rohitg00/pro-workflow

Agent Teams coordinates multiple Claude Code sessions as a team with shared task lists, mailbox messaging, and file-lock claiming. Use it to parallelize work on non-overlapping files or delegate cross-layer changes across a lead and teammates.

Auto Setup detects the project type and configures quality gates, hooks, and settings for a new codebase. Use it when onboarding a new project or setting up CI integration.

Batch Orchestration decomposes large-scale, repetitive code changes into independent units and spawns parallel agents in isolated worktrees to implement them. Use it for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.

Bug Capture turns a user-reported defect into a durable GitHub issue written in the project's own domain language, without exposing file paths or line numbers. Use it when a user reports a bug conversationally, runs a QA pass, or asks to file an issue.

Compact Guard preserves critical context state before compaction and restores it after, so an agent can resume work without losing task progress, decisions, or next steps.

Context Engineering helps you manage context windows in AI coding sessions by mastering four operations: Write, Select, Compress, and Isolate. Use it to keep token budgets efficient, plan compaction strategies, and partition work across subagents and worktrees.

Context Optimizer helps manage context windows and token budgets in Claude Code sessions. Use it when sessions feel slow, context is degraded, or you are running out of budget.

Cost Tracker monitors Claude Code session costs and token usage, sets budget alerts, and suggests strategies to optimize spend. Use it mid-session to check costs or set spending limits.

Design Engineering applies interface craft when building or reviewing UI, covering motion, easing, timing, springs, component feel, and visual foundations. Use it when polishing an interface, adding an animation, or reviewing a component so it feels right.

Deslop removes AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Use it before committing or when reviewing a SKILL.md before promoting it.

Domain Modeling builds the project's shared language and bounded contexts before writing code, so names stay consistent and the agent stops paraphrasing domain concepts. It produces a CONTEXT.md glossary and decision records, used at the start of a project or feature.

File Watcher sets up file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use it to create reactive workflows that respond to file system changes.

Improve Architecture audits an area of the codebase and proposes the smallest structural moves that improve it—untangle boundaries, kill duplication, fix seams, break cycles. It produces a prioritized plan and decision records, not a rewrite. Use it when the codebase feels tangled, hard to change, or becoming a ball of mud.

LLM Council orchestrates multi-LLM deliberation in three phases: independent responses, cross-model anonymized ranking, and chairman synthesis. Use it for high-stakes reviews, plan critique, or contested learning-rule resolution.

LLM Gate sets up AI-powered prompt hooks in Claude Code to validate commit messages, code patterns, and file writes before operations run. Use it to block bad commits, destructive commands, or secret leaks with fast, cheap LLM checks.

Learn Rule captures a correction or lesson as a persistent learning rule with category, mistake, and correction. Use it after mistakes or when the user says 'remember this', 'don't forget', 'note this', or 'learn from this'.

MCP Audit analyzes connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.

Module Map produces a one-screen map of an unfamiliar area of the codebase, showing entry points, modules, data flow, callers, and hidden coupling. Use it to orient quickly in unfamiliar code.

Orchestrate coordinates commands, agents, and skills to build features through structured research, planning, implementation, and review phases with validation gates. Use it for complex features touching multiple files or requiring architecture decisions.

Parallel Worktrees creates and manages git worktrees so you can run parallel coding sessions with zero dead time while tests or builds run. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.

Permission Tuner analyzes permission denial patterns and generates optimized alwaysAllow and alwaysDeny rules to reduce permission prompt fatigue. Use when permission prompts are slowing you down or after sessions with many denials.

Plan Interrogate stress-tests a plan by walking its decision tree one question at a time, resolving every open decision before code is written. Use it when a design needs pressure-testing before implementation.

Pro Workflow provides orchestration patterns, hook events, agents, and self-correction loops that reduce correction cycles in AI coding. Use it to set up CLAUDE.md memory, parallel worktrees, pre-flight discipline, and wrap-up rituals across Claude Code, Cursor, and other AI agents.

Replay Learnings surfaces relevant past mistakes and applied patterns before starting a coding task. It searches correction history and session logs to flag high-risk areas and suggest proven approaches.

Session Insights computes session analytics, learning patterns, correction trends, heatmaps, and productivity metrics from project memory and session history. Use it when asking for stats, progress, coding history, or a dashboard.