Your first task
A focused tutorial: install → verify → run a real consensus vote → wire it into your editor. About 5 minutes if you have Node 22; less if everything’s already installed.
This is the canonical new-user path. If you want platform-specific install details, jump to INSTALLATION.md. If you want every knob enumerated, jump to CONFIGURATION.md. For Claude Code plugin install specifically, see PLUGIN_INSTALL.md. Everything below stays on the canonical “first 5 minutes” path.
CLI vs MCP — read this first. The standalone CLI surface (
vote,orchestrate,review) is a useful subset you can run from any terminal. The full control plane — therunentry point plus the 46 MCP tools — lives behindsetupand an MCP-aware editor (Claude Code, Cursor, etc.). If you’re an MCP user, the one command to learn isrun "<goal>": it’s read-only by default (passexecute: trueto actually run), and the MetaOrchestrator picks the strategy for you, so you rarely pick a pipeline tool by hand. Noterunis MCP-only — it is not a CLI command.
1. Install
npm install -g nexus-agents
If you hit EACCES on Linux/macOS, configure a user-local npm prefix instead of using sudo (details).
For Claude Code, you can install as a plugin instead:
/plugin install nexus-agents
2. Verify
nexus-agents doctor
Prints a health table (illustrative example output — your versions and counts will differ):
Nexus Agents Doctor
===================
Checking environment...
✓ Node.js version: v22.x.x
⚠ API keys configured: 0 of 3
Set ANTHROPIC_API_KEY, OPENAI_API_KEY, or GOOGLE_AI_API_KEY
Checking CLI installations...
✓ Claude CLI Version: 2.x Auth: CLI auth
✓ Codex CLI Version: 0.x Auth: CLI auth
⚠ Gemini CLI Auth: Not authenticated Fix: gemini
Read-only; safe to run any time. If you have at least one working CLI (claude / codex / gemini), you can run the next step without setting any API keys — nexus-agents will use whatever CLI is configured.
3. Run a real consensus vote (no API keys needed)
nexus-agents vote --quick --proposal "Use SQLite over JSON files for the outcome store"
Three voter roles (architect, security, scope_steward) deliberate via whichever local CLIs you have. Expected output:
Nexus Agents Consensus Vote
============================
Collecting votes from 3 agents (timeout: 60s each)...
Proposal: Use SQLite over JSON files for the outcome store
Votes
✓ Software Architect: APPROVE (86%)
✓ Security Engineer: APPROVE (74%)
✓ Scope Steward: APPROVE (91%)
Summary
Approve: 3
Reject: 0
Abstain: 0
Approval: 100.0%
Threshold: simple_majority
Result: APPROVED
Completed in ~30s
That’s the smoke task. The verdict prints; the vote tally and per-voter confidence are recorded. For the richer 7-voter version (which also demonstrates mixed APPROVE/REJECT outcomes and graceful error handling), see the project site hero.
4. Wire into your editor (optional but recommended)
nexus-agents setup
Auto-configures nexus-agents as an MCP server in Claude Code, Cursor, OpenCode, Gemini, and Codex (whichever you have). Restart the editor; the 46 MCP tools (orchestrate, consensus_vote, research_synthesize, verify_audit_chain, …) become available to whatever agent you’re already using.
setup writes/updates up to seven things — each opt-outtable with the corresponding --skip-* flag. The full breakdown is in the project README; if you’d rather configure one CLI at a time, run setup --interactive (the default).
5. Try a real task
# Run a real orchestration task (uses an API key if available)
export ANTHROPIC_API_KEY=your-key
nexus-agents orchestrate "Explain the architecture of this codebase"
Or via the MCP tool (after setup):
In Claude Code: /orchestrate "Explain the architecture of this codebase"
The multi-stage CompositeRouter picks the right CLI, the right expert persona, and the right model based on task analysis. The trace goes to <repo>/.nexus-agents/traces/ for later replay (traces/ is per-repo state — epic #2872).
nexus-agents writes per-repo state to <repo>/.nexus-agents/ (auto-gitignored and created on first use) and shared, cross-repo state to ~/.nexus-agents/. Run nexus-agents doctor to see the resolved paths for your environment.
Where to go next
| Want to … | Read |
|---|---|
| Chain tools into a goal (research → vote → build) | COMPOSE_YOUR_FIRST_PIPELINE.md |
| Understand the consensus voting strategies | CONSENSUS_PROTOCOLS.md |
| Understand the routing pipeline | ROUTING_SYSTEM.md |
| Configure model preferences, custom experts, sandbox modes | CONFIGURATION.md |
| Wire an editor we don’t auto-detect | ../guides/HARNESS_COMPATIBILITY.md |
| Run the full dev pipeline (research → plan → vote → implement → QA) | run_dev_pipeline MCP tool — see ../ENTRYPOINTS.md |
| Inspect the audit chain | verify_audit_chain MCP tool, or the JSONL under <repo>/.nexus-agents/audit/ |
| Browse the research registry | ../research/RESEARCH_INDEX.md |
| See every CLI command + MCP tool | ../ENTRYPOINTS.md |