Dev Setup

/dev-setup

User request: "$ARGUMENTS"

Task

Detect the project's structure, propose a dev environment configuration, and generate bash scripts for managing servers, Chrome profiles, and worktree port isolation.

Process

Step 0: Ensure dependencies

Resolve plugin path:

bashCopy code
SKILL_DIR="$(find "$HOME/.claude/plugins/cache" -type d -name "dev-setup" -path "*/skills/dev-setup" 2>/dev/null | head -1)"
[[ -z "$SKILL_DIR" ]] && SKILL_DIR="$(find "$HOME" -maxdepth 8 -type d -name "dev-setup" -path "*/skills/dev-setup" 2>/dev/null | head -1)"

bashCopy code
bash "$SKILL_DIR/scripts/ensure-deps.sh"

If the script exits with an error, show the missing dependency message to the user and stop. Warnings about optional tools can be shown but should not block execution.

Route: upgrade

If $ARGUMENTS starts with "upgrade":

Read references/upgrade-route.md and follow the steps there.

Route: health

If $ARGUMENTS starts with "health":

1. Resolve plugin path (same as upgrade route)

2. Run the health check script:

   bashCopy code
   bash "$SKILL_DIR/reference/dev-setup-health.sh"
   

3. Print the output to the user. Then stop — do not continue to Step 1.

Step 1: Resolve project root

If $ARGUMENTS is a non-empty path, use it as the project root. Otherwise use the current directory ($PWD).

bashCopy code
PROJECT_ROOT="${ARGUMENTS:-$PWD}"
cd "$PROJECT_ROOT"

Important: Claude's Bash tool does not preserve cd between calls. Prefix every subsequent Bash command in Steps 2-5 with cd "$PROJECT_ROOT" && to ensure all detection runs in the correct directory.

Step 2: Detect package manager

Run the following detection in Bash:

bashCopy code
if [[ -f pnpm-lock.yaml ]]; then PM=pnpm
elif [[ -f bun.lock ]] || [[ -f bun.lockb ]]; then PM=bun
elif [[ -f yarn.lock ]]; then PM=yarn
elif [[ -f package-lock.json ]]; then PM=npm
elif [[ -f Cargo.toml ]]; then PM=cargo
elif [[ -f go.mod ]]; then PM=go
else PM=none
fi
echo "PM=$PM"

Step 3: Detect services and ports

First check if package.json exists:

bashCopy code
[[ -f package.json ]] && echo "NODE=true" || echo "NODE=false"

If NODE=false, skip the python3 snippet and the concurrently check in Step 4 — set CONCURRENTLY=false and note "not a Node project".

Scope note: Service detection, runner options, and package.json script generation (Steps 3-9) assume a Node/JS project. For non-Node stacks (cargo, go, etc.), only dev-post-checkout.sh (dependency install) is generated reliably. Tell the user: "Service management scripts for [stack] are not yet supported — only dependency install was generated. You can add custom start/stop scripts to <SCRIPT_DIR>/ manually."

Read package.json scripts for entries matching dev:*, start, serve, preview:

bashCopy code
python3 -c "
import json, sys
d = json.load(open('package.json'))
for k, v in d.get('scripts', {}).items():
    if any(x in k for x in ['dev', 'start', 'serve', 'preview', 'storybook']):
        print(f'SCRIPT={k} CMD={v}')
" 2>/dev/null || true

Read existing port assignments from env files:

bashCopy code
grep -hE "^([A-Z][A-Z0-9_]*_WT_PORT|VITE_[A-Z_]*)=" \
  .env.example .env 2>/dev/null | head -20 \
  || echo "ENV_FILES=none"

Try Context7 first. If resolve-library-id returns no match or query-docs returns no relevant result, use the WebFetch fallback URL instead.

