nazgul

NAZGUL

Multi-agent autonomous development loop for Claude Code
Discovery • Planning • Implementation • Review • Repeat

---

Nazgul runs a complete autonomous SDLC pipeline — from scanning your codebase to shipping reviewed code — with 18 core agents plus project-specific reviewers.

What Nazgul Does

• Auto-detects your project — classifies it (greenfield, brownfield, bugfix, refactor, migration) and tailors the pipeline
• Generates docs before code — PRDs, TRDs, and ADRs so agents build with context
• Multi-agent review board — Architect, Security, Code Quality + project-specific reviewers must ALL approve every task
• Fix-first review — auto-fixes mechanical issues (dead code, style), only asks about risky changes (security, architecture)
• Per-stage model routing — assign Opus, Sonnet, or Haiku to each pipeline stage for the right balance of cost, speed, and quality
• Survives interruptions — checkpoints, recovery pointers, session tracking, and hooks mean you can close your laptop and resume later

Install

From the Orodruin Labs marketplace (recommended):

/plugin marketplace add OrodruinLabs/nazgul
/plugin install nazgul

Direct install from GitHub:

/plugin install nazgul@github:OrodruinLabs/nazgul

Manual install (for development or pinning a specific version):

git clone https://github.com/OrodruinLabs/nazgul.git ~/.claude/plugins/nazgul

Update:

/plugin                # Select nazgul → "Update now"

Or enable auto-updates: /plugin → Marketplaces tab → orodruin-labs → Enable auto-update.

Quick Start

[!TIP] 3 commands to get started:

/nazgul:init            # Set up Nazgul for your project
/nazgul:start           # Start the autonomous loop
/nazgul:status          # Check progress anytime

Nazgul auto-detects project state: active work resumes, existing docs trigger planning, fresh projects scan for TODOs/issues/failing tests. Override with /nazgul:start "specific objective".

[!WARNING] Autonomous mode skips all permission prompts:

claude --dangerously-skip-permissions
/nazgul:start --yolo --max 30

Commands

Command	Description
/nazgul:init	First-time setup: discovery, reviewer generation, runtime dirs
/nazgul:start	Smart start/resume — auto-detects state, derives objective
/nazgul:status	Check loop progress, task counts, reviewer board
/nazgul:pause	Gracefully pause at next iteration boundary
/nazgul:task	Task lifecycle: skip, unblock, add, prioritize, list
/nazgul:review	Manually trigger review for a task
/nazgul:log	View run history — iterations, commits, reviews
/nazgul:board	Connect task tracking to GitHub Projects
/nazgul:docs	View or regenerate project documents
/nazgul:config	View and change settings (models, formatter, notifications)
/nazgul:enhance	Research Claude Code releases, propose Nazgul improvements
/nazgul:metrics	View loop performance — velocity, approval rates, self-improvement reports
/nazgul:verify	Human acceptance testing for completed tasks
/nazgul:help	Quick reference for all commands and modes
/nazgul:bootstrap-project	Generate a portable, Nazgul-free bundle (docs + Claude subagents)
/nazgul:learn	Distill recurring mistakes into numbered, human-approved Learned Rules

See /nazgul:help for the full command list and all flags.

Model Routing

Different pipeline stages have different complexity needs. Nazgul lets you assign the right model to each stage: