By agigante80
Code review agents (code-reviewer, architect-review, backend-architect, code-simplifier, coding-standards-auditor) and full-review/pr-enhance commands.
Orchestrate comprehensive multi-dimensional code review using specialized review agents across architecture, security, performance, testing, and best practices
You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability.
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and observability. Use PROACTIVELY when creating new backend services or APIs.
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
Simplifies and refines recently modified code for clarity, consistency, and maintainability while preserving all functionality. Triggers automatically after completing a coding task or writing a logical chunk of code. Use PROACTIVELY after every code change — do not wait to be asked.
Detects, consolidates, and writes coding standards for the project. Finds standards wherever they live (CLAUDE.md inline, CONTRIBUTING.md, STYLE_GUIDE.md, docs/, etc.), scores each category against a per-language reference checklist, writes a complete docs/coding-standards.md, removes inline standards from CLAUDE.md, and adds a canonical reference line. Fully automated — no manual paste required. Invoke when: "audit my coding standards", "set up coding standards", "fix my coding standards", "are my coding standards complete", "I don't have coding standards".
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
forge-adapt reads your codebase and installs the governance tools that fit — rewritten for your stack, not copy-pasted.
forge-kit is a library of project governance components: ticket gates, code reviewers, security auditors, dependency auditors, and more. forge-adapt is the skill that bridges forge-kit and your project — it reads your codebase, recommends what's relevant, and writes project-specific versions into .claude/. Nothing generic. Every component knows your stack.
1. Add the marketplace /plugin marketplace add agigante80/forge-kit
2. Install the plugin /plugin install forge-kit-adapt@forge-kit
3. Activate /reload-plugins
4. Open your project /forge-kit-adapt:adapt
and run forge-adapt (or say "run forge-adapt" to Claude Code)
forge-adapt takes it from there.
When you say "run forge-adapt", it:
.claude/ contents to build a project profile$queryRaw / $executeRaw injection in src/db/"Project profile:
Language/framework: TypeScript / Next.js 14
Domain: SaaS — multi-tenant project management with billing
Security surface: JWT auth, Stripe webhooks, PostgreSQL via Prisma
Governance already installed: none
### Recommended to install and adapt
| # | Component | Type | Why this project needs it | Priority |
|---|--------------------|---------|--------------------------------------------------|----------|
| 1 | ticket-gate | agent | Quality gate — universal need | P0 |
| 2 | security-auditor | agent | JWT + Stripe webhook surface has OWASP exposure | P0 |
| 3 | api-security-tester| agent | Public REST API with auth and payment endpoints | P0 |
| 4 | dep-auditor | agent | npm ecosystem with deep transitive deps | P1 |
| 5 | code-reviewer | agent | TypeScript/Next.js patterns and type safety | P1 |
| 6 | forge-adapt | skill | Keeps governance in sync with forge-kit | P1 |
Which would you like to import and adapt?
Reply with numbers (e.g. "1 3 5"), "all", or "none".
> all
✓ ticket-gate (agent) — adapted for agigante80/my-saas; Prisma + Stripe checks added
✓ security-auditor (agent) — JWT algorithm and webhook signature checks injected
✓ api-security-tester (agent) — Stripe webhook endpoint added to test surface
✓ dep-auditor (agent) — npm audit + license checks for payment libraries
✓ code-reviewer (agent) — Next.js App Router patterns and Prisma query safety
✓ forge-adapt (skill) — installed and self-updating
forge-kit ships two layers.
| Component | What it does |
|---|---|
| 6 issue templates | feature, bug, security, infrastructure, design, contribution — v4 with GWT scenarios, unit test specs, E2E test specs, GDPR and security checklists |
| GitHub labels | Standard label taxonomy for issue routing and prioritisation |
| Component | What it does |
|---|---|
forge-adapt skill | Analyses the target project, recommends relevant components, writes project-customised versions, and surfaces contribution candidates back to forge-kit |
ticket-gate agent | Scores every GitHub issue before implementation (5 core agents + dynamic routing by label). ALL must score 10/10 to pass |
| 11 specialist agents | code-reviewer, security-auditor, architect-review, backend-architect, backend-security-coder, api-security-tester, tdd-orchestrator, test-automator, performance-engineer, dep-auditor, health-check |
/full-review | Multi-phase code review orchestrator with a mid-run checkpoint |
/pr-enhance | Pull request description and checklist generation |
/ci-health | Check all GitHub Actions workflows, create P0 tickets for failures, auto-fix safe failures |
| 7 skills | forge-adapt, api-design-principles, owasp-api-security, architecture-patterns, microservices-patterns, cqrs-implementation, saga-orchestration |
Once forge-adapt has installed your components, the governance workflow looks like this:
file ticket → gate it (10/10 from all specialists) → implement → review
Security agents and OWASP checklist skill
ticket-gate agent and gate-ticket slash command
dep-auditor, health-check agents and /ci-health command
Testing agents: tdd-orchestrator, test-automator, performance-engineer
forge-adapt skill — analyses your project, suggests the right forge-kit components to adapt to your needs, and installs them for you
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
npx claudepluginhub agigante80/forge-kit --plugin forge-kit-review