If vite.config.* exists, resolve current Vite port API:

• Use Context7: resolve-library-id "vite" → query-docs "dev server port configuration"
• Fallback (WebFetch): https://vitejs.dev/config/server-options.html

If docker-compose.yml exists:

• Use Context7: resolve-library-id "docker compose" → query-docs "ports mapping"
• Fallback (parse directly — no docs needed): grep -A2 'ports:' docker-compose.yml

Step 4: Detect existing scripts and runtime tools

bashCopy code
# Find existing bash scripts
find . -maxdepth 4 \( -name "*.sh" -o -name "devctl" \) \
  -not -path "*/node_modules/*" -not -path "*/.git/*" 2>/dev/null

# Detect script directory convention (first match wins)
SCRIPT_DIR=""
for d in tools/dev scripts bin devtools; do
  [[ -d "$d" ]] && SCRIPT_DIR="$d" && echo "SCRIPT_DIR=$d" && break
done
[[ -z "$SCRIPT_DIR" ]] && echo "SCRIPT_DIR=tools/dev (will create)"

# Runtime tools
for t in tmux shellcheck shfmt ttyd; do
  command -v "$t" >/dev/null 2>&1 \
    && echo "TOOL=$t STATUS=available" \
    || echo "TOOL=$t STATUS=missing"
done

# concurrently in deps
grep -q '"concurrently"' package.json 2>/dev/null \
  && echo "CONCURRENTLY=true" || echo "CONCURRENTLY=false"

If shellcheck is missing (STATUS=missing), warn the user: "Required tool shellcheck not found. Run /dev-setup health for install instructions."

Step 5: Detect Chrome and gtr config

bashCopy code
# Chrome
grep -hE "^(CHROME_PROFILE|CHROME_CDP_WT_PORT)=" .env.example .env 2>/dev/null \
  || echo "CHROME=not-configured"

# git gtr
command -v gtr >/dev/null 2>&1 && echo "GTR_BINARY=found" || echo "GTR_BINARY=missing"
[[ -f .gtrconfig ]] && echo "GTRCONFIG=found" && cat .gtrconfig || echo "GTRCONFIG=none"
[[ -f .gtr-setup.sh ]] && echo "GTR_SETUP=found" || echo "GTR_SETUP=none"

Set GTR="yes" if GTR_BINARY=found, GTR="no" otherwise. Do not ask the user — presence in PATH is the decision.

If .gtrconfig exists, use Context7 to validate hook syntax:

Try Context7 first. If resolve-library-id returns no match or query-docs returns no relevant result, use the WebFetch fallback URL instead.

• resolve-library-id "git-worktree-runner" → query-docs "postCreate hook env vars WORKTREE_PATH BRANCH"
• Fallback: WebFetch https://github.com/coderabbitai/git-worktree-runner

Step 6: Propose configuration — Call A

Summarize the detected project in 2-3 lines (package manager, services found, tools available), then call AskUserQuestion with these 4 questions:

Constraint: Each call supports 1-4 questions with 2-4 options each.

Copy code
AskUserQuestion (4 questions):

Q1 — header: "Services", multiSelect: true
  question: "Which services should be managed? (detected from project)"
  options — build dynamically from detected SCRIPT entries (up to 4), e.g.:
    - label: "api  :3000"         description: "Backend server (PORT=3000)"
    - label: "web  :5173"         description: "Frontend dev server (WEB_WT_PORT=5173)"
    - label: "storybook  :61000"  description: "Component explorer (STORYBOOK_WT_PORT=61000)"
    - label: "ttyd  :7681"        description: "Browser terminal (TTYD_WT_PORT=7681)"
  Note: show only detected services. If fewer than 2 detected, add a generic "custom :3000" option alongside any detected ones (do not replace them).

Q2 — header: "Runner", multiSelect: false
  question: "How should servers be launched?"
  options:
    - label: "tmux"              description: "Detached 3-pane session per branch. Requires tmux."  (append " (not found on PATH)" if tmux STATUS=missing)
    - label: "concurrently"      description: "All servers in one terminal. No tmux required."
    - label: "tmux + fallback"   description: "tmux when available, concurrently otherwise."
    - label: "manual only"       description: "Generate scripts but no auto-launcher."

