pro-workflow

<p align="center">
  <img src="assets/banner.svg" alt="Pro Workflow" width="100%"/>
</p>

<p align="center">
  <a href="https://github.com/rohitg00/pro-workflow/stargazers"><img src="https://img.shields.io/github/stars/rohitg00/pro-workflow?style=for-the-badge&logo=github&color=D97757&labelColor=1e1e2e" alt="Stars"/></a>
  <a href="https://www.npmjs.com/package/pro-workflow"><img src="https://img.shields.io/npm/v/pro-workflow?style=for-the-badge&logo=npm&color=E8926F&labelColor=1e1e2e" alt="npm"/></a>
  <a href="https://github.com/rohitg00/pro-workflow/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-22c55e?style=for-the-badge&labelColor=1e1e2e" alt="License"/></a>
  <a href="https://agenstskills.com"><img src="https://img.shields.io/badge/SkillKit-32%2B%20agents-f59e0b?style=for-the-badge&labelColor=1e1e2e" alt="SkillKit"/></a>
  <a href="https://rohitg00-pro-workflow.mintlify.app/"><img src="https://img.shields.io/badge/Docs-Mintlify-0D9373?style=for-the-badge&logo=mintlify&labelColor=1e1e2e" alt="Docs"/></a>
</p>

<h3 align="center">Your Claude Code gets smarter every session.</h3>

<p align="center">
  Self-correcting memory that compounds over 50+ sessions. You correct Claude once &mdash; it never makes the same mistake again.<br/>
  <b>24 skills</b> &bull; <b>8 agents</b> &bull; <b>21 commands</b> &bull; <b>29 hook scripts across 24 events</b><br/>
  Works with <b>Claude Code</b>, <b>Cursor</b>, and <b>32+ agents</b> via SkillKit.
</p>

---

## The Problem

You correct Claude the same way 50 times. You tell it "don't mock the database" on Monday and again on Friday. You explain your project conventions every new session. Context compacts, learnings vanish, mistakes repeat.

**Every Claude Code user hits this wall.**

## The Solution

Pro Workflow captures every correction in a persistent SQLite database with full-text search. Corrections compound into rules. Rules load automatically on session start. After 50 sessions, Claude barely needs correcting.

<p align="center">
  <img src="assets/self-correction-demo.svg" alt="Self-Correction Loop" width="700"/>
</p>

```
Session 1:  You → "Don't mock the database in tests"
            Claude → Proposes rule → You approve → Saved to SQLite

Session 2:  SessionStart hook loads all learnings
            Claude → Writes integration tests (no mocks)
            You → Zero corrections needed

Session 50: Claude knows your conventions, style, and preferences
            Correction rate: near zero
```

## Install (30 seconds)

```bash
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow
```

<details>
<summary>Other install methods</summary>

```bash
# Cursor
/add-plugin pro-workflow

# Any agent via SkillKit
npx skillkit install pro-workflow

# Manual
git clone https://github.com/rohitg00/pro-workflow.git /tmp/pw
cp -r /tmp/pw/templates/split-claude-md/* ./.claude/

# Build with SQLite support
cd ~/.claude/plugins/*/pro-workflow && npm install && npm run build
```

</details>

---

## What's New in v3.2

- **LLM Gates** &mdash; First plugin with `type: "prompt"` hooks for AI-powered commit validation and secret detection
- **Permission Tuner** &mdash; Analyzes denial patterns, generates optimized allow/deny rules
- **Compact Guard** &mdash; Protects context through compaction (5-file restore limit, 50K budget)
- **Cost Tracker** &mdash; Session cost awareness with budget benchmarks
- **MCP Audit** &mdash; Analyzes MCP server token overhead per request
- **Auto Setup** &mdash; Detects project type, configures quality gates automatically
- **File Watcher** &mdash; Reactive workflows with `CLAUDE_ENV_FILE` injection
- **Agent Optimization** &mdash; `omitClaudeMd` on read-only agents saves tokens
- **6 New Hook Events** &mdash; PermissionDenied, Setup, WorktreeCreate, WorktreeRemove, CwdChanged, TaskCreated

