From itisagentready
Run the full audit → fix → redeploy → rescan loop for a target site using the agent-site-orchestrator engine.
How this command is triggered — by the user, by Claude, or both
Slash command
/itisagentready:orchestrate <url> [--dry-run]The summary Claude sees in its command listing — used to decide when to auto-load this command
# /orchestrate Top-level entry point. Drives one site from its current state to Agent-Native using the orchestrator engine (`scripts/orchestrate.py`). Steps: 1. Spawn the **orchestrator** subagent (worktree-isolated, Opus). It owns the run. 2. Baseline: `scan-site-bulk` + `agent-readiness-probe` → write pre scores to `site.yaml`. 3. Monolithic mcp-foundation generate pass → staging. 4. For each of the 20 generators in manifest order: activate its artifact group, **checkpoint before the first deploy of the domain**, deploy, run the `agent-readiness-probe` gate (Decision 1). A failed...
Top-level entry point. Drives one site from its current state to Agent-Native
using the orchestrator engine (scripts/orchestrate.py).
Steps:
scan-site-bulk + agent-readiness-probe → write pre scores to site.yaml.agent-readiness-probe gate (Decision 1). A failed gate halts and hands off
to the fixer subagent; the chain resumes from run.resumable_from.design_hints into the presentation layer (Decision 3).scan-site-bulk (target 100/100) + agent-readiness-probe (every
handshake live). Persist site.yaml; write evidence to
docs/orchestrator-runs/{url-slug}/.$ARGUMENTS — target URL, optional --dry-run (no deploy, probe skipped).
Deploy is the only external action and is checkpointed: never deploy a domain's first push without explicit human confirmation (mandate CHECKPOINT PROTOCOL).
npx claudepluginhub mahoneycontextprotocol/mahoneycontextprotocol --plugin itisagentready/orchestrateGenerates test orchestration configs for staged workflows with dependencies, parallel execution, smart selection of affected tests, retries, and CI/CD optimization.
/orchestrateDecomposes complex tasks into ordered sub-tasks with dependencies and parallel execution, tracks progress and failures, verifies results, and outputs a status summary table.
/orchestrateAnalyzes complex user requests, splits them into steps, assembles agent teams, executes with verification, and retries up to 5 times per step on failure.
/orchestrateOrchestrates parallel task execution via Agent Teams API, parsing prompt_plan.md tasks, analyzing dependencies, and coordinating across Node.js, Python, Rust, Go, .NET projects.
/orchestrateOrchestrates sequential agent workflows for complex tasks like feature development, bug fixes, refactoring, and security reviews, producing handoff documents between agents and a final report.
/orchestrateRoutes arguments to orchestration subcommands for multi-agent workflows: menu, help, explain, examples, templates, or inline syntax execution with visual feedback.