Q3 — header: "Chrome", multiSelect: false
  question: "Set up an isolated Chrome dev profile?"
  options:
    - label: "Yes — create profile"  description: "Creates ~/.chrome-profiles/<name> and a launcher."
    - label: "No — skip"             description: "Skip. Re-run /dev-setup to add later."

Q4 — header: "Script dir", multiSelect: false
  question: "Where should scripts be placed?"
  options — if a dir was detected in Step 4 (SCRIPT_DIR was set without "(will create)"), move that matching option to the first position; otherwise use this order:
    - label: "tools/dev/"   description: "Recommended. Mirrors reference pattern."
    - label: "scripts/"     description: "Common alternative."
    - label: "bin/"         description: "Minimal convention."
    - label: "devtools/"    description: "Custom directory (will be created)."

Store the user's answers as:

• SELECTED_SERVICES — array of selected labels
• RUNNER — selected label
• CHROME — selected label
• SCRIPT_DIR — selected label (strip trailing slash for filesystem use)

Step 7: Propose configuration — Call B (conditional)

Only run Call B if CHROME = "Yes — create profile".

If not, skip to Step 8.

Copy code
AskUserQuestion (1 question):

Q1 — header: "Profile name", multiSelect: false
  question: "Chrome profile name and CDP port?"
  options — derive <project-name> from package.json "name" field or directory basename:
    - label: "<project-name>  :19222"  description: "Profile: chrome-<project-name>, CDP: 19222"
    - label: "<project-name>  :19223"  description: "Profile: chrome-<project-name>, CDP: 19223"
    - label: "<project-name>  :19224"  description: "Profile: chrome-<project-name>, CDP: 19224"
    - label: "Other"                   description: "Enter name and port manually — skill will prompt"

Store answers as:

• CHROME_PROFILE_NAME — profile name extracted from label (e.g. "myapp" from "myapp :19222"), or if "Other": ask user for profile name (string, no spaces) and CDP port (number) separately
• CHROME_CDP_WT_PORT — port extracted from label (e.g. "19222")

Script Conventions

Apply these patterns to ALL generated scripts.

Strict mode

All standalone scripts: set -euo pipefail Sourced utilities (dev-read-ports.sh, dev-session-name.sh): NO strict mode — it would bleed into the caller shell.

Port reading (dev-read-ports.sh) and session naming (dev-session-name.sh)

Both are sourced utilities — no set -euo pipefail (would bleed into caller). See reference files for full pattern. Key behaviors:

• _read_env VAR DEFAULT reads from .wt-ports.env → .env → .env.example (first match wins)
• dev_session_name returns b-<branch> (normalized lowercase, hyphens)
• Adapt exported port vars to match SELECTED_SERVICES (don't hardcode all 4 from reference)

Output format — ALL status/lifecycle scripts

Emit KEY=value lines, no ANSI color, one line per entity:

Copy code
SERVICE=api PORT=3000 STATUS=running PID=12345 PROCESS=node
TMUX=b-main STATUS=active ATTACHED=false
CHROME=chrome-myapp STATUS=running CDP_PORT=19222 CDP_URL=http://localhost:19222

Port variable naming

All vars ending in _WT_PORT are worktree-isolated service ports written to .wt-ports.env per worktree. Config/range vars use PORT_ prefix (e.g. PORT_MIN, PORT_MAX).

Port allocator (dev-allocate-ports.sh)

Standalone script that allocates N consecutive free ports from a safe pool (20000-29999). Uses lsof -nP -iTCP:"$port" -sTCP:LISTEN to verify availability. Two modes:

• Allocate: bash dev-allocate-ports.sh 4 → prints 4 consecutive free ports
• Validate: bash dev-allocate-ports.sh 4 --validate 23847 23848 23849 23850 → checks ports, suggests replacements if occupied

See $SKILL_DIR/reference/dev-allocate-ports.sh for the full pattern.