---

## How Pro Workflow Compares

| Feature | Pro Workflow | [Superpowers](https://github.com/obra/superpowers) | [ECC](https://github.com/affaan-m/everything-claude-code) | [gstack](https://github.com/garrytan/gstack) | [GSD](https://github.com/gsd-build/get-shit-done) |
|---------|:-----------:|:-----------:|:---:|:------:|:---:|
| Self-correcting memory (SQLite + FTS5) | **Yes** | No | No | No | No |
| LLM-powered hooks (`type: "prompt"`) | **Yes** | No | No | No | No |
| Permission denial analysis | **Yes** | No | No | No | No |
| Compaction-aware state preservation | **Yes** | No | No | No | No |
| Cost tracking and budget alerts | **Yes** | No | No | No | No |
| MCP overhead auditing | **Yes** | No | No | No | No |
| Cross-agent (32+ agents via SkillKit) | **Yes** | No | Some | No | No |
| Skills | 24 | 14 | 140+ | 18+ | 0 |
| Agents | 8 | 5 | 36 | 0 | 18 |
| Commands | 21 | 3 | 60+ | 5+ | 57 |
| Hook Events | 24 | 8 | 18 | 0 | 0 |

---

## Try It

```bash
/develop add user authentication     # Multi-phase: Research > Plan > Implement > Review
/wrap-up                             # End session, capture learnings, audit changes
/doctor                              # Check your setup health
/learn-rule                          # Extract a correction into persistent memory
/commit                              # Quality gates > staged review > conventional commit
/permission-tuner                    # Analyze denials, generate allow/deny rules
/cost-tracker                        # Check session costs and token spend
/mcp-audit                           # Audit MCP servers for overhead
```

---

## What's Inside

### 24 Skills

| Skill | What It Does |
|:------|:------------|
| **Self-Correction Loop** | Claude learns from your corrections automatically |
| **Context Engineering** | Write/Select/Compress/Isolate framework for token management |
| **Agent Teams** | Multi-instance coordination with shared task list and messaging |
| **Batch Orchestration** | `/batch` pattern for parallel worktree agents |
| **Parallel Worktrees** | Zero dead time with native `claude -w` worktrees |
| **Smart Commit** | Quality gates, staged review, and conventional commits |
| **Wrap-Up Ritual** | End sessions with intention, capture learnings |
| **Context Optimizer** | Token management, context budget, MCP audit |
| **Deslop** | Remove AI-generated code slop and clean up style |
| **Orchestrate** | Wire Commands, Agents, and Skills for multi-phase development |
| **Session Handoff** | Generate handoff documents for session continuity |
| **Replay Learnings** | Surface past learnings relevant to the current task |
| **Insights** | Session analytics, correction trends, productivity metrics |
| **Safe Mode** | Guardrails for destructive operations |
| **Sprint Status** | Track progress across sessions |
| **Thoroughness Scoring** | Rate completeness of implementations |
| **Learn Rule** | Capture corrections as persistent learning rules |
| **LLM Gate** | AI-powered quality gates using `type: "prompt"` hooks |
| **Permission Tuner** | Analyze denial patterns, generate allow/deny rules |
| **Compact Guard** | State preservation through compaction cycles |
| **Cost Tracker** | Session cost awareness with budget benchmarks |
| **MCP Audit** | Audit MCP servers for token overhead and redundancy |
| **Auto Setup** | Detect project type, configure quality gates automatically |
| **File Watcher** | Reactive workflows on config and dependency changes |

### 8 Agents

| Agent | Purpose |
|-------|---------|
| **planner** | Break down complex tasks (read-only, approval-gated) |
| **reviewer** | Code review and security audit (checklist-based) |
| **scout** | Confidence-gated exploration (background, worktree-isolated) |
| **orchestrator** | Multi-phase feature development (Research > Plan > Implement > Review) |
| **debugger** | Systematic bug investigation (hypothesis-driven) |
| **context-engineer** | Context window analysis and optimization (lightweight, read-only) |
| **permission-analyst** | Analyze permission denial patterns, recommend rule optimizations |
| **cost-analys

[truncated…]