Skill Planner

Planner Skill

Thin wrapper that delegates plan creation to planner-agent subagent.

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

Context References

Reference (do not load eagerly):

• Path: .claude/context/core/formats/return-metadata-file.md - Metadata file schema
• Path: .claude/context/core/patterns/postflight-control.md - Marker file protocol
• Path: .claude/context/core/patterns/file-metadata-exchange.md - File I/O helpers
• Path: .claude/context/core/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 allows planning (not_started, researched)
• /plan command is invoked
• Implementation approach needs to be formalized

Execution Flow

Stage 1: Input Validation

Validate required inputs:

• task_number - Must be provided and exist in state.json
• Task status must allow planning

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

# Validate exists
if [ -z "$task_data" ]; then
  return error "Task $task_number not found"
fi

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

# Validate status
if [ "$status" = "completed" ]; then
  return error "Task already completed"
fi

Stage 2: Preflight Status Update

Update task status to "planning" BEFORE invoking subagent.

Update state.json:

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

Update TODO.md: Use Edit tool to change status marker from [RESEARCHED] or [NOT STARTED] to [PLANNING].

Stage 3: Create Postflight Marker

Create the marker file to prevent premature termination:

# Ensure task directory exists
padded_num=$(printf "%03d" "$task_number")
mkdir -p "specs/${padded_num}_${project_name}"

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

Stage 4: Prepare Delegation Context

Prepare delegation context for the subagent:

{
  "session_id": "sess_{timestamp}_{random}",
  "delegation_depth": 1,
  "delegation_path": ["orchestrator", "plan", "skill-planner"],
  "timeout": 1800,
  "task_context": {
    "task_number": N,
    "task_name": "{project_name}",
    "description": "{description}",
    "language": "{language}"
  },
  "research_path": "{path to research report if exists}",
  "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json"
}

Stage 5: Invoke Subagent

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

Required Tool Invocation:

Tool: Task (NOT Skill)
Parameters:
  - subagent_type: "planner-agent"
  - prompt: [Include task_context, delegation_context, research_path, metadata_file_path]
  - description: "Execute planning for task {N}"

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

The subagent will:

• Load planning context files
• Analyze task requirements and research
• Decompose into logical phases
• Identify risks and mitigations
• Create plan in specs/{NNN}_{SLUG}/plans/
• Write metadata to specs/{NNN}_{SLUG}/.return-meta.json
• Return a brief text summary (NOT JSON)

Stage 6: Parse Subagent Return (Read Metadata File)

After subagent returns, read the metadata file:

metadata_file="specs/${padded_num}_${project_name}/.return-meta.json"

if [ -f "$metadata_file" ] && jq empty "$metadata_file" 2>/dev/null; then
    status=$(jq -r '.status' "$metadata_file")
    artifact_path=$(jq -r '.artifacts[0].path // ""' "$metadata_file")
    artifact_type=$(jq -r '.artifacts[0].type // ""' "$metadata_file")
    artifact_summary=$(jq -r '.artifacts[0].summary // ""' "$metadata_file")
else
    echo "Error: Invalid or missing metadata file"
    status="failed"
fi

Stage 7: Update Task Status (Postflight)

If status is "planned", update state.json and TODO.md:

Update state.json:

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

Update TODO.md: Use Edit tool to change status marker from [PLANNING] to [PLANNED].

On partial/failed: Keep status as "planning" for resume.

Stage 8: Link Artifacts

Add artifact to state.json with summary.

IMPORTANT: Use two-step jq pattern to avoid Issue #1132 escaping bug. See jq-escaping-workarounds.md.

if [ -n "$artifact_path" ]; then
    # Step 1: Filter out existing plan artifacts (use "| not" pattern to avoid != escaping - Issue #1132)
    jq '(.active_projects[] | select(.project_number == '$task_number')).artifacts =
        [(.active_projects[] | select(.project_number == '$task_number')).artifacts // [] | .[] | select(.type == "plan" | not)]' \
      specs/state.json > /tmp/state.json && mv /tmp/state.json specs/state.json

    # Step 2: Add new plan artifact
    jq --arg path "$artifact_path" \
       --arg type "$artifact_type" \
       --arg summary "$artifact_summary" \
      '(.active_projects[] | select(.project_number == '$task_number')).artifacts += [{"path": $path, "type": $type, "summary": $summary}]' \
      specs/state.json > /tmp/state.json && mv /tmp/state.json specs/state.json
fi

Update TODO.md: Add plan artifact link:

- **Plan**: [implementation-{NNN}.md]({artifact_path})

Stage 9: Git Commit

Commit changes with session ID:

git add -A
git commit -m "task ${task_number}: create implementation plan

Session: ${session_id}

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>"

Stage 10: Cleanup

Remove marker and metadata 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}/.return-meta.json"

Stage 11: Return Brief Summary

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

Plan created for task {N}:
- {phase_count} phases defined, {estimated_hours} hours estimated
- Key phases: {phase names}
- Created plan at specs/{NNN}_{SLUG}/plans/implementation-{NNN}.md
- Status updated to [PLANNED]
- Changes committed

Error Handling

Input Validation Errors

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

Metadata File Missing

If subagent didn't write metadata file:

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

Git Commit Failure

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

jq Parse Failure

If jq commands fail with INVALID_CHARACTER or syntax error (Issue #1132):

1. Log to errors.json:

jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
   --arg sid "$session_id" \
   --arg msg "jq parse error in postflight artifact linking" \
   --argjson task "$task_number" \
  '.errors += [{
    "id": ("err_" + ($ts | gsub("[^0-9]"; ""))),
    "timestamp": $ts,
    "type": "jq_parse_failure",
    "severity": "medium",
    "message": $msg,
    "context": {"session_id": $sid, "command": "/plan", "task": $task, "checkpoint": "GATE_OUT"},
    "recovery": {"suggested_action": "Use two-step jq pattern from jq-escaping-workarounds.md", "auto_recoverable": true},
    "fix_status": "unfixed"
  }]' specs/errors.json > /tmp/errors.json && mv /tmp/errors.json specs/errors.json

2. Retry with two-step pattern (already implemented in Stage 8)

Subagent Timeout

Return partial status if subagent times out (default 1800s). Keep status as "planning" for resume.

Return Format

This skill returns a brief text summary (NOT JSON). The JSON metadata is written to the file and processed internally.

Example successful return:

Plan created for task 414:
- 5 phases defined, 2.5 hours estimated
- Covers: agent structure, execution flow, error handling, examples, verification
- Created plan at specs/414_create_planner_agent/plans/implementation-001.md
- Status updated to [PLANNED]
- Changes committed with session sess_1736700000_abc123

Example partial return:

Plan partially created for task 414:
- 3 of 5 phases defined before timeout
- Partial plan saved at specs/414_create_planner_agent/plans/implementation-001.md
- Status remains [PLANNING] - run /plan 414 to complete