By thierryn
Orchestrate research-backed AI-driven SDLC workflows from project idea to production: initialize with git and requirements interview, research architectures, plan executable phases using skills library, execute in parallel with atomic commits, verify via 70-point checklists and UAT, perform adversarial reviews, handoff sessions with memory, and track metrics autonomously.
npx claudepluginhub thierryn/fire-flowOrient on an existing project - understand what's here and what's next
Initialize a new project with Dominion Flow (Dominion Flow)
Research, vision selection, and roadmap generation for a new project (Dominion Flow)
Install tooling, create handoff, and finalize project initialization (Dominion Flow)
Gather implementation context through adaptive questioning before planning
Plan a phase with skills library access and WARRIOR validation
Verify phase completion with must-haves and 70-point validation
Create comprehensive session handoff for next AI agent
Resume from previous session handoff with full context restoration
Multi-perspective code review with 15 specialized reviewer personas
Add a new skill to the skills library when you solve a hard problem
View skills usage analytics and effectiveness metrics
List and validate assumptions for a phase before planning or execution
Full autopilot — plan, execute, verify all phases autonomously after PRD is complete
Dedicated ideation and exploration before implementation
Archive completed milestone and prepare for next version with WARRIOR validation
Track context usage, estimate session costs, and trigger strategic compaction
Display visual project dashboard with status and progress
Systematic debugging with persistent state, skills library integration, and WARRIOR validation
AI-powered pattern discovery and skill suggestions
Deep validation before claiming work is complete
Execute a single plan with segment-based routing, per-task atomic commits, and test enforcement
Linear code walkthrough learning mode — transforms any repo into a step-by-step learning experience. Based on Simon Willison's Agentic Engineering Patterns.
Resume a Power Loop from Sabbath Rest or stopped state
Cancel the active Power Loop and save progress
Start self-iterating loop until completion with circuit breaker, error classification, context engineering, and skills integration
Analyze codebase with parallel mapper agents to produce structured documentation
Interactive database migration assistant — assess, plan, execute, and verify migrations between PostgreSQL, MySQL, SQLite, and SQL Server
Start a new milestone cycle with questioning, research, requirements, and roadmap
/fire-reflect
/fire-research
Autonomous Resurrection Mode — reverse-engineer intent from messy code, then rebuild clean from scratch
Guided wizard for creating features and components within a phase
Search the skills library for patterns, solutions, and best practices
Security audit a GitHub repo before installing as a skill or plugin
Inspect skills, plugins, MCP tools, and code for prompt injection, PII harvesting, credential theft, and supply chain attacks
Auto-generate compact session summary with aggregate status, readiness, outlook, and next steps
One-time developer profile onboarding — answer once, never asked again
Unified skill management CLI — create, import, test, list, stats, and export skills
Compare different versions of a skill
View version history for a skill in the skills library
Rollback a skill to a previous version
Synchronize skills between project library and global library
Run Dominion Flow plugin integration tests to verify all commands and integrations work correctly
Capture, list, and manage todos during work sessions
Complete phase transition with metrics collection, bottleneck detection, auto-skill extraction, and trend analysis
Check for and apply plugin updates from GitHub repository
Validate skills library structural integrity — frontmatter, sections, cross-references, markdown syntax
Conversational User Acceptance Testing with automatic parallel diagnosis on failures
AI-powered application vulnerability scanner using OWASP Top 10 — find what regex-based tools miss
Codebase analyzer — maps architecture, dependencies, patterns, and concerns
Systematic debugger — hypothesis-driven investigation with evidence tracking
Executes plans with honesty protocols and creates unified handoff documents
Adversarial verification agent that independently attempts to disprove research findings
Per-step explainer for learncoding mode — extracts real code snippets, explains WHAT/WHY/PATTERN, scaffolds file, handles both watch and active modes
Dependency graph mapper for learncoding mode — detects entry point and produces ordered linear step list from entry point outward
Creates phase plans with skills library integration and WARRIOR validation
Researches a specific domain focus area for new project/milestone initialization
Merges parallel research findings into a unified synthesis document
Researches phase context using skills library and pattern matching
Reverse-engineers developer intent from messy codebases — extracts what code was TRYING to do
Independent code reviewer — architecture, patterns, performance, maintainability
Creates project roadmap with phase breakdown from research synthesis
Combines must-haves verification with WARRIOR 70-point validation
Generates 2-3 competing architecture vision branches from research synthesis
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
The development-workflow plugin for Claude Code — 35 skills organized around a 6-phase workflow (Think → Review → Build → Ship → Maintain → Setup), 24 agents, and an interactive setup wizard for rules, modes, hooks, and MCP servers.
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Opinionated workflow guides and best practices - the preacher's proven patterns for Claude Code projects
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Describe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.
Corca Workflow Framework — consolidated hooks and skill orchestration for structured development sessions