setup

name	setup
description	Configure review agents and stack detection for your project
disable-model-invocation	true
user-invocable	false

Compound Workflows Setup

Interactive setup for compound-workflows.local.md — configures which agents run during /do:review and /do:work.

Step 1: Check Existing Config

Read compound-workflows.local.md in the project root. If it exists, display current settings summary and use AskUserQuestion:

question: "Settings file already exists. What would you like to do?"
header: "Config"
options:
  - label: "Reconfigure"
    description: "Run the interactive setup again from scratch"
  - label: "View current"
    description: "Show the file contents, then stop"
  - label: "Cancel"
    description: "Keep current settings"

If "View current": read and display the file, then stop. If "Cancel": stop.

Step 2: Detect and Ask

Auto-detect the project stack:

test -f tsconfig.json && echo "typescript" || \
test -f package.json && echo "javascript" || \
test -f pyproject.toml && echo "python" || \
test -f requirements.txt && echo "python" || \
echo "general"

Use AskUserQuestion:

question: "Detected {type} project. How would you like to configure?"
header: "Setup"
options:
  - label: "Auto-configure (Recommended)"
    description: "Use smart defaults for {type}. Done in one click."
  - label: "Customize"
    description: "Choose stack, focus areas, and review depth."

If Auto-configure -> Skip to Step 4 with defaults:

• Python: [python-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle]
• TypeScript: [typescript-reviewer, code-simplicity-reviewer, security-sentinel, performance-oracle]
• General: [code-simplicity-reviewer, security-sentinel, performance-oracle, architecture-strategist]

If Customize -> Step 3

Step 3: Customize (3 questions)

a. Stack — confirm or override:

question: "Which stack should we optimize for?"
header: "Stack"
options:
  - label: "{detected_type} (Recommended)"
    description: "Auto-detected from project files"
  - label: "Python"
    description: "Python — adds Pythonic pattern reviewer"
  - label: "TypeScript"
    description: "TypeScript — adds type safety reviewer"

Only show options that differ from the detected type.

b. Focus areas — multiSelect:

question: "Which review areas matter most?"
header: "Focus"
multiSelect: true
options:
  - label: "Security"
    description: "Vulnerability scanning, auth, input validation (security-sentinel)"
  - label: "Performance"
    description: "N+1 queries, memory leaks, complexity (performance-oracle)"
  - label: "Architecture"
    description: "Design patterns, SOLID, separation of concerns (architecture-strategist)"
  - label: "Code simplicity"
    description: "Over-engineering, YAGNI violations (code-simplicity-reviewer)"

c. Depth:

question: "How thorough should reviews be?"
header: "Depth"
options:
  - label: "Thorough (Recommended)"
    description: "Stack reviewers + all selected focus agents."
  - label: "Fast"
    description: "Stack reviewers + code simplicity only. Less context, quicker."
  - label: "Comprehensive"
    description: "All above + git history, data integrity, agent-native checks."

Step 4: Build Agent List and Write File

Stack-specific agents:

• Python -> python-reviewer
• TypeScript -> typescript-reviewer
• General -> (none)

Focus area agents:

• Security -> security-sentinel
• Performance -> performance-oracle
• Architecture -> architecture-strategist
• Code simplicity -> code-simplicity-reviewer

Depth:

• Thorough: stack + selected focus areas
• Fast: stack + code-simplicity-reviewer only
• Comprehensive: all above + git-history-analyzer, data-integrity-guardian, agent-native-reviewer

Plan review agents: stack-specific reviewer + code-simplicity-reviewer.

Write compound-workflows.local.md:

---
review_agents: [{computed agent list}]
plan_review_agents: [{computed plan agent list}]
stats_capture: true
stats_classify: true
compact_version_check: false
compact_cost_summary: true
compact_auto_commit: false
compact_compound_check: true
compact_push: true
---

# Review Context

Add project-specific review instructions here.
These notes are passed to all review agents during /do:review and /do:work.

Examples:
- "Our API is public — extra scrutiny on input validation"
- "Performance-critical: we serve 10k req/s on this endpoint"

Migration: Stats Keys

If compound-workflows.local.md exists but lacks stats_capture, append both stats keys with true defaults:

bash ${CLAUDE_SKILL_DIR}/../../scripts/migrate-stats-keys.sh

Read the stdout for STATS_KEYS_ADDED=true status.

Stats toggles default to enabled — missing keys are treated as enabled by orchestrator commands (Decision 6: "Missing keys = enabled"). The migration adds keys for explicitness.

Migration: Compact Config Keys

If compound-workflows.local.md exists, check for each of the 5 compact config keys independently and append any that are missing with their defaults. Keys may be partially present (e.g., user added some manually). Handle each key independently:

Migration procedure: Read compound-workflows.local.md (create with touch if it does not exist). For each of the 5 compact config keys below, check whether the key is already present (grep -q). For any missing key, use the Edit tool to append it at the end of the file with its default value.

Key	Default
compact_version_check	false
compact_cost_summary	true
compact_auto_commit	false
compact_compound_check	true
compact_push	true

Handle each key independently — partial presence is expected during migration.

Defaults: most keys default to true (enabled, preserves current behavior). Exceptions: compact_version_check defaults to false (only relevant to plugin developers) and compact_auto_commit defaults to false (opt-in to auto-execute).

Step 5: Confirm

Saved to compound-workflows.local.md

Stack:        {type}
Review depth: {depth}
Agents:       {count} configured
              {agent list, one per line}

Tip: Edit the "Review Context" section to add project-specific instructions.
     Re-run this setup anytime to reconfigure.