awsome-slash

Awesome Slash Commands

Professional-grade workflow automation for AI coding assistants

A cross-platform plugin providing powerful, zero-configuration slash commands for development workflows. Works with Claude Code, Codex CLI, and OpenCode.

What's New in v2.4.0

• Reality Check Plugin - Deep repository analysis to detect plan drift and gaps
• Multi-Agent Parallel Scanning - Issue scanner, doc analyzer, code explorer run simultaneously
• Prioritized Reconstruction Plans - Automated drift detection with priority-weighted action items

Installation

Claude Code (Native)

# Option 1: Marketplace (recommended)
claude plugin marketplace add avifenesh/awsome-slash
claude plugin install next-task@awsome-slash ship@awsome-slash

# Option 2: Direct install
git clone https://github.com/avifenesh/awsome-slash.git
./scripts/install/claude.sh

OpenCode

git clone https://github.com/avifenesh/awsome-slash.git
cd awsome-slash
./scripts/install/opencode.sh

Codex CLI

git clone https://github.com/avifenesh/awsome-slash.git
cd awsome-slash
./scripts/install/codex.sh

Available Commands

📋 /next-task:next-task - Master Workflow Orchestrator

Complete task-to-production automation with state management and resume capability.

/next-task:next-task                   # Start new workflow with policy selection
/next-task:next-task --status          # Check current workflow state
/next-task:next-task --resume          # Resume from last checkpoint
/next-task:next-task --abort           # Cancel workflow and cleanup
/next-task:next-task bug               # Filter by task type

13-Phase Autonomous Workflow:

• Policy Selection → Ask user preferences via checkboxes
• Task Discovery → Find and prioritize tasks from GitHub/Linear/PLAN.md
• Worktree Setup → Create isolated development environment [sonnet]
• Exploration → Deep codebase analysis [opus]
• Planning → Design implementation plan [opus]
• User Approval → Get plan approval (LAST human interaction)
• Implementation → Execute the plan [opus]
• Pre-Review Gates → deslop-work + test-coverage-checker [sonnet]
• Review Loop → Multi-agent review until approved [opus]
• Delivery Validation → Autonomous task completion check [sonnet]
• Docs Update → Auto-update related documentation [sonnet]
• Ship → PR creation, CI monitoring, merge
• Cleanup → Remove worktree, update state

Features:

• Fully autonomous after plan approval - no human in the loop
• Resume capability with .claude/.workflow-state.json
• 14 specialist agents with model optimization (opus/sonnet)
• Quality gates: deslop-work, test-coverage-checker, delivery-validator, docs-updater
• SubagentStop hooks for automatic workflow transitions
• Policy-based stopping points (pr-created, merged, deployed, production)

🚀 /ship:ship - Complete PR Workflow

Ship your code from commit to production with full validation and state integration.

/ship:ship                        # Default workflow
/ship:ship --strategy rebase      # Rebase before merge
/ship:ship --dry-run              # Show plan without executing
/ship:ship --state-file PATH      # Integrate with next-task workflow

12-Phase Workflow:

• Pre-flight checks and platform detection
• Commit with AI-generated message
• Create PR with context
• Wait for CI
• Multi-agent review (code quality, silent failures, test coverage)
• Merge PR
• Deploy to development (if multi-branch)
• Validate development
• Deploy to production
• Validate production
• Cleanup
• Completion report

Platform Support:

• CI: GitHub Actions, GitLab CI, CircleCI, Jenkins, Travis CI
• Deployment: Railway, Vercel, Netlify, Fly.io, Platform.sh, Render

🧹 /deslop-around:deslop-around - AI Slop Cleanup

Remove debugging code, old TODOs, and AI slop from your codebase.

/deslop-around:deslop-around               # Report mode - analyze only
/deslop-around:deslop-around apply         # Apply fixes with verification
/deslop-around:deslop-around apply src/ 10 # Fix up to 10 issues in src/

Detects:

• Console debugging (console.log, print(), dbg!())
• Old TODOs and commented code
• Placeholder text, magic numbers
• Empty catch blocks, disabled linters

🔍 /project-review:project-review - Multi-Agent Code Review

Comprehensive code review with specialized agents that iterate until zero issues.

/project-review:project-review              # Full codebase review
/project-review:project-review --recent     # Only recent changes
/project-review:project-review --domain security

8 Specialized Agents: Security · Performance · Architecture · Testing · Error Handling · Code Quality · Type Safety · Documentation

📝 /next-task:update-docs-around - Documentation Sync

Sync documentation with actual code state across the entire repository.

