From claude-codex
Orchestrates sequential agent workflows for complex tasks like features, bug fixes, refactoring, and security reviews. Produces handoff documents between agents and a final report with summaries, file changes, tests, and recommendations.
npx claudepluginhub aventerica89/claude-codex --plugin claude-codex# Orchestrate Command Sequential agent workflow for complex tasks. ## Usage `/orchestrate [workflow-type] [task-description]` ## Workflow Types ### feature Full feature implementation workflow: ### bugfix Bug investigation and fix workflow: ### refactor Safe refactoring workflow: ### security Security-focused review: ## Execution Pattern For each agent in the workflow: 1. **Invoke agent** with context from previous agent 2. **Collect output** as structured handoff document 3. **Pass to next agent** in chain 4. **Aggregate results** into final report ## Handoff Document Forma...
/orchestrateServes as legacy shim delegating to dmux-workflows for parallel agent execution with tmux worktrees and autonomous-agent-harness for persistent loops and governance.
/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.
/orchestrateOrchestrates agent teams to execute complex requests: analyzes into steps, runs with verification, auto-retries failures up to 5x per step, escalates to user if needed, and reports outcomes.
/orchestrateOrchestrates parallel task execution from prompt_plan.md using Agent Teams API, analyzing dependencies and running domain-specific build/test/lint. Supports --type, --parallel, --dry-run flags.
/orchestrateRoutes arguments to orchestration subcommands for multi-agent workflows: menu, help, explain, examples, templates, or inline syntax execution with visual feedback.
Sequential agent workflow for complex tasks.
/orchestrate [workflow-type] [task-description]
Full feature implementation workflow:
planner -> tdd-guide -> code-reviewer -> security-reviewer
Bug investigation and fix workflow:
explorer -> tdd-guide -> code-reviewer
Safe refactoring workflow:
architect -> code-reviewer -> tdd-guide
Security-focused review:
security-reviewer -> code-reviewer -> architect
For each agent in the workflow:
Between agents, create handoff document:
## HANDOFF: [previous-agent] -> [next-agent]
### Context
[Summary of what was done]
### Findings
[Key discoveries or decisions]
### Files Modified
[List of files touched]
### Open Questions
[Unresolved items for next agent]
### Recommendations
[Suggested next steps]
/orchestrate feature "Add user authentication"
Executes:
Planner Agent
HANDOFF: planner -> tdd-guideTDD Guide Agent
HANDOFF: tdd-guide -> code-reviewerCode Reviewer Agent
HANDOFF: code-reviewer -> security-reviewerSecurity Reviewer Agent
ORCHESTRATION REPORT
====================
Workflow: feature
Task: Add user authentication
Agents: planner -> tdd-guide -> code-reviewer -> security-reviewer
SUMMARY
-------
[One paragraph summary]
AGENT OUTPUTS
-------------
Planner: [summary]
TDD Guide: [summary]
Code Reviewer: [summary]
Security Reviewer: [summary]
FILES CHANGED
-------------
[List all files modified]
TEST RESULTS
------------
[Test pass/fail summary]
SECURITY STATUS
---------------
[Security findings]
RECOMMENDATION
--------------
[SHIP / NEEDS WORK / BLOCKED]
For independent checks, run agents in parallel:
### Parallel Phase
Run simultaneously:
- code-reviewer (quality)
- security-reviewer (security)
- architect (design)
### Merge Results
Combine outputs into single report
$ARGUMENTS:
feature <description> - Full feature workflowbugfix <description> - Bug fix workflowrefactor <description> - Refactoring workflowsecurity <description> - Security review workflowcustom <agents> <description> - Custom agent sequence/orchestrate custom "architect,tdd-guide,code-reviewer" "Redesign caching layer"