By caseyrtalbot
Phase-locked development workflow with test-first discipline, evidence-gated verification, and dynamic skill routing.
npx claudepluginhub caseyrtalbot/forge --plugin forgeAnalyzes impact of changes across the codebase. Deploy before execution to identify files, modules, and tests affected by planned changes.
Keeps documentation in sync with code changes. Deploy after significant implementation to update relevant docs.
Executes single plan tasks with test-first discipline. Fresh instance per task to prevent context pollution. Deploy during EXECUTION phase.
End-to-end verification that changes work together. Deploy during VERIFICATION phase to run full test suites and build checks.
Two-stage code review: first checks spec compliance, then code quality. Deploy after task implementation during VERIFICATION phase.
OWASP-aware vulnerability scanning on diffs. Deploy proactively when code touches user input, authentication, API endpoints, or sensitive data.
Validates design documents for completeness, contradiction, and ambiguity. Deploy during the DESIGN phase to review specs before user approval.
Breaks approved specs into independently executable tasks with verification criteria. Deploy during the PLANNING phase.
Determines what tests are needed and verifies coverage meets requirements. Deploy when planning test strategy or auditing test gaps.
Check gate conditions for the current phase and advance to the next phase if all pass. User-invoked only: do not auto-trigger.
Run comprehensive quality, security, and completeness audit on current work. User-invoked only: do not auto-trigger.
Use when an approved spec exists and needs to be decomposed into executable tasks with verification criteria. Phase: PLANNING.
Run verification commands and show output before any completion claim. Evidence before assertions. Fresh execution required, not cached results.
Use when starting any new feature, change, or project. Collaboratively refines what to build through structured questions before any design or code begins. Phase: DISCOVERY.
Use at the end of a workflow or after significant debugging. Captures what went well, what went wrong, and what to do differently next time.
Use when a complete plan exists and tasks are ready for implementation. Dispatches fresh agents per task with individual verification. Phase: EXECUTION.
Multi-stage review with re-review loops. Spec compliance first, then code quality, then security. Issues must be fixed and re-reviewed before proceeding.
Create isolated git worktrees for feature work. Smart directory selection and safety verification.
Use when all verification passes and code is ready to integrate. Handles branch preparation, PR creation, merge decisions, and cleanup. Phase: INTEGRATION.
Write failing test before any production code. Red-green-refactor for all features and fixes. No exceptions except config, types, and static assets.
Use when receiving code review feedback. Verify suggestions against the codebase before implementing. Push back when feedback is incorrect.
Use when an approved direction exists and a spec document is needed. Creates architecture, data flow, edge cases, and error handling documentation. Phase: DESIGN.
Initiate a new Forge workflow. Creates .forge/ state and begins the discovery phase. User-invoked only: do not auto-trigger.
Show current Forge workflow phase, progress, and pending gates. User-invoked only: do not auto-trigger.
Systematic root cause analysis before proposing fixes. Reproduce, hypothesize, test, document. Three failed fixes means question the architecture.
Battle-tested Claude Code plugin for engineering teams — 48 agents, 182 skills, 68 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
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.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
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
Meta-prompting and spec-driven development system for Claude Code. Productivity framework for structured AI-assisted development.