/next-task:update-docs-around               # Report mode - analyze only
/next-task:update-docs-around --apply       # Apply safe fixes
/next-task:update-docs-around docs/ --apply # Sync specific directory

Checks:

• Outdated code references in documentation
• Invalid syntax in code examples
• Missing CHANGELOG entries
• Version mismatches
• Broken file/import paths

✅ /next-task:delivery-approval - Delivery Validation

Validate task completion and approve for shipping (standalone or part of workflow).

/next-task:delivery-approval                # Validate current work
/next-task:delivery-approval --task-id 142  # Validate specific task
/next-task:delivery-approval --verbose      # Show detailed check output

Validation Checks:

• Tests pass (npm test)
• Build passes (npm run build)
• Lint passes
• Type check passes
• Task requirements met

🎯 /reality-check:scan - Plan Drift Detection

Deep repository analysis to identify where documented plans diverge from actual code reality.

/reality-check:scan           # Full reality check scan
/reality-check:set            # Configure scan settings

Multi-Agent Parallel Scan:

• Issue Scanner - Analyzes GitHub issues, PRs, milestones
• Doc Analyzer - Examines README, PLAN.md, CLAUDE.md, docs/
• Code Explorer - Deep codebase structure and feature analysis
• Plan Synthesizer - Combines findings and creates prioritized plan

Detects:

• Plan stagnation (low completion rates)
• Priority neglect (stale high-priority issues)
• Documentation lag (features not documented)
• Scope overcommit (documented but not implemented)
• Missing tests, outdated docs, overdue milestones

Output:

• Drift analysis with severity ratings
• Gap identification (missing tests, docs, CI)
• Cross-reference: documented vs implemented features
• Prioritized reconstruction plan (immediate, short-term, medium-term)

First-Run Setup: Interactive checkboxes configure:

• Data sources (GitHub, Linear, docs, code)
• Scan depth (quick, medium, thorough)
• Output format (file, display, both)

Cross-Platform Integration

All platforms share the same workflow tools via MCP (Model Context Protocol):

Tool	Description
workflow_status	Get current workflow state
workflow_start	Start a new workflow
workflow_resume	Resume from checkpoint
workflow_abort	Cancel and cleanup
task_discover	Find and prioritize tasks
review_code	Run multi-agent review

See docs/CROSS_PLATFORM.md for details.

Architecture

State Management

Workflows persist state in .claude/.workflow-state.json:

{
  "workflow": { "id": "...", "status": "in_progress" },
  "policy": { "taskSource": "gh-issues", "stoppingPoint": "merged" },
  "task": { "id": "142", "title": "Fix auth timeout" },
  "phases": { "current": "implementation", "history": [...] },
  "checkpoints": { "canResume": true, "resumeFrom": "implementation" }
}

Specialist Agents (12 Total)

Core Workflow (Opus - Complex Tasks):

Agent	Purpose
exploration-agent	Deep codebase analysis
planning-agent	Design implementation plans
implementation-agent	Execute plans with quality code
review-orchestrator	Multi-agent code review with iteration

Quality Gates (Sonnet - Side Reviewers):

Agent	Purpose
deslop-work	Clean AI slop from new work (committed but unpushed)
test-coverage-checker	Validate new work has test coverage
delivery-validator	Autonomous delivery validation (NOT manual)
docs-updater	Update docs related to changes

Operational (Sonnet - Infrastructure):

Agent	Purpose
policy-selector	Configure workflow policy
task-discoverer	Find and prioritize tasks
worktree-manager	Create isolated worktrees
ci-monitor	Monitor CI/PR status with sleep loops

Repository Structure

awsome-slash/
├── .claude-plugin/
│   └── marketplace.json      # Claude Code marketplace manifest
├── plugins/
│   ├── next-task/           # Master workflow orchestrator
│   │   ├── commands/        # next-task, update-docs-around, delivery-approval
│   │   ├── agents/          # 14 specialist agents
│   │   └── hooks/           # SubagentStop hooks for workflow automation
│   ├── ship/                # PR workflow
│   ├── deslop-around/       # AI slop cleanup
│   └── project-review/      # Multi-agent review
├── lib/
│   ├── state/               # Workflow state management
│   ├── platform/            # Auto-detection
│   └── patterns/            # Code analysis patterns
├── mcp-server/              # Cross-platform MCP server
├── scripts/install/         # Platform installers
└── docs/

Requirements

Required:

• Git
• Node.js 18+
• GitHub CLI (gh) with authentication

For Claude Code:

• Claude Code CLI

For OpenCode:

• OpenCode CLI (opencode)

For Codex CLI:

• Codex CLI (codex)

Contributing

Contributions welcome! See CONTRIBUTING.md.

License

MIT © Avi Fenesh

Support

• Issues: https://github.com/avifenesh/awsome-slash/issues
• Discussions: https://github.com/avifenesh/awsome-slash/discussions

Made with ❤️ for the AI coding community