Worktree port allocator (dev-wt-ports.sh)

Calls dev-allocate-ports.sh to get a block of free ports, then writes them to .wt-ports.env. Must use $WORKTREE_PATH and $BRANCH env vars (set by git gtr postCreate hook), not $PWD.

Step 8: Generate bash scripts

Using the user's answers (SELECTED_SERVICES, RUNNER, CHROME, SCRIPT_DIR, GTR) and the convention patterns above, generate each script. Throughout this section, <SCRIPT_DIR> refers to the $SCRIPT_DIR value collected in Step 6 — replace it with the actual path (e.g. tools/dev) everywhere it appears. For every file:

1. Generate content following the conventions
2. Write with the Write tool
3. Run shellcheck <file> immediately — fix all error-level issues before continuing

Adaptation contract

Reference files (in $SKILL_DIR/reference/) are patterns from a tools/dev/ + pnpm project. Do NOT copy them verbatim. Adapt every generated script:

Reference → generated name mapping

Utility scripts keep their names: dev-read-ports.sh, dev-session-name.sh, dev-allocate-ports.sh, dev-post-checkout.sh.

Reference loading (progressive — load only what you need)

Always read first (core patterns):

• $SKILL_DIR/reference/dev-read-ports.sh — port reading utility (sourced, no strict mode)
• $SKILL_DIR/reference/dev-allocate-ports.sh — pool-based port allocator (20000-29999)
• $SKILL_DIR/reference/dev-session-name.sh — tmux session naming
• $SKILL_DIR/reference/dev-servers-status.sh — KEY=value status format
• $SKILL_DIR/reference/dev-stop-all-servers.sh — stop pattern
• $SKILL_DIR/reference/dev-restart-all-servers.sh — restart pattern
• $SKILL_DIR/reference/dev-post-checkout.sh — dependency install after clone

Read if RUNNER includes tmux:

• $SKILL_DIR/reference/dev-tmux-start.sh — tmux session with pane titles
• $SKILL_DIR/reference/dev-tmux.sh — tmux helper utilities

Read if RUNNER includes concurrently:

• $SKILL_DIR/reference/dev-concurrently.sh — concurrently runner

Read if CHROME = "Yes — create profile":

• $SKILL_DIR/reference/dev-chrome-profile-setup.sh — Chrome profile setup
• $SKILL_DIR/reference/dev-open-browser.sh — browser open

Do not call directly (inline the pattern):

• $SKILL_DIR/reference/dev-check-ports.sh — inline the lsof -nP -tiTCP:"$PORT" -sTCP:LISTEN check in dev-start.sh instead of calling this script. On collision, suggest running dev-allocate-ports.sh for a fresh block.

Scripts to generate

Always generate (in this order):

1. <SCRIPT_DIR>/dev-allocate-ports.sh — pool-based port allocator. Allocates N consecutive free ports from 20000-29999. Used by dev-wt-ports.sh and can be run standalone to reassign ports on collision.

2. <SCRIPT_DIR>/dev-wt-ports.sh — dual-mode worktree port allocator. Reads services keys from .claude/dev-setup.json, allocates one port per service key via dev-allocate-ports.sh, writes results to .wt-ports.env.

3. <SCRIPT_DIR>/dev-read-ports.sh — port reading utility (no strict mode, sourced only)

4. <SCRIPT_DIR>/dev-session-name.sh — tmux session naming function (no strict mode, sourced only)

5. <SCRIPT_DIR>/dev-status.sh — KEY=value status of all selected services + tmux + chrome

6. <SCRIPT_DIR>/dev-stop.sh — kill server processes (lsof -ti + kill) + tmux kill-session

7. <SCRIPT_DIR>/dev-start.sh — start all services:

   • If RUNNER=tmux: create detached tmux session with one pane per service, set pane titles to service:port
   • If RUNNER=concurrently: concurrently with named processes
   • If RUNNER=tmux + fallback: try tmux, fall back to concurrently if not on PATH
   • If RUNNER=manual only: print usage instructions only

8. <SCRIPT_DIR>/dev-restart.sh — resolve sibling path via BASH_SOURCE[0], then call stop and start:

   bashCopy code
   #!/usr/bin/env bash
   set -euo pipefail
   SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
   bash "$SCRIPT_DIR/dev-stop.sh"
   exec bash "$SCRIPT_DIR/dev-start.sh"
   

9. <SCRIPT_DIR>/dev-post-checkout.sh — install deps using detected $PM

If GTR=yes, also generate:

1. <SCRIPT_DIR>/gtr-setup.sh — team onboarding script. Configures git gtr hooks for the project (see Step 11).

If CHROME = "Yes — create profile", also generate:

1. <SCRIPT_DIR>/dev-chrome-profile-setup.sh — creates ~/.chrome-profiles/<CHROME_PROFILE_NAME> + ~/.local/bin/<CHROME_PROFILE_NAME> launcher, upserts CHROME_PROFILE + CHROME_CDP_WT_PORT in .env
2. <SCRIPT_DIR>/dev-open-browser.sh — reads dev-status output, opens one tab per running service in Chrome profile

Write .claude/dev-setup.json — create or overwrite with two keys:

• scriptDir: the script directory chosen in Q4 (e.g. tools/dev)

• services: an object mapping each selected service's port variable to its start command, derived from the services selected in Call A and the detected start commands from Step 3. Example:

  jsonCopy code
  {
    "scriptDir": "tools/dev",
    "services": {
      "API_WT_PORT":  "pnpm dev:api",
      "WEB_WT_PORT":  "pnpm dev:web"
    }
  }
  

  Do not include wtPattern. Do not include Chrome or tmux config — services covers server processes only.

Step 9: Update package.json

Add to the scripts object using the Edit tool. Skip any key that already exists and note the conflict. Do not reformat the entire file — use a targeted edit on the scripts block only.

Step 10: Update .env.example

Build the expected port variables from SELECTED_SERVICES and the ports detected in Step 3:

bashCopy code
# Only include variables for selected services:
API_WT_PORT=3000              # if api selected
WEB_WT_PORT=5173              # if web selected
STORYBOOK_WT_PORT=61000       # if storybook selected
TTYD_WT_PORT=7681             # if ttyd selected

# Only if CHROME = "Yes — create profile":
CHROME_PROFILE=<CHROME_PROFILE_NAME>
CHROME_CDP_WT_PORT=<CHROME_CDP_PORT>

If .env.example does not exist

Create it with a header:

bashCopy code
# Generated by /dev-setup for <project-name>
# Copy to .env and adjust ports if running multiple worktrees

API_WT_PORT=3000
WEB_WT_PORT=5173
...

If .env.example already exists

For each expected variable:

1. Variable not present → append it at the end, under a section comment:

   bashCopy code
   # --- dev-setup managed ports (added <date>) ---
   WEB_WT_PORT=5173
   

2. Variable present with same value → skip (no change needed)

3. Variable present with different value → ask the user with AskUserQuestion:

   Copy code
   question: ".env.example has PORT=8080 but detected service runs on :3000. Update?"
   options:
     - label: "Update to 3000"    description: "Match detected service port"
     - label: "Keep 8080"         description: "Preserve existing value"
   

   If the user chooses to update, replace the value in-place using the Edit tool. If keep, leave it and note the mismatch in the Step 13 summary.

