msd-core/get-shit-done/workflows/execute-phase.md

Execute all plans in a phase using wave-based parallel execution. Orchestrator stays lean by delegating plan execution to subagents.

<core_principle> The orchestrator's job is coordination, not execution. Each subagent loads the full execute-plan context itself. Orchestrator discovers plans, analyzes dependencies, groups into waves, spawns agents, handles checkpoints, collects results. </core_principle>

Confirm phase exists and has plans:

PHASE_DIR=$(ls -d .planning/phases/${PHASE_ARG}* 2>/dev/null | head -1)
if [ -z "$PHASE_DIR" ]; then
  echo "ERROR: No phase directory matching '${PHASE_ARG}'"
  exit 1
fi

PLAN_COUNT=$(ls -1 "$PHASE_DIR"/*-PLAN.md 2>/dev/null | wc -l | tr -d ' ')
if [ "$PLAN_COUNT" -eq 0 ]; then
  echo "ERROR: No plans found in $PHASE_DIR"
  exit 1
fi

Report: "Found {N} plans in {phase_dir}"

List all plans and extract metadata:

# Get all plans
ls -1 "$PHASE_DIR"/*-PLAN.md 2>/dev/null | sort

# Get completed plans (have SUMMARY.md)
ls -1 "$PHASE_DIR"/*-SUMMARY.md 2>/dev/null | sort

For each plan, read frontmatter to extract:

• depends_on: [] - Plan IDs this plan requires
• files_modified: [] - Files this plan touches
• autonomous: true/false - Whether plan has checkpoints

Build plan inventory:

• Plan path
• Plan ID (e.g., "03-01")
• Dependencies
• Files modified
• Autonomous flag
• Completion status (SUMMARY exists = complete)

Skip completed plans. If all complete, report "Phase already executed" and exit.

Build dependency graph from frontmatter:

Direct dependencies:

• depends_on: ["03-01"] → this plan depends on 03-01

File conflict dependencies:

• If two plans modify same file, later plan (by number) depends on earlier

Build graph:

plan-01: {deps: [], files: [src/user.ts], autonomous: true}
plan-02: {deps: [], files: [src/product.ts], autonomous: true}
plan-03: {deps: ["plan-01"], files: [src/dashboard.tsx], autonomous: false}
plan-04: {deps: ["plan-02"], files: [src/cart.ts], autonomous: true}
plan-05: {deps: ["plan-03", "plan-04"], files: [src/checkout.ts], autonomous: true}

Group plans into execution waves based on dependencies:

Wave assignment algorithm:

1. Wave 1: All plans with no dependencies AND autonomous=true
2. Non-autonomous plans with no dependencies: execute after Wave 1, before Wave 2
3. Wave N: Plans whose dependencies are all in earlier waves

Separate checkpoint plans: Plans with autonomous: false execute in main context (not parallel subagent) to handle user interaction.

Example:

Wave 1 (parallel): [plan-01, plan-02]
Checkpoint: [plan-03] - has human-verify, runs in main context
Wave 2 (parallel): [plan-04]
Wave 3: [plan-05]

Report wave structure to user:

Execution Plan:
  Wave 1 (parallel): 03-01, 03-02
  Checkpoint: 03-03 (requires user verification)
  Wave 2 (parallel): 03-04
  Wave 3: 03-05

Total: 5 plans in 3 waves + 1 checkpoint

Execute each wave in sequence. Autonomous plans within a wave run in parallel.

For each wave:

1. Spawn all autonomous agents in wave simultaneously:

   Use Task tool with multiple parallel calls. Each agent gets prompt from subagent-task-prompt template:

   <objective>
   Execute plan {plan_number} of phase {phase_number}-{phase_name}.
   
   Commit each task atomically. Create SUMMARY.md. Update STATE.md.
   </objective>
   
   <execution_context>
   @~/.claude/get-shit-done/workflows/execute-plan.md
   @~/.claude/get-shit-done/templates/summary.md
   @~/.claude/get-shit-done/references/checkpoints.md
   @~/.claude/get-shit-done/references/tdd.md
   </execution_context>
   
   <context>
   Plan: @{plan_path}
   Project state: @.planning/STATE.md
   Config: @.planning/config.json (if exists)
   </context>
   
   <success_criteria>
   - [ ] All tasks executed
   - [ ] Each task committed individually
   - [ ] SUMMARY.md created in plan directory
   - [ ] STATE.md updated with position and decisions
   </success_criteria>
   

2. Wait for all agents in wave to complete:

   Task tool blocks until each agent finishes. All parallel agents return together.

3. Collect results from wave:

   For each completed agent:

   • Verify SUMMARY.md exists at expected path
   • Note any issues reported
   • Record completion

4. Handle failures:

   If any agent in wave fails:

   • Report which plan failed and why
   • Ask user: "Continue with remaining waves?" or "Stop execution?"
   • If continue: proceed to next wave (dependent plans may also fail)
   • If stop: exit with partial completion report

5. Execute checkpoint plans between waves:

   See <checkpoint_handling> for details.

