Development workflow framework — tier-based planning, doc-aware context gathering, RAG-powered search, session tracking, and implementation plan generation
Manage documentation — health, search, stale, scan, validate, fix, create
Explore codebase — topic discovery, flow tracing, component mapping
Execute an approved Implementation Plan by walking through Execution Groups, validating at checkpoints, generating tests, resolving review, and merging.
Initialize Root framework — detect structure, configure, ingest docs
Author PRDs via guided, code-informed requirements elicitation
Use proactively for ALL Tier 1 planning work — writing Implementation Plans, tracing code paths, designing approaches, analyzing risk, or producing Change Manifests. Delegate here before any implementation begins. Trigger words: "plan", "design", "architect", "how should we", "trace", "investigate before changing", "figure out what files", "approach for". Read-only; operates in plan mode and hands off to team-implementer for execution.
Use proactively for ALL code-writing work — implementing features, editing files, fixing bugs, refactoring, adding routes, writing components, running migrations. The main thread should delegate to this agent rather than editing files directly. Trigger words: "implement", "add", "build", "write", "fix", "refactor", "edit", "change", "update the code", "make the changes". Full read/write; follows approved Implementation Plans or task specifications.
Use proactively after ANY implementation work completes and before committing or opening a PR. Validates changes against the Implementation Plan's Change Manifest, runs lint/type-check/tests, and flags deviations. Trigger words: "review", "validate", "check", "before PR", "before commit", "did I miss anything", "second opinion", "audit". Read + run checks only — never writes production code. Run this BEFORE team lead commits for Tier 1 work.
Use proactively whenever production code changes — to author new tests, update existing ones, validate coverage, or fix failing test suites. Trigger words: "test", "tests", "coverage", "vitest", "jest", "playwright", "spec", "write tests for", "missing tests", "test this", "broken tests". Writes tests alongside implementation work; never modifies production code to make it testable. Part of every Tier 1 Execution Group.
Use proactively for ANY backend work — new API routes, middleware changes, auth flows, request validation, background jobs, webhook handlers, or external service integrations. Trigger words: "API", "endpoint", "route", "middleware", "auth", "JWT", "webhook", "background job", "cron", "Express", "server", "backend". Customize this agent for your project's backend stack, middleware, auth patterns, and API conventions.
Use this skill when ingesting or querying documents with MCP local RAG, including `query_documents`, `ingest_file`, `ingest_data`, and CLI bulk ingestion. Covers query refinement, result score interpretation, and source metadata conventions for PDF, HTML, DOCX, TXT, and Markdown. Not for general file operations or SQL/database queries.
Start or continue a Root development session for a GitHub issue. On first invocation classifies tier, loads docs via RAG, and plans. On re-invocation drives the stream through implementation, review, and merge. Also handles orchestration verbs (list, status, approve, run, sync, delete, clean, reset).
Admin access level
Server config contains admin-level keywords
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Development workflow framework for Claude Code and Gemini CLI.
Root provides tier-based planning, doc-aware context gathering, RAG-powered search, multi-feature orchestration, and autonomous issue-to-PR workflows.
1. Add the Marketplace
/plugin marketplace add BrandCast-Signage/root
2. Install the Plugin
/plugin install root@root-plugins --scope local
/reload-plugins
1. Install the Extension
gemini extension install https://github.com/BrandCast-Signage/root
The extension auto-installs its RAG MCP server on first session start.
/root:init
This interactively detects your project structure, asks which directories contain docs and source code, generates root.config.json, installs templates, and ingests your docs into RAG.
| Command | Description |
|---|---|
/root <task> | Start a development session, or continue one. Context gathering, planning, and phase-aware orchestration in a single command. |
/root <verb> | Orchestration verbs: list, status, approve, run, sync, delete, clean, reset |
/root:init | Interactive project setup |
/root:prd [action] | PRD authoring: new, edit, review, list |
/root:impl [action] | Execute a plan: run, resume, status, finalize |
/root:explore [action] | RAG-powered codebase exploration: topic, flow, map |
/root:rag [action] | Manage RAG database: status, ingest, refresh, clear, config, scan |
/root:docs [action] | Documentation management: health, search, stale, scan, validate, fix, create |
/root IS the orchestrator. Running /root #<issue> creates a stream on first invocation and advances it on every subsequent invocation — re-running is the universal "continue" gesture.
/root #42 # Create stream, classify tier, plan. Stops at plan approval.
/root #42 # (after approving) Dispatches /root:impl, drives to PR-ready.
/root #58 # Start a second stream — each gets its own worktree
/root list # View all active streams
/root status #42 # Detailed status for one stream
/root approve #42 # Green-light a Tier 1 plan AND continue execution
/root run # If one active stream, resume it; else prompt
/root sync # Sync local state with GitHub labels
/root delete #42 # Abandon a stream and tear down its worktree
/root clean # Tear down merged worktrees
How it works: Each stream progresses through a state machine (queued → planning → plan-ready → approved → implementing → validating → pr-ready → merged). Gates at each transition determine whether to auto-advance or pause for human approval. Tier 2 work (bug fixes) runs fully autonomously to PR. Tier 1 work pauses once for plan approval, then runs autonomously.
Streams are tracked locally in .root/board/ and reflected on GitHub issues via labels (root:planning, root:plan-ready, root:approved, root:implementing, root:pr-ready). Approve from anywhere — CLI, GitHub UI, or your phone.
/root #1132 # Start session from a GitHub issue
/root #1132 webhook flaky on retries # Issue + in-the-moment color
/root 1234 # Bare number also works
/root reset # Clear completed streams
/root:prd new #1234 # Guided PRD creation from an issue
/root:prd review auth-refresh # Quality review of a PRD
/root:prd list # List all PRDs in the project
/root:impl # Execute the approved plan
/root:impl status # Check implementation progress
/root:impl resume # Pick up where you left off
/root:explore topic auth # Explore a topic across the codebase
/root:explore flow login # Trace a flow end-to-end
/root:explore map # Map the codebase architecture
/root:rag status # Check RAG database state
/root:rag refresh # Re-ingest all docs after major changes
/root:rag scan # Discover new directories to index
/root:docs health # Dashboard of doc coverage and freshness
/root:docs search oauth # Find docs about a topic
/root:docs stale # Find outdated documentation
/root:docs scan # Find undocumented code, triage, generate docs
/root:docs create src/services/auth.ts # Generate a doc from source code
/root:docs validate # Check frontmatter across all docs
/root:docs fix # Auto-add missing frontmatter
npx claudepluginhub brandcast-signage/root --plugin rootImplementation planning, execution, and PR creation workflows with multi-agent collaboration
AI-Driven Engineering workflow commands for managing issues, tasks, implementation, and PRs.
Autonomous development methodology: PRD interviews → agent execution → automated review
Development workflow automation including feature development, code quality, and PR management
A Claude Code plugin for structured, context-efficient software development.
Orchestration plugin. v1 use case: async development - turn ready issues into pull requests, then iterate on review feedback until a human takes over. Designed to host more orchestration use cases (refactoring, docs, audits) in future versions.