By ialameh
Autonomous multi-agent coding workflows with 90+ specialized commands for development, testing, documentation, security, debugging, and Salesforce-specific workflows
npx claudepluginhub ialameh/sift-coderAdd a new feature to an existing application, following established patterns and conventions.
**Autonomous multi-file refactoring with planning, execution, validation, and rollback capabilities.**
**AI-powered AgentForce agent development for Salesforce.**
**Analyze multiple files for insights without writing code.**
Generate enterprise Apex patterns - FFLib, Selector, Domain, Service, UnitOfWork
Apex development - analyze anti-patterns, bulkify code, generate enterprise patterns
Generate, validate, and manage API documentation and tooling.
Deep Code History Intelligence - AI-powered archaeology into why code exists
**Execute Approved Autonomous Manifest**
**SiftCoder Full Autonomous Mode - "Fire & Forget"**
Run comprehensive tests to verify that changes are contained within defined boundaries and haven't affected protected areas.
Bridge the gap between two codebases (e.g., website and admin panel) by analyzing, finding gaps, generating specs, and building integrations
Token/cost awareness - set budgets, track usage, optimize efficiency
Fix build errors automatically
Build a new project from a specification file
AI-designed chaos experiments based on your specific architecture. Find weaknesses before they find you.
Save and restore named checkpoints with full context
Create a chroot jail for safe file operations - works with build, fix, investigate, document
Manage licenses, generate SBOMs, and ensure regulatory compliance.
Configure siftcoder settings and cloud sync
**Consolidate multiple markdown files into one with auto-generated table of contents.**
Continue a paused siftcoder workflow from where you left off
**AI-powered Salesforce CPQ (Configure, Price, Quote) configuration and development.**
Analyze errors, trace issues, and find root causes faster.
Generate documentation - code, user-manual, architecture, or technical
Let AI "dream" creative solutions without constraints. Explore wild ideas, then filter back to reality. Unlock innovation through unconstrained thinking.
AI Rubber Duck Debugging - Forces YOU to explain code, AI asks probing questions
**Generate and optimize Einstein AI prompts for Salesforce.**
Detects code that causes developer frustration, measures cognitive load, and identifies emotional friction in your codebase.
Browse real-world examples of siftcoder in action.
**Generate executive summaries for positioning, technology stack fit, and industry alignment.**
**Analyze commercial viability, market potential, and competitive requirements.**
Manage the feature queue for siftcoder workflows.
Fix an issue with defined boundaries to prevent unintended changes
**AI-powered Salesforce Flow development for automation and business logic.**
Focus siftcoder on a specific feature, area, or file set
Technical Debt Fortune Telling - Predicts which tech debt will cause problems and when
Intelligent Edge Case Generation - AI-generated adversarial test cases targeting code weak points
Find gaps between specification and implementation, plus discover undocumented features.
Explore alternative implementations without touching your actual code. Ask "what if?" and see the consequences.
Session memory and handoff - persist context across sessions
When a build, test, or lint fails, automatically analyze the error, propose a fix, apply it, and retry - looping until success or max iterations.
Your guide to siftcoder - the autonomous multi-agent coding system.
Analyze specifications, research market trends, and creatively suggest new features with multi-level depth analysis.
Enhance and improve specification quality with testable criteria
Connect with GitHub, issue trackers, and other development tools.
Automatic Contract Mining - Discovers implicit invariants and makes them explicit
Safely investigate an issue in read-only mode without making changes
**Capture, query, and share team knowledge automatically.**
Explore, understand, and learn codebases effectively.
LWC debugging - wire issues, lifecycle, performance, component state analysis
Lightning Web Component development - create, analyze, wire adapters, events, Jest tests
Safely upgrade dependencies, migrate frameworks, and manage database changes.
Check what's not yet implemented from spec or feature queue
Analyze logs, errors, and production behavior.
Code-to-Story Translation - Converts code into narrative explanations for any audience
**Interactive codebase tours and role-specific onboarding for new developers.**
Refactor or optimize code with safety boundaries and regression testing.
Predictive Intent Engine - Predicts what you're about to do before you ask
Organize a project folder into the Sift monorepo structure
Interactive pair programming mode - AI suggests, you approve each step
Extract reusable patterns from recent work
List all patterns in knowledge base
Search knowledge base patterns
Pause the current siftcoder workflow for later resumption
Analyze, profile, and optimize application performance.
Cross-Language Intelligence - Ensures consistency and finds issues across multiple languages
Preview changes before applying - show diff with approval step
---
Identify and execute safe refactoring operations.
Resume a paused workflow (alias for /siftcoder:continue)
Reverse engineer existing code to create a specification document. Analyzes the codebase and produces a structured spec that could be used to recreate the project.
Comprehensive code review automation for PRs, diffs, and code changes.
Change Impact Visualization - See how changes ripple through your entire system
Rollback to a previous checkpoint, undoing changes made during a feature or fix workflow.
