Skill Spawn

Spawn Skill

Thin wrapper that delegates blocker analysis to spawn-agent subagent, then handles all state management in postflight: creates new task entries, establishes parent-child relationships, and updates dependencies.

IMPORTANT: This skill implements the skill-internal postflight pattern. After the subagent returns, this skill handles all postflight operations (task creation, dependency linking, git commit) before returning. This eliminates the "continue" prompt issue between skill return and orchestrator.

Context References

Reference (do not load eagerly):

• Path: .opencode/context/formats/return-metadata-file.md - Metadata file schema
• Path: .opencode/context/patterns/postflight-control.md - Marker file protocol
• Path: .opencode/context/patterns/jq-escaping-workarounds.md - jq escaping patterns (Issue #1132)

Note: This skill is a thin wrapper with internal postflight. Context is loaded by the delegated agent.

Trigger Conditions

This skill activates when:

• Task status is not terminal (completed, abandoned, expanded)
• /spawn command is invoked with a valid task number

Execution Flow

Stage 1: Parse Delegation Context

Parse inputs from the /spawn command:

# Extract from delegation context
task_number=$1
session_id="$2"
blocker_prompt="$3"  # May be empty

# Lookup task data
task_data=$(jq -r --argjson num "$task_number" \
  '.active_projects[] | select(.project_number == $num)' \
  specs/state.json)

# Validate exists
if [ -z "$task_data" ]; then
  echo "Error: Task $task_number not found"
  exit 1
fi

# Extract fields
project_name=$(echo "$task_data" | jq -r '.project_name')
task_type=$(echo "$task_data" | jq -r '.task_type // "general"')
status=$(echo "$task_data" | jq -r '.status')
description=$(echo "$task_data" | jq -r '.description // ""')

Stage 2: Preflight Status Update

Determine spawn type and preserve original status before updating.

Spawn type detection:

• If status is blocked, implementing, or partial -> Blocker-driven spawn
• If status is any other non-terminal state -> Holistic decomposition

Note: [BLOCKED] means "has unmet dependencies", not "encountered an error". The parent task transitions to blocked because it now depends on spawned subtasks.

Update state.json (preserve previous_status):

padded_num=$(printf "%03d" "$task_number")
previous_status=$(echo "$task_data" | jq -r '.status')

jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
   --arg status "blocked" \
   --arg prev "$previous_status" \
   --arg sid "$session_id" \
  '(.active_projects[] | select(.project_number == '$task_number')) |= . + {
    status: $status,
    previous_status: $prev,
    last_updated: $ts,
    session_id: $sid
  }' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json

Stage 3: Update TODO.md Parent Status

Use Edit tool to change status marker to [BLOCKED] if not already blocked.

old_string: - **Status**: [{current_status}]
new_string: - **Status**: [BLOCKED]

Stage 4: Create Postflight Marker

Create the marker file to prevent premature termination:

mkdir -p "specs/${padded_num}_${project_name}"

cat > "specs/${padded_num}_${project_name}/.postflight-pending" << EOF
{
  "session_id": "${session_id}",
  "skill": "skill-spawn",
  "task_number": ${task_number},
  "operation": "spawn",
  "reason": "Postflight pending: task creation, dependency linking, git commit",
  "created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
  "stop_hook_active": false
}
EOF

Stage 5: Prepare Delegation Context

Find the latest plan path (if exists):

plan_path=""
if [ -d "specs/${padded_num}_${project_name}/plans" ]; then
  plan_path=$(ls -t "specs/${padded_num}_${project_name}/plans/"*.md 2>/dev/null | head -1)
fi

Determine analysis mode for the agent:

analysis_mode="holistic"
if [ "$status" = "blocked" ] || [ "$status" = "implementing" ] || [ "$status" = "partial" ] || [ -n "$blocker_prompt" ]; then
    analysis_mode="blocker"
fi

Prepare delegation context for the subagent:

{
  "session_id": "sess_{timestamp}_{random}",
  "delegation_depth": 2,
  "delegation_path": ["orchestrator", "spawn", "skill-spawn"],
  "timeout": 1800,
  "task_number": N,
  "task_data": {
    "project_number": N,
    "project_name": "{slug}",
    "status": "blocked",
    "task_type": "{task_type}",
    "description": "{description}",
    "effort": "{effort}"
  },
  "blocker_prompt": "{optional user description}",
  "plan_path": "{path to latest plan or null}",
  "analysis_mode": "blocker" | "holistic",
  "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json"
}

Stage 6: Invoke Subagent

CRITICAL: You MUST use the Task tool to spawn the subagent.

Required Tool Invocation:

Tool: Task (NOT Skill)
Parameters:
  - subagent_type: "spawn-agent"
  - prompt: [Include task_number, task_data, blocker_prompt, plan_path, metadata_file_path, session_id]
  - description: "Analyze blocker for task {N} and propose new tasks"

DO NOT use Skill(spawn-agent) - this will FAIL.

The subagent will:

• Load task context and plan
• Analyze the blocker and identify root cause
• Propose minimal new tasks with dependencies
• Write blocker analysis report
• Write .spawn-return.json with task definitions
• Return a brief text summary (NOT JSON)

Stage 6b: Self-Execution Fallback

CRITICAL: If you performed the work above WITHOUT using the Task tool (i.e., you read files, wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a .return-meta.json file now before proceeding to postflight. Use the schema from return-metadata-file.md with the appropriate status value for this operation.

If you DID use the Task tool, skip this stage -- the subagent already wrote the metadata.

Postflight (ALWAYS EXECUTE)

The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 6b). Do NOT skip these stages for any reason.

Stage 7: Read Return Metadata

Read the spawn return file:

spawn_file="specs/${padded_num}_${project_name}/.spawn-return.json"

if [ -f "$spawn_file" ] && jq empty "$spawn_file" 2>/dev/null; then
    new_tasks=$(jq -r '.new_tasks' "$spawn_file")
    task_count=$(jq '.new_tasks | length' "$spawn_file")

    if [ "$task_count" -eq 0 ]; then
        echo "Spawn cancelled: no tasks selected."
        # Cleanup and restore parent status if needed
        rm -f "specs/${padded_num}_${project_name}/.postflight-pending"
        rm -f "specs/${padded_num}_${project_name}/.spawn-return.json"
        exit 0
    fi

    dependency_order=$(jq -r '.dependency_order' "$spawn_file")
    analysis_summary=$(jq -r '.analysis_summary' "$spawn_file")
    report_path=$(jq -r '.report_path' "$spawn_file")
else
    echo "Error: Invalid or missing spawn return file"
    exit 1
fi

Stage 8: Get Next Task Numbers

Get the next available task numbers from state.json:

next_num=$(jq -r '.next_project_number' specs/state.json)

# Calculate task numbers for each new task based on dependency_order
# First task gets next_num, second gets next_num+1, etc.

Stage 9: Apply Topological Sort (Kahn's Algorithm)

The agent provides dependency_order which is already topologically sorted (foundational tasks first). Map internal indices to actual task numbers:

# Example: dependency_order = [0, 1] means task at index 0 is foundational
# If next_num = 242:
#   - Index 0 -> Task {N} (foundational)
#   - Index 1 -> Task {M} (depends on {N})

# Build index->task_number mapping
declare -A task_num_map
order_idx=0
for idx in $(echo "$dependency_order" | jq -r '.[]'); do
    task_num_map[$idx]=$((next_num + order_idx))
    order_idx=$((order_idx + 1))
done

Stage 10: Create New Task Directories

For each new task, create directory structure:

for idx in $(echo "$dependency_order" | jq -r '.[]'); do
    new_task_num=${task_num_map[$idx]}
    new_padded=$(printf "%03d" "$new_task_num")

    # Get task data from spawn return
    task_title=$(jq -r --argjson i "$idx" '.new_tasks[$i].title' "$spawn_file")
    task_slug=$(echo "$task_title" | tr '[:upper:]' '[:lower:]' | tr ' ' '_' | sed 's/[^a-z0-9_]//g')

