director-mode-lite

Guided 5-minute onboarding for Director Mode Lite. Use immediately after installing Director Mode Lite, or when unsure which command to run next.

Self-Evolving Development Loop - Dynamic skill generation with learning and evolution

View Self-Evolving Loop session status, history, and memory metrics

Automatically routes tasks to external AI CLIs (Codex or Gemini) when more efficient; routing decisions are made automatically based on task type, with no manual commands needed. Use when a task is a large refactor, a batch operation, or needs 100K+ tokens of context better handled by an external CLI.

Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.

Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.

List all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.

TDD-based autonomous development loop with checkpoint recovery and observability changelog

View and manage the runtime changelog for observability

Verify the development environment is ready for Director Mode: claude CLI, git, python3, jq, project runtime, and installed skills/agents/hooks. Use after installation, when hooks or skills misbehave, or when the user runs /check-environment.

Code review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.

Systematic debugging method: 5-step root-cause analysis (capture, isolate, hypothesize, investigate, fix & verify) plus common bug-pattern reference. Use when errors, exceptions, test failures, or unexpected behavior appear. Loaded automatically by the debugger agent.

Documentation templates and standards: README structure, API reference format, changelog (Keep a Changelog), and comment guidelines. Use when creating or updating documentation. Loaded automatically by the doc-writer agent.

Deeply scope a problem before coding: parallel Explore agents map related files, similar implementations, and test patterns, producing a problem definition, boundaries, and minimal implementation plan. Use when planning a feature, investigating a bug, or entering an unfamiliar codebase area.

Delegate tasks to other authorized Claude Code instances (separate accounts/profiles like claude-z-1, claude-z-2) via headless `claude -p`. Use when you need parallel execution on a second account's quota, account isolation, or background workers that don't consume this session's context.

Delegate bulk mechanical tasks (mass refactors, template generation, simple batch edits) to OpenAI Codex CLI via non-interactive `codex exec`, preserving Claude context. Use when the user says 'use codex'/'hand off to codex' or a task is 10+ files of mechanical changes.

Delegate long-context analysis, research, and large-document summarization to Google Gemini CLI (1M-token context) via non-interactive `gemini -p`, preserving Claude context. Use when the user says 'use gemini'/'hand off to gemini' or a task needs 100K+ tokens of context.

Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.

Validate hooks configuration and scripts. Use after adding or editing hooks in settings.json, before committing hook changes, or when a hook fails to fire.

Validate MCP configuration and suggest improvements. Use when MCP servers fail to load, after editing .mcp.json, or when the user runs /mcp-check.

Break a complex task into an ordered, dependency-aware task list with estimates and verification steps. Use when a request spans multiple components or days, before starting large features, or when the user runs /plan.

Audit project health across 7 dimensions (documentation, test coverage, security, code quality, dependencies, database, build/deploy) producing a scored report with prioritized fixes. Use for periodic checkups, before releases, or when the user runs /project-health-check.

Set up Director Mode in a project: detect language/framework, generate CLAUDE.md, configure agents/skills/hooks and MCP, and verify the install. Use on first setup of a project, after cloning, or when the user runs /project-init.

Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.

Generate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.

List all available skills grouped by category. Use when the user asks what skills are available or runs /skills.

Create clean Conventional Commits: inspect the diff, group related changes, run quality checks, and write type(scope) messages. Use when committing work, or when the user runs /smart-commit or asks to commit changes.

Drive one feature through a strict TDD Red-Green-Refactor cycle with checklists for each phase. Use when implementing new functionality test-first, or when the user runs /test-first.

Test execution reference: framework detection (pytest/jest/vitest/go/cargo/junit) and correct run/coverage commands, plus failure-analysis steps. Use when running tests, analyzing test failures, or verifying coverage after code changes.

Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.

Track development session events in a daily markdown changelog, including file changes, test results, and key decisions.

Validate CLAUDE.md structure and completeness

Generate CLAUDE.md template for current project