Customization
Project Context
Create or update AGENTS.md (created on first run or via /init) with a short project summary:
# Project
## Tech
- Node.js, TypeScript, PostgreSQL
## Standards
- Async/await everywhere
- Tests for new features
- No hardcoded secrets
Agent Configuration
Edit .claude/agents/[agent].md to adjust behavior (model, tools, permission mode, memory).
Custom Commands
Add skill files to .claude/skills/[skill-name]/SKILL.md. Use /skill-name in Claude Code to run user-invocable skills.
Skills
Skills live in .claude/skills/ and are loaded on demand:
project-bootstrapagent-diagnosticsdocs-validationux-responsive
Recommended policy:
- Load skills on demand only when the task clearly matches the domain.
- Use one relevant skill by default; add a second only for explicit cross-domain work.
Security and Permissions
Use .claude/settings.json for team-shared permission rules and hooks. Prefer deny-by-default access to sensitive paths and risky commands. Use PreToolUse hooks for deterministic command/path enforcement.
Scope Policy (Core-only)
Current distribution is intentionally core-only; no optional skill packs are shipped.
When evaluating potential additions, use this gate:
- Repeated demand in real usage
- Clear capability gap vs current core
- Named maintenance owner
- Clean licensing/provenance (or clean-room rewrite)