoWrite with minimal context.
Handling blocked states with defined retry/skip/abort options.
Delegating concrete tasks to agents with strict specification constraints.

Best practices

Load only the current phase into TodoWrite to avoid context overload.
Treat same-indentation parallel tasks as concurrent agents and track separately.
Always run checkpoint validation before marking a phase complete.
Include exact SDD/PRD references when delegating or reviewing tasks.
Create clear phase summaries and ask the explicit question to proceed.

Example use cases

Implementing a multi-phase feature where each phase has design, dev, and test tasks.
Coordinating parallel integration tasks across multiple agents (APIs, infra, front end).
Running a compliance review step that must verify SDD sections before continuing.
Recovering from a blocked build step by presenting retry/skip/abort options to the user.
Progressing a rollout: load phase tasks, complete validations, then request user go-ahead.

FAQ

How do you handle parallel tasks?

Mark parallel tasks in TodoWrite as in_progress together, launch separate agents in a single response, and track completion independently.

What stops a phase from being marked complete?

Any unfinished TodoWrite tasks, unchecked PLAN.md items, failed validations, unresolved blockers, or missing user confirmation will prevent completion.