OrodruinLabs

OrodruinLabs/nazgul

Plugin Claude Code

Plugin marketplace listing 1 plugin: nazgul.

OrodruinLabs/nazgul

Plugin Claude Code

Multi-agent autonomous development loop with review pipeline, context management, and parallel execution.

OrodruinLabs/nazgul

Settings file Claude Code

Multi-agent autonomous development loop for Claude Code — 17 agents, review pipeline, context management, and parallel execution.

OrodruinLabs/nazgul

Instructions file

Claude Code instructions for OrodruinLabs/nazgul, covering claude.md — nazgul framework plugin, what this project is, directory structure, build rules and code style.

OrodruinLabs/nazgul

Agent

Generates and maintains CI/CD pipelines — GitHub Actions, GitLab CI, or detected CI system. Handles build, test, lint, security scan, and deploy stages.

OrodruinLabs/nazgul

Agent

Adversarial post-loop verifier — grades the QUALITY of inline source doc-comments (XML , JSDoc, docstrings, shell doc headers) on files changed this objective for templated, restatement, and contradiction defects, and writes the objective-scoped completion marker required by the stop-hook comment-verifier gate.

OrodruinLabs/nazgul

Agent

Generates safe database migrations with rollback plans, validates data integrity, and handles zero-downtime migration patterns.

OrodruinLabs/nazgul

Agent

Investigates repeated task failures — traces root causes, analyzes review feedback, and writes diagnosis for the implementer.

OrodruinLabs/nazgul

Agent

Generates design system, component specs, and visual direction for this project. Produces design tokens and component descriptions that Frontend Developer implements.

OrodruinLabs/nazgul

Agent

Generates and maintains infrastructure configuration — Docker, Kubernetes, cloud resources, environment setup, and deployment configurations.

OrodruinLabs/nazgul

Agent

Scans codebase to build project profile and generate tailored reviewer, specialist, and post-loop agents.

OrodruinLabs/nazgul

Agent

Generates project documents (PRD, TRD, ADR, test plan, etc.) based on project classification and objective. Runs after Discovery, before Planning.

OrodruinLabs/nazgul

Agent

Adversarial post-loop verifier — cross-checks generated docs and CHANGELOG against source (event names, config keys, commands, scripts, schema versions) and writes the objective-scoped completion marker required by the stop-hook doc-verifier gate.

OrodruinLabs/nazgul

Agent

Updates project documentation after tasks complete — README, API docs, changelog, JSDoc/docstrings, migration guides.

OrodruinLabs/nazgul

Agent

Consolidates review feedback from all reviewers into one actionable document with prioritized, specific fix instructions.

OrodruinLabs/nazgul

Agent

Implements UI components, pages, and client-side logic following the project's frontend patterns and design system.

OrodruinLabs/nazgul

Agent

Implements one task at a time following project patterns and reviewer feedback.

OrodruinLabs/nazgul

Agent

Distills recurring mistakes (review rejections, debugger diagnoses, repeated test failures) into candidate Learned Rules. Proposes only — never approves. Run by /nazgul:learn and the post-loop phase.

OrodruinLabs/nazgul

Agent

Implements mobile-specific features, platform APIs, navigation, and responsive layouts for React Native, Flutter, or native iOS/Android projects.

OrodruinLabs/nazgul

Agent

Ensures new code has appropriate logging, error tracking, metrics, and alerting.

OrodruinLabs/nazgul

Agent

Decomposes objectives into dependency-ordered, independently reviewable tasks with explicit file scopes and acceptance criteria.

OrodruinLabs/nazgul

Agent

Manages versioning, changelog generation, release notes, and git tags after objective completion.

OrodruinLabs/nazgul

Agent

Orchestrates the review board — runs pre-checks, delegates to reviewers, collects verdicts, manages task state transitions.

OrodruinLabs/nazgul

Agent

Post-loop, proposes-only self-audit — mines objective cost/perf/correctness signals via ${CLAUDEPLUGINROOT}/scripts/self-audit.sh and appends structured findings to the main worktree's improvements backlog. Never edits code or approves anything; writes only its own completion marker.