By tstomtimes
A multi-agent orchestration layer for Claude Code. Coordinates specialized subagents (UI, API, Data, Integration, QA, etc.) using declarative skill and policy mappings.
Release manager for deployment coordination and lifecycle management. Use this agent proactively when deploying to staging/production, rolling back releases, preparing release notes/changelogs, coordinating hotfixes, or managing sprint releases. Orchestrates pipeline execution and ensures safe deployment procedures.
Documentation lead for technical writing and knowledge sharing. Use this agent proactively after implementing features/changes, post-deployment, when creating ADRs/runbooks/onboarding materials, or when stakeholders need technical summaries. Creates READMEs, operational guides, and handover docs for cross-team collaboration.
QA and testing specialist for automated validation. Use this agent proactively when features need test coverage, tests are flaky/failing, coverage validation needed before PR/merge, release candidates need smoke/regression testing, or performance thresholds must be validated. Designs unit/integration/E2E tests. Skip if requirements unresolved.
Security auditor for sensitive changes. Use this agent proactively when code touches auth/secrets, integrates third-party APIs, updates dependencies, adds env variables, or before PR/merge. Reviews secret handling, permissions, vulnerabilities, and security policies. Skip for pure docs/UI without backend changes.
System architect for structural decisions and design. Use this agent proactively when features impact architecture/performance/security, multiple services/modules need coordination, refactoring/migrations need planning, dependency choices require evaluation, or before PRs with architectural changes. Documents ADRs and trade-offs.
Automatically create professional git commits after completing agent tasks with semantic commit messages.
Core development principles and guidelines covering security, QA, performance, documentation, and coding standards. Used by all agents to ensure consistent quality across the Orchestra system.
Domain-specific development mode guidelines for UI, API, database, integration, migration, and specialized workflows. Each mode provides tailored principles, checklists, and patterns for different types of development work.
Safely navigate, interact with, and capture evidence from web pages using automated browser operations.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Turn Claude Code into a semi-autonomous development team with specialized AI agents, automated quality gates, and seamless integrations.
English | 日本語
🔒 Security: Orchestra Plugin uses automated hooks with built-in safety guards. Dangerous operations are automatically blocked. See docs/SECURITY.md for details.
Just use Claude Code as you normally would. No new commands to learn, no complex workflows. Orchestra Plugin works quietly in the background:
It just works. Install once, code naturally.
Orchestra Plugin requires MCP servers to be set up locally. Follow these steps:
git clone https://github.com/tstomtimes/orchestra.git
cd orchestra
cp .env.example .env
# Edit .env with your GitHub token (required) and optional service tokens
./setup.sh
This installs:
Alternatively, you can run the setup from within Claude Code:
/orchestra-setup
In Claude Code, run:
/plugin marketplace add /path/to/orchestra
/plugin install orchestra
Replace /path/to/orchestra with the full path to your cloned repository.
Restart Claude Code to activate all features.
After installing the Orchestra Plugin, configure each project where you want to use it:
Copy the .claude/settings.json file from the Orchestra repository:
# In your project directory
cd /path/to/your-project
# Create .claude directory if it doesn't exist
mkdir -p .claude
# Copy Orchestra settings
cp /path/to/orchestra/.claude/settings.json .claude/settings.json
IMPORTANT: Edit .claude/settings.json and update the path to point to your Orchestra installation:
{
"extraKnownMarketplaces": {
"orchestra-marketplace": {
"source": {
"source": "directory",
"path": "/absolute/path/to/orchestra" ← Update this!
}
}
}
}
Replace /absolute/path/to/orchestra with the full path where you cloned the Orchestra repository.
What this enables:
/browser, /screenshot, /orchestra-setup)Restart Claude Code to apply the configuration.
All Orchestra features are now available in your project:
/browser, /screenshot, /orchestra-setup)Important: The plugin's hooks, agents, and commands work automatically. No additional files needed in your project. Just copy .claude/settings.json and you're done.
Use Claude Code exactly as before. Orchestra Plugin enhances everything automatically:
You: "Add a user profile page with avatar upload"
→ Claude Code breaks down and coordinates the task
→ Mina (Frontend) handles UI implementation
→ Eden (QA) validates quality
→ Iris (Security) checks for vulnerabilities
→ Pre-merge hooks ensure everything passes
→ Changelog and docs generated automatically
Orchestra automatically initializes persistent project knowledge that survives Claude Code session restarts.
What is Memory Bank?
npx claudepluginhub tstomtimes/orchestraMulti-agent orchestrator — supervisor loop that launches agents to implement plans
Context-optimized task orchestration for AI agents. Decomposes complex tasks into a DAG and dispatches focused sub-agents with minimal context prompts.
Context management and multi-agent orchestration with performance optimization tools
Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)
Multi-agent orchestration for complex tasks using cc-mirror tasks and TodoWrite. Use when tasks require parallel work, multiple agents, sophisticated coordination, or decomposition into parallel subtasks.
Conductor v3 — Multi-agent orchestration with Evaluate-Loop, parallel execution, Board of Directors, and bundled SupaConductor skills for Claude Code