    # Create directory with research artifact stub
    mkdir -p "specs/${new_padded}_${task_slug}/reports"

    # Copy spawn analysis as initial research for first task
    # (or create stub pointing to parent's spawn analysis)
done

Stage 11: Update state.json with New Tasks

Insert new tasks in topological order (foundational first):

for idx in $(echo "$dependency_order" | jq -r '.[]'); do
    new_task_num=${task_num_map[$idx]}

    # Extract task fields
    task_title=$(jq -r --argjson i "$idx" '.new_tasks[$i].title' "$spawn_file")
    task_desc=$(jq -r --argjson i "$idx" '.new_tasks[$i].description' "$spawn_file")
    task_effort=$(jq -r --argjson i "$idx" '.new_tasks[$i].effort' "$spawn_file")
    task_lang=$(jq -r --argjson i "$idx" '.new_tasks[$i].task_type' "$spawn_file")
    internal_deps=$(jq -r --argjson i "$idx" '.new_tasks[$i].dependencies' "$spawn_file")

    # Convert internal deps to task numbers
    resolved_deps="[]"
    for dep_idx in $(echo "$internal_deps" | jq -r '.[]'); do
        dep_num=${task_num_map[$dep_idx]}
        resolved_deps=$(echo "$resolved_deps" | jq --argjson n "$dep_num" '. + [$n]')
    done

    # Create task slug
    task_slug=$(echo "$task_title" | tr '[:upper:]' '[:lower:]' | tr ' ' '_' | sed 's/[^a-z0-9_]//g')

    # Add to state.json
    jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
       --argjson num "$new_task_num" \
       --arg name "$task_slug" \
       --arg desc "$task_desc" \
       --arg effort "$task_effort" \
       --arg lang "$task_lang" \
       --argjson deps "$resolved_deps" \
       --argjson parent "$task_number" \
       --arg report "$report_path" \
      '.active_projects += [{
        "project_number": $num,
        "project_name": $name,
        "status": "researched",
        "task_type": $lang,
        "description": $desc,
        "effort": $effort,
        "parent_task": $parent,
        "dependencies": $deps,
        "created": $ts,
        "last_updated": $ts,
        "artifacts": [{"type": "research", "path": $report, "summary": "Spawn analysis from parent task"}]
      }]' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json
done

# Update next_project_number
jq --argjson next "$((next_num + task_count))" \
  '.next_project_number = $next' \
  specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json

Stage 12: Update TODO.md with New Task Entries

Insert new task entries after the Tasks header, in topological order:

### {NEW_TASK_NUM}. {Title}
- **Effort**: {estimate}
- **Status**: [RESEARCHED]
- **Task Type**: {task_type}
- **Dependencies**: Task #{dep1}, Task #{dep2}  OR  None
- **Parent Task**: #{parent_task_number}
- **Started**: {timestamp}
- **Research**: [02_spawn-analysis.md]({parent_dir}/reports/02_spawn-analysis.md)

**Description**: {full description}

CRITICAL — Batch Insertion: Spawn creates multiple tasks. Build a single batch_markdown string by joining ALL task entries with \n\n, then use ONE Edit tool call:

oldString: "## Tasks\n"
newString: "## Tasks\n\n{batch_markdown}\n"

WARNING: DO NOT search for the last --- separator and append text after it. DO NOT insert at the bottom of the file. DO NOT prepend each task entry individually — individual prepending reverses task order (last task becomes first). ALWAYS use the heading-anchored Edit tool pattern with oldString: "## Tasks\n". The heading ## Tasks is unique in TODO.md and is the only reliable insertion anchor.

After inserting, re-read the first few lines after ## Tasks:

• Confirm the first task after ## Tasks has the expected task number
• If it doesn't match, the insertion went wrong — fix and re-verify

Refresh Recommended Order section (non-blocking):

# Refresh Recommended Order section to include spawned tasks (non-blocking)
if source "$PROJECT_ROOT/.opencode/scripts/update-recommended-order.sh" 2>/dev/null; then
    refresh_recommended_order || echo "Note: Failed to refresh Recommended Order"
fi

Stage 13: Update Parent Task Dependencies

Add new task numbers to parent task's dependencies in state.json:

# Build array of new task numbers
new_task_nums="[]"
for idx in $(echo "$dependency_order" | jq -r '.[]'); do
    new_task_nums=$(echo "$new_task_nums" | jq --argjson n "${task_num_map[$idx]}" '. + [$n]')
done

