doctor
SKILL.md
OrchestKit Health Diagnostics
Overview
The /ork:doctor command performs comprehensive health checks on your OrchestKit installation. It auto-detects installed plugins and validates 12 categories:
- Installed Plugins - Detects orkl or ork
- Skills Validation - Frontmatter, references, token budget (dynamic count)
- Agents Validation - Frontmatter, tool refs, skill refs (dynamic count)
- Hook Health - Registration, bundles, async patterns
- Permission Rules - Detects unreachable rules (CC 2.1.3 feature)
- Schema Compliance - Validates JSON files against schemas
- Coordination System - Checks lock health and registry integrity
- Context Budget - Monitors token usage against budget
- Memory System - Graph memory health
- Claude Code Version - Validates CC >= 2.1.47
- External Dependencies - Checks optional tool availability (agent-browser)
- MCP Status - Active vs disabled vs misconfigured, API key presence for paid MCPs
When to Use
- After installing or updating OrchestKit
- When hooks aren't firing as expected
- Before deploying to a team environment
- When debugging coordination issues
- After running
npm run build
Quick Start
/ork:doctor # Standard health check
/ork:doctor -v # Verbose output
/ork:doctor --json # Machine-readable for CI
CLI Options
| Flag | Description |
|---|---|
-v, --verbose |
Detailed output per check |
--json |
JSON output for CI integration |
--category=X |
Run only specific category |
Health Check Categories
Detailed check procedures: See rules/diagnostic-checks.md for bash commands and validation logic per category.
MCP-specific checks: See rules/mcp-status-checks.md for credential validation and misconfiguration detection.
Output examples: See references/health-check-outputs.md for sample output per category.
Categories 0-3: Core Validation
| Category | What It Checks | Reference |
|---|---|---|
| 0. Installed Plugins | Auto-detects orkl or ork, counts skills/agents | diagnostic-checks |
| 1. Skills | Frontmatter, context field, token budget, links | skills-validation |
| 2. Agents | Frontmatter, model, skill refs, tool refs | agents-validation |
| 3. Hooks | hooks.json schema, bundles, async patterns | hook-validation |
Categories 4-5: System Health
| Category | What It Checks | Reference |
|---|---|---|
| 4. Memory | .claude/memory/ exists, decisions.jsonl integrity, queue depth | memory-health |
| 5. Build | plugins/ sync with src/, manifest counts, orphans | diagnostic-checks |
Categories 6-9: Infrastructure
| Category | What It Checks |
|---|---|
| 6. Permission Rules | Unreachable rules detection (CC 2.1.3) |
| 7. Schema Compliance | JSON files against schemas |
| 8. Coordination | Multi-worktree lock health, stale locks |
| 9. Context Budget | Token usage against budget |
Categories 10-12: Environment
| Category | What It Checks | Reference |
|---|---|---|
| 10. CC Version | Runtime version against minimum required | version-compatibility |
| 11. External Deps | Optional tools (agent-browser) | diagnostic-checks |
| 12. MCP Status | Enabled/disabled state, credential checks | mcp-status-checks |
Report Format
See references/report-format.md for ASCII report templates (ork and orkl), JSON CI output schema, and exit codes.
Interpreting Results & Troubleshooting
See references/remediation-guide.md for the full results interpretation table and troubleshooting steps for common failures (skills validation, build sync, memory).
Related Skills
ork:configure- Configure plugin settingsork:quality-gates- CI/CD integrationsecurity-scanning- Comprehensive audits
References
Weekly Installs
45
Repository
yonatangross/orchestkitGitHub Stars
96
First Seen
Jan 22, 2026
Security Audits
Installed on
gemini-cli38
opencode37
claude-code36
github-copilot36
codex36
cursor34