Step 11: Update .gtrconfig (only if GTR=yes)

If .gtrconfig exists, append missing entries. If it doesn't exist, create it.

gitconfigCopy code
[copy]
    include = .env.example

[hooks]
    postCreate = bash <SCRIPT_DIR>/dev-post-checkout.sh
    postCreate = bash <SCRIPT_DIR>/dev-wt-ports.sh

Also create <SCRIPT_DIR>/gtr-setup.sh for team onboarding:

bashCopy code
#!/bin/sh
# One-time setup: configure git gtr hooks for this project
# Run after: git clone + cd into repo
# Usage: bash <SCRIPT_DIR>/gtr-setup.sh
git config --add gtr.copy.include ".env.example"
git config --add gtr.hook.postCreate "bash <SCRIPT_DIR>/dev-post-checkout.sh"
git config --add gtr.hook.postCreate "bash <SCRIPT_DIR>/dev-wt-ports.sh"
echo "✓ git gtr configured for this project"

Step 12: Adaptation review

Before running shellcheck, verify that each generated script is adapted to this project — not a copy of the reference. Read each generated file and confirm:

For each file that fails a check: fix it before proceeding to shellcheck.

Step 12b: Quality gates

After all scripts are written, run validation on every generated .sh file.

shellcheck (required — errors block completion):

bashCopy code
find <SCRIPT_DIR> -name "*.sh" | sort | while read -r f; do
  if shellcheck "$f"; then
    echo "✓ $f"
  else
    echo "✗ $f — fix errors above before proceeding"
  fi
done

• error level: must fix before continuing. Show the exact shellcheck line and suggestion.
• warning/info level: show to user but do not block.
• If shellcheck is missing: print ⚠ shellcheck not found. Install: brew install shellcheck and continue (do not block).

shfmt (optional — apply if available, skip silently if not):

bashCopy code
if command -v shfmt >/dev/null 2>&1; then
  mapfile -t _sh_files < <(find <SCRIPT_DIR> -name "*.sh" | sort)
  if [[ ${#_sh_files[@]} -gt 0 ]]; then
    if shfmt -d "${_sh_files[@]}" | grep -q .; then
      shfmt -w "${_sh_files[@]}"
      echo "✓ shfmt formatting applied"
    else
      echo "✓ formatting already clean"
    fi
  fi
fi

Step 13: Output summary

Print the following summary. Replace <PM>, <SCRIPT_DIR>, and bracket-wrapped optional lines based on what was actually generated.

Copy code
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ Dev setup complete
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Scripts generated in <SCRIPT_DIR>/:
  ✓ dev-allocate-ports.sh  → allocate free ports from pool (20000-29999)
  ✓ dev-start.sh           → <PM> dev:start
  ✓ dev-stop.sh            → <PM> dev:stop
  ✓ dev-restart.sh         → <PM> dev:restart
  ✓ dev-status.sh          → <PM> dev:status
  ✓ dev-post-checkout.sh       → called on git clone / gtr new
  [✓ dev-chrome-profile-setup.sh  → <PM> dev:browser:setup]
  [✓ dev-open-browser.sh      → <PM> dev:browser]
  [✓ dev-wt-ports.sh          → called by git gtr postCreate]
  [✓ gtr-setup.sh             → one-time team onboarding]

Config updated:
  ✓ package.json  (scripts added: dev:start, dev:stop, dev:restart, dev:status)
  ✓ .env.example  (port vars added)
  [✓ .gtrconfig   (postCreate hooks added)]
  [✓ gtr-setup.sh  (team onboarding script — run on each contributor's machine)]

Next steps:
  1. cp .env.example .env  (adjust ports if running multiple worktrees)
  2. <PM> dev:start
  [3. <PM> dev:browser:setup  (first-time Chrome profile setup)]
  [4. bash <SCRIPT_DIR>/gtr-setup.sh  (on each team member's machine)]

If Context7 MCP tools (mcp__plugin_context7_context7__*) were NOT available during this session, also print:

Copy code
Tip: Add Context7 for richer doc lookups next time:
  claude mcp add --transport http context7 https://mcp.context7.com/mcp
  (free, no API key required)