essentials

Convert plans to Beads - works with /beads-loop, /beads-swarm, or RalphTUI

Execute beads iteratively until all tasks complete

Execute beads with parallel agent swarm (dependency-aware)

Deep bug investigation with architectural fix plan generation - works with any executor (loop or swarm)

Cancel any active loop

Cancel any active swarm

Cancel any active agent team

LSP-powered architectural code quality analysis - works with any executor (loop or swarm)

Generate or update hierarchical code map from any directory as root, with nested tree structure (project)

Generate DEVGUIDE.md architectural documentation using LSP (project)

Implement from conversation context with iterative loop

Implement from conversation context with parallel swarm

Implement from conversation context with Agent Teams

Generate and apply MR/PR description directly via gh or glab CLI (project)

Create architectural plans for new features - works with any executor (loop or swarm). For bugs use /bug-plan-creator, for code quality use /code-quality-plan-creator.

Execute a plan file with iterative loop until completion

Execute a plan file with parallel agent swarm (dependency-aware)

Execute a plan file with Agent Teams (contract-first parallel coordination)

Write recommended RalphTUI config for json or beads tracker

Reset a beads epic to initial state (reopen all child tasks)

Reset a prd.json file to initial state (all tasks pending)

Show task or bead status summary with formatted table

Convert plans to prd.json - works with /tasks-loop, /tasks-swarm, or RalphTUI

Execute prd.json tasks iteratively until all complete

Execute prd.json with parallel agent swarm (dependency-aware)

Verbatim plan-to-beads converter using the `bd` CLI. Copies full implementation code, requirements, and exit criteria directly into each bead. Each bead is 100% self-contained - no plan back-references or external lookups needed.

Architectural Bug Investigation Agent. Deep investigation with line-by-line code analysis, produces fix plans with exact code changes, regression prevention, and verification criteria. Plans work with any executor (loop or swarm).

Architectural Code Quality Agent (LSP-Powered) - Creates comprehensive architectural improvement plans suitable for loop or swarm executors (/implement-loop, /tasks-loop or /tasks-swarm, /beads-loop or /beads-swarm). Uses Claude Code's built-in LSP for semantic code understanding. This agent thoroughly analyzes code using LSP semantic navigation, identifies quality issues across multiple dimensions, and produces detailed architectural plans with exact specifications. Plans specify the HOW, not just the WHAT - exact code changes, pattern alignments, and verification criteria. Built-in LSP operations: documentSymbol, findReferences, goToDefinition, workspaceSymbol, incomingCalls, outgoingCalls Examples: - User: "Analyze code quality for src/services/auth_service" Assistant: "I'll use the code-quality-plan-creator agent to create an architectural improvement plan using LSP analysis." - User: "Analyze code quality for agent/prompts/manager" Assistant: "Launching code-quality-plan-creator agent to create an architectural quality plan with LSP-verified dependencies."

Generate or update hierarchical code maps using LSP. Two modes: **create** (full scan from root) and **update** (re-scan only changed files from git diff, MR, or PR). Maps show directory tree with symbols, signatures, dependencies, and export status. Consumed by `/plan-creator` for codebase orientation.

Generate DEVGUIDE.md architectural documentation using LSP for symbol extraction and pattern analysis. Creates `.claude/rules/` files when missing. ONLY creates documentation - does not edit existing docs.

Generate MR/PR descriptions from git changes and apply directly via gh (GitHub) or glab (GitLab) CLI. Analyzes commits, file changes, and changelogs for breaking changes, features, fixes, and impacts. Supports custom templates.

Architectural Planning Agent for Brownfield Development. Creates plans for new features with exact code structures, per-file implementation details, and dependency graphs. Plans work with any executor (loop or swarm). For bugs use bug-plan-creator, for code quality use code-quality-plan-creator.

Verbatim plan-to-prd.json converter for RalphTUI, /tasks-loop, or /tasks-swarm execution. Copies full implementation code, requirements, and exit criteria directly into each task. Each task is 100% self-contained - no plan back-references or external lookups needed.

Beads (bd CLI) reference — issue types, statuses, priorities, dependencies, and common commands

GitHub CLI (gh) wrapper for PR status, issues, and repository operations

GitLab CLI (glab) wrapper for MR status, issues, and repository operations

Plan file (.claude/plans/*-plan.md) reference — sections, per-file format, dependency graph, and converter mappings

prd.json schema reference for Ralph TUI — validates structure, prevents unsupported fields