Stats
Actions
Tags
From ork
Configures OrchestKit plugin settings, MCP servers, hook permissions, and keybindings via interactive wizard. Supports presets like Complete or Lite for skills, agents, and hooks customization.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ork:configurehaikuThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Interactive setup for customizing your OrchestKit installation.
Interactive setup for customizing your OrchestKit installation.
/ork:configure
/ork:configure mcp memory
PRESET = "$ARGUMENTS[0]" # Optional preset name or subcommand, e.g., "mcp"
TARGET = "$ARGUMENTS[1]" # Optional target, e.g., "memory"
# If no arguments, run interactive wizard.
# $ARGUMENTS is the full string (CC 2.1.59 indexed access)
Use AskUserQuestion:
| Preset | Skills | Agents | Hooks | Description |
|---|---|---|---|---|
| Complete | 91 | 31 | 96 | Everything |
| Standard | 91 | 0 | 96 | Skills, no agents |
| Lite | 10 | 0 | 96 | Essential only |
| Hooks-only | 0 | 0 | 96 | Just safety |
| Monorepo | 91 | 31 | 96 | Complete + monorepo detection |
Categories available:
Product Agents (2):
Technical Agents (17):
Operations Agents (6):
Research Agents (4):
Safety Hooks (Always On):
Toggleable Hooks:
CC 2.1.49 Managed Settings: OrchestKit ships plugin
settings.jsonwith default hook permissions. These are managed defaults — users can override them in project or user settings. Enterprise admins can lock managed settings via managed profiles.
All 5 MCPs ship enabled by default. Tavily requires an API key; agentation requires a local package install.
| MCP | Purpose | Default | Requires |
|---|---|---|---|
| context7 | Library documentation | enabled | Nothing |
| memory | Cross-session persistence | enabled | Nothing |
| sequential-thinking | Structured reasoning for subagents | enabled | Nothing |
| tavily | Web search + extraction | enabled | API key (free tier: app.tavily.com) |
| agentation | UI annotation tool | enabled | npm install agentation-mcp |
Why all enabled? OrchestKit ships 30+ Sonnet/Haiku subagents. While Opus 4.6 has native extended thinking, Sonnet and Haiku do not — they benefit from sequential-thinking. Tavily and agentation are used by specific agents (see
mcpServersin agent frontmatter). CC's MCPSearch auto-defers schemas when overhead exceeds 10% of context, so token cost is managed automatically.
Background agents: MCP tools are NOT available in background subagents (hard CC platform limitation). Agents that need MCP tools must run in the foreground.
Already have these MCPs installed globally? If Tavily or memory are already in your ~/.claude/mcp.json, skip enabling them here to avoid duplicate entries. OrchestKit agents will use whichever instance Claude Code resolves first.
Opt out of claude.ai MCP servers (CC 2.1.63+): Claude Code may load MCP servers from claude.ai by default. To disable this and only use locally-configured MCPs:
export ENABLE_CLAUDEAI_MCP_SERVERS=false
Add to your shell profile (~/.zshrc or ~/.bashrc) to persist across sessions. This only affects MCP servers sourced from claude.ai — locally-configured MCPs in .mcp.json and ~/.claude/mcp.json are unaffected.
Load details: Read("${CLAUDE_SKILL_DIR}/references/cc-version-settings.md") for full configuration options.
Covers CC 2.1.7 (MCP deferral threshold, effective context window), CC 2.1.20 (task deletion, PR enrichment, agent permissions, monorepo detection, team distribution), CC 2.1.23 (spinner verbs customization), and CC 2.1.79 (turn duration display).
Configure dual-channel telemetry for streaming session data to HQ or your own API.
AskUserQuestion(questions=[{
"question": "Set up session telemetry?",
"header": "Telemetry",
"options": [
{"label": "Full streaming (Recommended)", "description": "All 18 events stream via native HTTP + enriched summaries"},
{"label": "Summary only", "description": "SessionEnd and worktree events only (command hooks)"},
{"label": "Skip", "description": "No telemetry — hooks run locally only"}
],
"multiSelect": false
}])
AskUserQuestion(questions=[{
"question": "What is your webhook endpoint URL?",
"header": "Webhook URL",
"options": [
{"label": "Custom URL", "description": "Enter your API endpoint (e.g., https://api.example.com/hooks)"}
],
"multiSelect": false
}])
npm run generate:http-hooks -- <webhook-url> --write
# File: .claude/orchestration/config.json
saveConfig({ webhookUrl: "<webhook-url>" })
Set ORCHESTKIT_HOOK_TOKEN in your environment (never in config files):
export ORCHESTKIT_HOOK_TOKEN=your-secret
Two channels now active:
Channel 1 (HTTP): All 18 events → /cc-event (Bearer auth, zero overhead)
Channel 2 (Command): SessionEnd → /ingest (HMAC auth, enriched data)
Save webhookUrl to config and remind about env var (same as above, skip generator step).
Load Read("${CLAUDE_SKILL_DIR}/references/http-hooks.md") for architecture details.
Load details: Read("${CLAUDE_SKILL_DIR}/references/integrations.md") for full integration setup steps.
Covers Agentation UI annotation tool (npm install, MCP config, component scaffold, CSP updates). All steps are idempotent.
Tip (CC 2.1.69+): After saving configuration changes, run
/reload-pluginsto activate them without restarting your session.
Save to: ~/.claude/plugins/orchestkit/config.json
{
"version": "1.0.0",
"preset": "complete",
"skills": { "ai_ml": true, "backend": true, ... },
"agents": { "product": true, "technical": true },
"hooks": { "safety": true, "productivity": true, ... },
"mcps": { "context7": false, ... }
}
VSCode users can run /remote-control to bridge their terminal session to claude.ai/code. This lets you continue the same session from a browser or phone — useful for monitoring long-running configurations or agent tasks away from your desk.
ork:doctor: Diagnose configuration issuesLoad on demand with Read("${CLAUDE_SKILL_DIR}/references/<file>"):
| File | Content |
|---|---|
references/presets.md | Preset definitions |
references/mcp-config.md | MCP configuration |
references/http-hooks.md | CC 2.1.63+ observability hooks (Langfuse, Datadog, custom endpoints) |
references/cc-version-settings.md | CC 2.1.7, 2.1.20, 2.1.23, 2.1.79 version-specific settings |
references/integrations.md | Optional third-party integrations (Agentation) |
npx claudepluginhub yonatangross/orchestkit --plugin orkRuns OrchestKit onboarding wizard: scans codebase for stack detection, configures plugins interactively, generates readiness score and improvement plan. Use for new projects, rescans, or config.
Installs Claude-Code-Tunnels Project Orchestrator into the project directory, verifies Python 3.10+, registers workspaces, connects messenger channels. Invoke via /claude-code-tunnels:setup-orchestrator.
Orchestrates multi-phase workflows chaining foundational task skills (git-wrapup, release-and-publish, maintenance, etc.) for MCP server projects. Routes user intent to workflow files for greenfield builds, maintenance, or fix-and-release.