6. Proceed to next wave

Plans with `autonomous: false` require user interaction.

Detection: Check autonomous field in frontmatter.

Execution flow for checkpoint plans:

1. Spawn agent for checkpoint plan:

   Task(prompt="{subagent-task-prompt}", subagent_type="general-purpose")
   

2. Agent runs until checkpoint:

   • Executes auto tasks normally
   • Reaches checkpoint task (e.g., type="checkpoint:human-verify")
   • Agent returns with checkpoint details in its response

3. Agent return includes:

   • Checkpoint type (human-verify, decision, human-action)
   • Checkpoint details (what-built, options, instructions)
   • Agent ID for resumption
   • Progress so far (tasks completed)

4. Orchestrator presents checkpoint to user:

   ## Checkpoint: Visual Verification Required
   
   **Plan:** 03-03 Dashboard Layout
   **Progress:** 2/3 tasks complete
   
   **What was built:**
   Responsive dashboard with sidebar navigation
   
   **Please verify:**
   1. Run: npm run dev
   2. Visit: http://localhost:3000/dashboard
   3. Desktop (>1024px): Verify sidebar left, content right
   4. Mobile (375px): Verify single column layout
   
   Type "approved" to continue, or describe issues to fix.
   

5. User responds:

   • "approved" → resume agent
   • Description of issues → resume agent with feedback

6. Resume agent:

   Task(resume="{agent_id}", prompt="User response: {user_input}")
   

7. Agent continues from checkpoint:

   • If approved: proceed to next task
   • If issues: fix and re-present checkpoint, or ask for clarification

8. Repeat until plan completes or user stops

Checkpoint in parallel context: If a plan in a parallel wave has a checkpoint:

• Spawn as normal
• Agent pauses at checkpoint and returns
• Other parallel agents may complete while waiting
• Handle checkpoint, resume agent
• Wait for all agents to finish before next wave

After all waves complete, aggregate results:

## Phase {X}: {Name} Execution Complete

**Waves executed:** {N}
**Plans completed:** {M} of {total}

### Wave Summary

| Wave | Plans | Status |
|------|-------|--------|
| 1 | plan-01, plan-02 | ✓ Complete |
| CP | plan-03 | ✓ Verified |
| 2 | plan-04 | ✓ Complete |
| 3 | plan-05 | ✓ Complete |

### Plan Details

1. **03-01**: [one-liner from SUMMARY.md]
2. **03-02**: [one-liner from SUMMARY.md]
...

### Issues Encountered
[Aggregate from all SUMMARYs, or "None"]

Update ROADMAP.md to reflect phase completion:

# Mark phase complete
# Update completion date
# Update status

Commit roadmap update:

git add .planning/ROADMAP.md
git commit -m "docs(phase-{X}): complete phase execution"

Present next steps based on milestone status:

If more phases remain:

## Next Up

**Phase {X+1}: {Name}** — {Goal}

`/gsd:plan-phase {X+1}`

<sub>`/clear` first for fresh context</sub>

If milestone complete:

MILESTONE COMPLETE!

All {N} phases executed.

`/gsd:complete-milestone`

<context_efficiency> Why this works:

Orchestrator context usage: ~10-15%

• Read plan frontmatter (small)
• Analyze dependencies (logic, no heavy reads)
• Fill template strings
• Spawn Task calls
• Collect results

Each subagent: Fresh 200k context

• Loads full execute-plan workflow
• Loads templates, references
• Executes plan with full capacity
• Creates SUMMARY, commits

No polling. Task tool blocks until completion. No TaskOutput loops.

No context bleed. Orchestrator never reads workflow internals. Just paths and results. </context_efficiency>

<failure_handling> Subagent fails mid-plan:

• SUMMARY.md won't exist
• Orchestrator detects missing SUMMARY
• Reports failure, asks user how to proceed

Dependency chain breaks:

• Wave 1 plan fails
• Wave 2 plans depending on it will likely fail
• Orchestrator can still attempt them (user choice)
• Or skip dependent plans entirely

All agents in wave fail:

• Something systemic (git issues, permissions, etc.)
• Stop execution
• Report for manual investigation

Checkpoint fails to resolve:

• User can't approve or provides repeated issues
• Ask: "Skip this plan?" or "Abort phase execution?"
• Record partial progress in STATE.md </failure_handling>

**Resuming interrupted execution:**

If phase execution was interrupted (context limit, user exit, error):

1. Run /gsd:execute-phase {phase} again
2. discover_plans finds completed SUMMARYs
3. Skips completed plans
4. Resumes from first incomplete plan
5. Continues wave-based execution

STATE.md tracks:

• Last completed plan
• Current wave
• Any pending checkpoints