health-cleanup
The health-cleanup command executes an inline dead code detection and removal workflow without spawning a separate orchestrator agent. Use this to identify unused code through the dead-code-hunter worker, remove it by priority using the dead-code-remover worker, and verify changes with type checking and build quality gates across a maximum of three iterations.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/maslennikov-ig/claude-code-orchestrator-kit/HEAD/.claude/commands/health-cleanup.md -o ~/.claude/commands/health-cleanup.mdhealth-cleanup.md
# Cleanup Health Check Execute the `cleanup-health-inline` skill for inline orchestration. **You ARE the orchestrator.** Do not spawn a separate orchestrator agent. ## Quick Start 1. Read `.claude/skills/cleanup-health-inline/SKILL.md` 2. Follow the workflow phases directly 3. Use Task tool only for workers (dead-code-hunter, dead-code-remover) 4. Run quality gates inline via Bash ## Workflow Summary ``` Pre-flight → Detect → [Remove by Priority] → Verify → Report ``` **Workers**: dead-code-hunter, dead-code-remover **Quality gates**: `pnpm type-check && pnpm build` **Max iterations**: 3 --- Now read and execute the skill: `.claude/skills/cleanup-health-inline/SKILL.md`
Initialize Beads issue tracking in your project with interactive configuration setup.
Inline orchestration workflow for automated bug detection and fixing with Beads integration. Provides step-by-step phases for bug-hunter detection, history enrichment for priority bugs, priority-based fixing with bug-fixer, and verification cycles.
Dependency audit and update workflow (inline orchestration)
Code duplication detection and consolidation workflow (inline orchestration)
Security vulnerability detection and remediation workflow (inline orchestration)
Connect any project to Gastown multi-agent orchestration
Process error logs from admin panel - fetch new errors, analyze, create tasks, fix, and mark resolved
Automated release management with version bumping and dual changelog generation