claude-code-ultimate-guide

Clean up stale git worktrees with merged branch detection and disk usage report

Safely remove a git worktree with branch cleanup and safety checks

Create isolated git worktrees for feature development without switching branches

Check status of background verification tasks running in a git worktree

Perform a comprehensive code review of a pull request

Display native sandbox status, configuration, and recent violations

Interactive coach that asks 4-5 questions to determine whether you need an agent, command, skill, hook, or rule, then generates a ready-to-use template. Usage: /scaffold (no arguments needed, starts the coaching session)

Save the current session state (decisions, modified files, current status, and next steps) to a handoff file for later resume.

Quick configuration security check against known threats database

Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when onboarding to a project with existing agents, after adding new agents to a fleet, or when an orchestrator consistently selects the wrong agent.

Audit Claude Code hooks defined in settings.json files for validity, performance safety, and correctness. Resolves each command against the filesystem, checks exit-code strategy for blocking hooks, flags missing timeouts, and reviews interactive vs async patterns. Use when setting up hooks for the first time, debugging a hook that never fires or hangs the agent, or doing a periodic hooks hygiene pass.

Autonomous improvement loop: scan codebase metrics, scaffold experiment files, run agent-driven iterations until metric improves

Post-deploy monitoring: watch production after a deploy and alert on regressions

Restore context after /clear by summarizing recent work and project state

Launch and navigate the ccboard TUI/Web dashboard for Claude Code. Use when monitoring token usage, tracking costs, browsing sessions, or checking MCP server status across projects.

Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5

Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.

Push current branch and return the pipeline tracking URL (GitLab or GitHub Actions)

Show current pipeline status for the active branch (GitLab CI or GitHub Actions)

Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test)

Generate a conventional commit message for staged changes

Interactive troubleshooting assistant for Claude Code issues

Explain code, concepts, or system behavior with adjustable depth levels

Generate comprehensive tests for specified code

Generate a structured handoff document from the current session. Captures scope, relevant files with line numbers, key discoveries, work completed, current status, next steps, and code snippets. Use before ending a session or handing work to another agent.

Systematic root-cause debugging: find the cause before writing any fix

Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.

Test understanding of recently written or accepted code

Step-by-step explanation of a concept with progressive depth

Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack

Analyze and suggest performance improvements for code, queries, or systems

Strategic product gate: challenge the brief, find the 10-star product hiding inside the request, before writing any code

Engineering architecture gate: lock architecture, diagrams, edge cases, and test matrix before writing implementation code

Execute a validated plan: worktree isolation, TDD scaffolding, level-based parallel agents, quality gate with smoke test, PR creation and merge. Handles everything through to merged PR.

Orchestrates the complete planning pipeline: product direction (ceo-review) -> architecture (eng-review) -> implementation plan (start) -> validation (validate) -> execution (execute). Run stages individually or let the orchestrator coordinate the full flow.

5-phase planning: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.

2-layer plan validation: instant structural checks + trigger-based specialist agents. Auto-fixes issues using ADRs and first principles. Every issue must be resolved before execution.

Analyze changes, detect scope issues, and create a well-structured PR

Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop

Template for commands that implement a structured recipe: validate preconditions, then execute numbered steps. Fork this and replace the placeholder content. The 'Context Validation Checkpoints' section is the key pattern, forcing Claude to verify preconditions before starting.