# Update parent task dependencies (use "| not" pattern for Issue #1132)
jq --argjson new_deps "$new_task_nums" \
   --argjson num "$task_number" \
  '(.active_projects[] | select(.project_number == $num) | .dependencies) =
   ((.active_projects[] | select(.project_number == $num) | .dependencies) // [] + $new_deps)' \
  specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json

Stage 14: Update Parent Task Dependencies in TODO.md

Edit the parent task entry to add/update the Dependencies line:

# If no Dependencies line exists, add after Status line:
old_string: - **Status**: [BLOCKED]
new_string: - **Status**: [BLOCKED]
- **Dependencies**: Task #{N}, Task #{M}

# If Dependencies line exists, update it:
old_string: - **Dependencies**: None
new_string: - **Dependencies**: Task #{N}, Task #{M}

Use Edit tool to update the parent task entry.

Stage 15: Git Commit

Commit all changes with session ID:

git add -A
git commit -m "$(cat <<'EOF'
task {N}: spawn {M} tasks to resolve blocker

Session: {session_id}

EOF
)"

Commit failure is non-blocking (log and continue).

Stage 16: Cleanup

Remove temporary files:

rm -f "specs/${padded_num}_${project_name}/.postflight-pending"
rm -f "specs/${padded_num}_${project_name}/.postflight-loop-guard"
rm -f "specs/${padded_num}_${project_name}/.spawn-return.json"
rm -f "specs/${padded_num}_${project_name}/.return-meta.json"

Stage 17: Return Brief Summary

Return a brief text summary (NOT JSON). Example:

Spawned {M} tasks to unblock task {N}:
- Task #{X}: {title} (no dependencies)
- Task #{Y}: {title} (depends on #{X})
- Parent task #{N} now depends on: #{X}, #{Y}
- Status: Parent [BLOCKED], spawned tasks [RESEARCHED]
- Next: /plan {first_spawned_task_num}

Error Handling

Input Validation Errors

Return immediately with error message if task not found or status invalid.

Spawn Return File Missing

If subagent didn't write spawn return file:

1. Keep status as "blocked"
2. Do not cleanup postflight marker
3. Report error to user

Empty Task Selection (Cancelled Spawn)

If user selected no tasks in holistic mode:

1. task_count will be 0
2. Exit gracefully with informative message
3. Cleanup temporary files
4. Parent task remains [BLOCKED] (it still has the dependency intent)

Invalid Dependency Graph

If dependency_order contains cycles or invalid indices:

1. Log error
2. Fall back to sequential ordering by index
3. Report warning to user

Git Commit Failure

Non-blocking: Log failure but continue with success response.

jq Parse Failure

If jq commands fail (Issue #1132):

1. Log error
2. Retry using "| not" pattern
3. See jq-escaping-workarounds.md

MUST NOT (Postflight Boundary)

After the agent returns, this skill MUST NOT:

1. Perform research or analysis - Analysis is done by agent
2. Make decisions about task breakdown - Agent decides decomposition
3. Write implementation files - Only state files in specs/
4. Modify files outside specs/ - All changes confined to specs/

The postflight phase is LIMITED TO:

• Reading agent spawn return file
• Creating task directories
• Updating state.json with new tasks
• Updating TODO.md with new task entries
• Updating parent task dependencies
• Git commit
• Cleanup of temp/marker files

Reference: @.opencode/context/standards/postflight-tool-restrictions.md

Return Format

This skill returns a brief text summary (NOT JSON). The structured data is processed internally.

Example successful return:

Spawned 2 tasks to unblock task {N}:
- Task #{M}: Create state validation utilities (no dependencies)
- Task #{P}: Implement recovery workflow (depends on #{M})
- Parent task #{N} now depends on: #{M}, #{P}
- Status: Parent [BLOCKED], spawned tasks [RESEARCHED]
- Next: /plan 242

Example partial return:

Spawn partially completed for task {N}:
- Blocker analyzed, 2 tasks proposed
- Task creation failed at Task #{P}
- Partial state may exist, run /task --sync to reconcile