/setup

name: setup
license: MIT
compatibility: "Claude Code 2.1.277+."
description: "Onboarding wizard: scans the codebase and stack, recommends skills and MCP servers, scores readiness. Use when setting up OrchestKit in a project or rescanning after big changes."
argument-hint: "[--rescan] [--score-only] [--plan-only] [--channel] [--configure]"
context: fork
# user-typed commands stay interactive; CC >= 2.1.218 backgrounds forks by default (#3093)
background: false
user-invocable: true
disable-model-invocation: false
allowed-tools: "Read Write Grep Glob Bash AskUserQuestion TaskCreate TaskUpdate mcp__memory__search_nodes mcp__memory__create_entities mcp__memory__create_relations"
skills: [configure, remember, explore, help]
metadata:
  category: configuration
  mcp-server: memory
  version: "2.1.0"
  author: "OrchestKit"
  complexity: "medium"
  tags: "onboarding, setup, wizard, configuration, stack-detection, mcp, personalization, telemetry, presets"
triggers:
  keywords: [setup, onboarding, configure, "just installed", "get orchestkit working", "set up orchestkit", "set up ork", "readiness score", wizard]
  examples:
    - "set up orchestkit for this project"
    - "run the onboarding wizard"
    - "i just installed orchestkit, what do i do first"
  anti-triggers: [doctor, help, explore, implement, fix]

OrchestKit Setup Wizard

Personalized onboarding that scans your codebase, detects your stack, recommends skills and MCPs, and generates an actionable improvement plan.

When to Use

• First time after installing OrchestKit (`/plugin install ork`)
• Joining a new project and want OrchestKit tuned for it
• Periodically with `--rescan` to track improvement
• Enterprise users who need safe, user-scoped install confirmation

Quick Start

setup              # Full 7-phase wizard
setup --rescan     # Re-scan after changes (skip safety phase)
setup --score-only # Just show readiness score
setup --plan-only  # Just show improvement plan
setup --configure  # Jump directly to Phase 3.5: project configuration wizard

Argument Resolution

FLAG = "$ARGUMENTS[0]"  # First token: --rescan, --score-only, --plan-only, --channel
# If no arguments, run full 7-phase wizard.
# $ARGUMENTS is the full string (CC 2.1.59 indexed access)

CRITICAL: Task Management is MANDATORY (CC 2.1.16)

**BEFORE doing ANYTHING else, create tasks to track progress:**

# 1. Create main task IMMEDIATELY
TaskCreate(
  subject="Setup: onboarding wizard",
  description="Personalized setup scanning codebase and configuring OrchestKit",
  activeForm="Running setup wizard"
)

# 2. Create subtasks for key phase groups
TaskCreate(subject="Scan & detect stack", activeForm="Scanning codebase and detecting stack")
TaskCreate(subject="Safety & configure", activeForm="Checking config and running configuration wizard")
TaskCreate(subject="Recommend skills & MCPs", activeForm="Matching stack to skills and MCPs")
TaskCreate(subject="Score & plan", activeForm="Computing readiness score and improvement plan")

# 3. Set dependencies for sequential phases
TaskUpdate(taskId="3", addBlockedBy=["2"])
TaskUpdate(taskId="4", addBlockedBy=["3"])
TaskUpdate(taskId="5", addBlockedBy=["4"])

# 4. Update status as you progress
TaskUpdate(taskId="2", status="in_progress")  # When starting
TaskUpdate(taskId="2", status="completed")    # When done

The Phases

| Phase | What | Tools Used | Output | |-------|------|-----------|--------| | 1. Scan | Detect languages, frameworks, infra, existing config | Glob, Grep, Read | Raw scan data | | 2. Stack | Classify detected stack, confidence levels | — | Stack profile | | 3. Safety | Check existing config, confirm scope (user/project) | Read, AskUserQuestion | Install confirmation | | 3.5. Configure | Interactive project configuration wizard → writes env block to per-project settings | Read, Write, AskUserQuestion | Configured settings file | | 3.6. Protect | Deliver ork's canonical `permissions.deny` payload to an ENFORCING scope (a plugin settings.json is inert: CC reads only `agent`/`subagentStatusLine`, #3835). Run `node ${CLAUDE_SKILL_DIR}/scripts/write-operator-permissions.mjs --scope user --dry-run`, show the additions and the print-only sandbox suggestion, then ONLY on an explicit yes rerun without `--dry-run`. The script backs up the file and prints the one-command rollback. Never write without the dry-run + consent pair. | Bash, AskUserQuestion | Enforced deny rules + rollback line | | 4. Skills | Match stack to skills, suggest custom skills | Grep, Glob | Skill recommendations | | 5. MCPs | Recommend MCPs based on stack and gaps | Read, Bash | MCP recommendations | | 6. Score | Compute readiness score (0-10, 6 dimensions) | All above data | Readiness score | | 7. Plan | Prioritized improvements with runnable commands | — | Action plan |

---

Phase 1: Scan

Load details: `Read("references/scan-phase.md")` for full scan commands (20 parallel Glob probes + dependency file reads + pattern detection counts).

Scans for package manifests (package.json, pyproject.toml, go.mod, Cargo.toml, etc.), infrastructure (Docker, GitHub Actions, Terraform, K8s), and existing CC configuration. Pattern detection counts API routes, React components, models, and tests for custom skill suggestions.

Phase 2: Stack Detection

**Stack snapshot, already loaded.** Claude Code ran this loader when it opened this skill (a fork never runs frontmatter hooks, and a body step can be skipped, #4683). Keep its `additionalContext` below in mind. A blank line means it had nothing to add. If you see `[shell command execution disabled by policy]` instead, run it yourself: `echo '{"hook_event_name":"PreToolUse","tool_name":"Bash","tool_input":{}}' | node "${CLAUDE_PLUGIN_ROOT}/hooks/bin/run-hook.mjs" skill/setup-env-detector`:

!`echo '{"hook_event_name":"PreToolUse","tool_name":"Bash","tool_input":{}}' | node "${CLAUDE_SKILL_DIR}/../../hooks/bin/run-hook.mjs" skill/setup-env-detec