orchestrate — Claude Code command: what it does, how to install
orchestrate routes a complex task through a sequence of agents and combines their findings into a report. Choose a workflow for a feature, bug fix, refactor, or security review.
MIT ★ 6,739 updated 2026-01-23
/plugin marketplace add WorldFlowAI/everything-claude-code
/plugin install everything-claude-code@everything-claude-codeWhat orchestrate does
Run /orchestrate with a workflow type and task description. The feature path moves from planning to test-led implementation, code review, and a security check. Bug fixes start with investigation; refactoring starts with an architect.
Agents pass context forward in handoff documents covering findings, changed files, and unresolved questions. The final report brings together agent summaries, test results, security findings, and a recommendation. You can also define a custom sequence; since its order is explicit, review it before running the task.
Install the plugin with /plugin marketplace add WorldFlowAI/everything-claude-code, followed by /plugin install everything-claude-code@everything-claude-code. The command file in the repository is .claude/commands/orchestrate.md.
What it helps with
- plan and implement a feature through a sequence of agents
- investigate a bug and pass the fix on for review
- check a refactor with tests and code review
- combine security findings into a final report
Example prompts for the agent
- Run the feature workflow to plan and build user authentication.
- Investigate the cache bug and take it through the
bugfixworkflow. - Review the payment code for security issues, then pass the findings to the architect.
How to install orchestrate
1Plugin marketplace
/plugin marketplace add WorldFlowAI/everything-claude-code/plugin install everything-claude-code@everything-claude-code2Manually: put the files in place
.claude/commands/orchestrate.mdCall it with /orchestrate. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/orchestrate.mdCall it with /prompts:orchestrate. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/orchestrate.prompt.mdManually: put the files in place
.gemini/commands/orchestrate.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about orchestrate
How do I install orchestrate in Claude Code?
Run /plugin marketplace add WorldFlowAI/everything-claude-code, then /plugin install everything-claude-code@everything-claude-code. The command file in the repository is .claude/commands/orchestrate.md.
What does orchestrate do?
It sends a task through a chosen sequence of agents and combines their work into a report. Workflows cover feature development, bug fixes, refactoring, and security reviews.
Can I choose my own agent sequence?
Yes. Use custom, list agents separated by commas, and provide a task description, for example /orchestrate custom "architect,tdd-guide,code-reviewer" "Redesign caching layer".
Source text
orchestrate.md · MIT
# Orchestrate Command Sequential agent workflow for complex tasks. ## Usage `/orchestrate [workflow-type] [task-description]` ## Workflow Types ### feature Full feature implementation workflow: ``` planner -> tdd-guide -> code-reviewer -> security-reviewer ``` ### bugfix Bug investigation and fix workflow: ``` explorer -> tdd-guide -> code-reviewer ``` ### refactor Safe refactoring workflow: ``` architect -> code-reviewer -> tdd-guide ``` ### security Security-focused review: ``` security-reviewer -> code-reviewer -> architect ``` ## 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 Format Between agents, create handoff document: ```markdown ## 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] ``` ## Example: Feature Workflow ``` /orchestrate feature "Add user authentication" ``` Executes: 1. **Planner Agent** - Analyzes requirements - Creates implementation plan - Identifies dependencies - Output: `HANDOFF: planner -> tdd-guide` 2. **TDD Guide Agent** - Reads planner handoff - Writes tests first - Implements to pass tests - Output: `HANDOFF: tdd-guide -> code-reviewer` 3. **Code Reviewer Agent** - Reviews implementation - Checks for issues - Suggests improvements - Output: `HANDOFF: code-reviewer -> security-reviewer` 4. **Security Reviewer Agent** - Security audit - Vulnerability check - Final approval - Output: Final Report ## Final Report Format ``` 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] ``` ## Parallel Execution For independent checks, run agents in parallel: ```markdown ### Parallel Phase Run simultaneously: - code-reviewer (quality) - security-reviewer (security) - architect (design) ### Merge Results Combine outputs into single report ``` ## Arguments $ARGUMENTS: - `feature <description>` - Full feature workflow - `bugfix <description>` - Bug fix workflow - `refactor <description>` - Refactoring workflow - `security <description>` - Security review workflow - `custom <agents> <description>` - Custom agent sequence ## Custom Workflow Example ``` /orchestrate custom "architect,tdd-guide,code-reviewer" "Redesign caching layer" ``` ## Tips 1. **Start with planner** for complex features 2. **Always include code-reviewer** before merge 3. **Use security-reviewer** for auth/payment/PII 4. **Keep handoffs concise** - focus on what next agent needs 5. **Run verification** between agents if needed
© Affaan Mustafa · MIT · WorldFlowAI/everything-claude-code