setup
Claude Code infrastructure + agent team setup — rules, hooks, memory, routing, and agent installation from a guided interview. Combines infrastructure + agent team into one flow. Not project scaffolding (CLAUDE.md/ROADMAP/.gitignore/.env.example) — use project-init for that. Triggers: /setup, setup, harness setup, agent team setup.
AlexZio00 · AI review on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add AlexZio00/sovereign-skills --skill setupAbout this skill
skill_type: infrastructure tools: Read, Write, Edit, Bash, WebFetch, Agent triggers:
- "/setup"
- "setup"
- "rules 만들어"
- "harness 설정"
- "harness setup" name: setup description: "Claude Code infrastructure + agent team setup — rules, hooks, memory, routing, and agent installation from a guided interview. Combines infrastructure + agent team into one flow. Not project scaffolding (CLAUDE.md/ROADMAP/.gitignore/.env.example) — use project-init for that. Triggers: /setup, setup, harness setup, agent team setup." user_invocable: true concurrency_profile: read_only: false concurrency_safe: false destructive: low not_for:
- "Existing harness audit -> project-check"
- "Single rule addition -> edit the rule file directly"
- "Project scaffolding (CLAUDE.md/ROADMAP/.gitignore/.env.example) -> project-init" see_also:
- skill: project-check relation: "setup=new project, project-check=existing audit"
- skill: project-init relation: "setup=AI harness/agent team setup, project-init=project scaffolding (separate skill)"
Setup — Claude Code Infrastructure + Agent Team
Dominant Variable
Does the initialized harness work immediately? — rules/hooks/memory/routing must be applied from the first session after installation. If "installed but not working" occurs, that is failure.
Purpose
Set up the full Claude Code harness layer — rules, hooks, memory, agent routing.
Not project scaffolding (use /project-init for that). This is the AI orchestration layer.
Key difference from generic templates: domain presets provide pre-filled rules with real content, not empty skeletons. Every harness includes reject-by-default and violation testing.
Dominant variable: Do the generated project rules' Tier 0 rules pass violation testing? — Rules without tests are decoration. Discard if: A complete harness already exists and only a single rule addition is needed — edit that rule file directly.
Trigger
/setup- "rules 만들어"
- "harness 설정"
- "harness setup"
Key Assumptions
- Write permission on
~/.claude/directory — If broken: guide on permissions. - No existing rules/hooks, or overwrite is approved — If broken: resolve conflicts, then proceed.
Phase 0: Prerequisites
Existing File Check (overwrite protection)
Check each target file before generating:
| File | If exists |
|---|---|
~/.claude/rules/project rules | Read it. Offer: update (extend) or replace. Default: update. |
~/.claude/rules/agents.md | Read it. Merge new agent definitions, never replace existing ones. |
~/.claude/rules/output-style.md | Read it. Offer: update or replace. |
~/.claude/settings.json (hooks) | Always merge — append to existing arrays, never overwrite. |
memory/MEMORY.md | Read it. Append new sections, preserve existing entries. |
tasks/lessons.md | If exists → read it. Contains AI behavior correction rules from past sessions. |
Merge algorithm for hooks (settings.json):
1. Read existing settings.json
2. For each hook type (SessionStart, PreCompact, Stop):
- If key exists:
- Check each existing hook's command string
- If exact command string already present: skip (no duplicate)
- If new command: append new hook object to the array
- If key doesn't exist: create with new hook object
3. Write merged result back
Never replace the entire hooks object. Never delete existing hook entries.
Check if CLAUDE.md exists in the project root.
- If yes → read it for context (Hard Rules, stack, conventions)
- If no → recommend running
/project-initfirst, but don't block
Hard Rules conflict check (if both CLAUDE.md and ~/.claude/rules/project rules exist):
- Extract Hard Rules from CLAUDE.md
- Compare with Tier-0 rules in project rules
- If divergent:
- Rules in CLAUDE.md not in project rules → propose adding them to project rules
- Rules in CLAUDE.md weaker than project rules → flag: "CLAUDE.md has a weaker version, remove it"
- If identical or CLAUDE.md just has a reference link → no action needed
- Recommended outcome: CLAUDE.md contains only
Hard Rules → see [.claude/rules/project rules](.claude/rules/project rules), actual rules live only in project rules
Check if ~/.claude/ global structure exists.
- Read existing rules to detect conflicts before generating.
- If no global rules exist → this will be the first setup.
Phase 1: Domain Selection (determines everything else)
Q1 — Domain Preset
What kind of system are you building?
1. Trading / Finance — no-action default, no fabrication, paper-only
2. Web Application — secrets protection, input validation, auth-first
3. CLI Tool / Automation — idempotent operations, dry-run default
4. Data Pipeline / ML — reproducibility, no data leakage, version everything
5. General — start minimal, add rules as needed
6. Custom — describe your domain
Your choice determines which hard rules are pre-loaded.
You can add, modify, or remove any of them afterward.
After Q1, load the matching preset (see Presets section below). Show the user what's pre-loaded and ask: "Anything to add, change, or remove?"
Q2 — Agent Complexity (adapts based on Q1)
How complex is your AI agent setup?
- Minimal: rules + memory only. No agent routing.
→ Generates: rules/, memory/, hooks. Done.
- Standard: review agents (code review, testing, verification).
→ Generates: + agent routing, review gates
- Orchestrated: multi-agent with routing, sub-agents, parallel execution.
→ Generates: + agent definitions, tier priorities, keyword triggers, scope boundaries
If Q2 = Minimal → skip Q3. Go to Phase 2. If Q2 = Standard → ask Q3 simplified. If Q2 = Orchestrated → ask Q3 full.
Q3 — Review Gates (only if Q2 >= Standard)
Standard version:
Which review steps before code ships?
- Basic: code review only
- Standard: code review + verification checklist
- Strict: code review + security + v
Read the complete source ↗