Schema migration and change management - plan, diff, deploy, rollback schema changes
Salesforce schema management - create objects, fields, relationships, ERD diagrams
Manage boundaries for fix/optimize workflows - show, add, remove files
**Find code by meaning, not just keywords. Uses vector embeddings for intelligent code discovery.**
Comprehensive security scanning for your codebase.
Evaluate session for extractable patterns
Setup MCP servers with auto-detection
Salesforce architecture review - security, scalability, governor limits, sharing model
Salesforce architecture tools - diagrams, capacity planning, architecture analysis
Salesforce integration setup - Named Credentials, External Credentials, OAuth, REST callouts
Salesforce debug log analysis - parse logs, identify bottlenecks, governor limits
Salesforce deployment management - validate, deploy, diff, rollback, CI/CD setup
Salesforce custom logging - Platform Events, logging framework, real-time monitoring
Salesforce package development - unlocked packages, versioning, dependencies
**Automated Salesforce security review and vulnerability scanning.**
Salesforce test data management - factories, seed data, sanitization
Salesforce test generation - comprehensive tests, coverage analysis, bulk testing, mocks
Salesforce webhook handling - create inbound webhook endpoints with HMAC verification
Main siftcoder orchestration - autonomous coding workflows for BUILD, MAINTAIN, and DOCUMENT
Learn from failures - remember what didn't work and try different approaches
**Generate detailed specifications from user stories or requirements.**
Show current siftcoder progress and status with resume context
Analyzes your request and suggests the most appropriate SiftCoder command to use.
Discover trending app ideas from online resources, filter by your preferences, generate specifications, and build your next project.
Parallel agent execution - run multiple agents on independent tasks simultaneously
Synchronize knowledge to cloud storage
Test-driven generation - write tests first, generate code that passes them
Team knowledge sharing and collaboration
Generate, analyze, and improve tests for your codebase.
Reconstruct the exact state of your application at any point in history. Debug issues by traveling back to when they occurred.
View execution trace - see what AI did, why, and alternatives considered
Analyze and capture understanding of a project's structure, patterns, and architecture.
Generate architecture codemaps
Generate documentation automatically
**Generate detailed use cases from project descriptions or specifications.**
Build beautiful, modern websites from your codebase or from scratch
Interactive step-by-step guide to using siftcoder. Perfect for first-time users.
Minimalist Code Mode - Aggressively simplifies code, removing every non-essential line
**Specialized agent for pure analysis and insight extraction from non-code sources.**
Cross-codebase integration specialist. Analyzes two codebases, identifies gaps, generates integration specifications, and plans bridge implementations.
Implementation specialist for writing code from plans. Expert in following patterns, writing clean code, and running tests. Use when executing coding subtasks from a plan.
Documentation specialist for generating code documentation, user manuals, architecture diagrams, and technical docs. Use when creating or updating documentation.
Read-only investigation specialist for safely exploring issues without making changes. Use when investigating bugs, understanding code behavior, or exploring unfamiliar codebases.
**Multi-agent coordination for parallel execution and conflict resolution.**
Planning specialist for breaking down features into implementation tasks. Use when you need to create a detailed implementation plan before coding. This agent explores the codebase, identifies patterns, and creates structured subtask breakdowns.
Issue resolution specialist for fixing QA-identified problems. Focused on addressing specific issues without scope creep. Use when QA Reviewer has identified issues that need fixing.
Quality assurance specialist for reviewing implementations. Runs comprehensive tests, validates acceptance criteria, and identifies issues. Use after coding is complete to validate the work.
General-purpose code review agent for pull requests, code analysis, and architectural feedback. Provides comprehensive code quality assessments and improvement suggestions.
**Vector-based code discovery and semantic matching.**
Analyzes user requests and suggests the most appropriate SiftCoder command.
General-purpose testing agent for test generation, coverage analysis, and test quality assessment. Creates comprehensive unit, integration, and e2e tests across languages and frameworks.
Reusable capabilities for autonomous multi-file operations
Full autonomous mode for "fire & forget" autonomous project completion
Generate visual documentation including Mermaid diagrams, code maps, and architecture visualizations
Detect gaps between specification and implementation, and identify undocumented features
Conduct comprehensive market research including competitor analysis, market trends, and user demand signals
Automatically organize a project folder into the Sift monorepo structure
Detect and document code patterns, conventions, and architectural styles in existing codebases
Interactive assistant that guides users through crafting effective prompts for SiftCoder commands
Automated code quality validation with configurable checks
Comprehensive security analysis for codebases
Vector-based code discovery using LanceDB and Ollama embeddings
Research search trends, keywords, and user intent to inform feature development and content strategy
Full autonomous multi-agent workflow for implementing features
Extract testable features from natural language specifications
Analyzes natural language requests and suggests the most appropriate SiftCoder command to use
Analyze user experience patterns, best practices, and accessibility requirements
Build beautiful, modern websites from codebase or from scratch
Keep generated websites synchronized with codebase changes
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Bypasses permissions
Runs without the normal permission approval flow
Uses power tools
Uses Bash, Write, or Edit tools
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation