Plugin Claude Code
Enterprise & Startup SDLC orchestration plugin: 10 agents across 5 phases (Plan, Build, Verify, Ship, Operate), 43 knowledge skills, 16 commands. Hyper-scale RCA, 7-tier test matrix, Stripe monetization, and dynamic autonomous routing.
Instructions file
Instructions for saitarrun/Devforge-ai, covering sdlc workflow plugin, project, repository map, commands and agent conventions.
Agent
Builds data pipelines for ETL/ELT, manages analytics storage (data warehouse/lake), and ensures data quality. Optimizes data ingestion, transformation, and reporting. Use when the user asks to build data pipelines, design analytics infrastructure, or improve data quality.
Agent
Designs CI/CD pipelines, provisions cloud infrastructure, and manages releases. Absorbed cloud-engineer and release-manager responsibilities. Runs as the sole Ship phase agent. Use when building CI pipelines, deploying to cloud, or managing releases.
Agent
Implements complete features spanning frontend UI and backend APIs. Handles database schema, API endpoints, and component logic end-to-end. Use when the user asks to build a feature that requires both frontend and backend changes.
Agent
Profiles systems, identifies bottlenecks, optimizes code and infrastructure, and prevents performance regressions. Uses flame graphs, benchmarking, and data-driven analysis. Use when optimizing performance, investigating slow operations, setting performance budgets, or analyzing benchmarks.
Agent
Conducts grill-me interview to deeply understand the feature, then decomposes it into tracer bullet slices and emits scope.json. Runs as the sole Plan phase agent. Use for /sdlc-plan to kick off any feature.
Agent
Writes cross-slice E2E tests covering flows that span multiple slices. Runs once after all feature slices complete in the Build phase. Reads implementation-log.md to understand the full shape of what was built. Flags which slices caused any E2E failures for targeted retry.
Agent
Performs SAST analysis, OWASP Top 10 audit, dependency scanning, and (when scope requires) penetration testing. Runs in the Verify phase. Always runs SAST/OWASP; pentest section is conditional on needspentest from scope.json.
Agent
Defines SLOs, designs monitoring/alerting, writes runbooks, and (when hasauth is true) sets up security monitoring. Absorbed secops-analyst responsibilities. Runs in Operate phase. Use for reliability, observability, and security operations.
Agent
Writes API documentation, SDK guides, tutorials, developer guides, and external communication. Makes technical concepts accessible to diverse audiences. Maintains docs-as-code philosophy with examples and runnable code. Use when creating API docs, writing developer guides, documenting SDKs, or creating tutorials.
Agent
Conducts user research, defines personas, creates wireframes, and produces design tokens and component specs. Runs once at the start of the Build phase when hasui is true. Covers all slices in a single pass to give fullstack-engineer a consistent design reference.
Command
Phase 2 — Build. Reads plan-handoff.md, optionally runs ux-designer (hasui gate), then loops fullstack-engineer over each slice with ralph-loop self-correction, then runs qa-engineer for E2E tests.
Command
Automated Root-Cause Analysis (RCA) and surgical fix engine for massive enterprise codebases (up to 1.5M+ files).
Command
Interactive user guide and command navigator to help you pick the right tool, agent, and phase with zero confusion.
Command
Standalone issue implementation with Ralph Loop — implements a single Linear issue or free-form spec using fullstack-engineer + self-correcting retry loop.
Command
Industrial legacy system modernization, Strangler Fig migrations, monolith decoupling, and zero-downtime schema evolution.
Command
Navigate, map, and explore large codebases, complex directory hierarchies, symbol dependencies, and call chains.
Command
Phase 5 — Operate. Runs sre-engineer always + data-engineer when hasdatapipeline is true. Reads ship-handoff.md for clean context.
Command
Phase 1 — Plan. Runs product-manager grill-me interview + slice decomposition, then publishes PRD and creates issues. Invokes exactly 1 agent.
Command
Anytime — Industry-standard code review. Spawns 3 parallel reviewers (compliance, bugs, history). Posts inline comments via gh pr comment.
Command
Automatically audit, patch vulnerabilities, upgrade dependencies, and implement enterprise security protocols (Zero-Trust, mTLS, OWASP fixes).
Command
Phase 4 — Ship. Runs devops-engineer for CI/CD, cloud deploy, and release. Reads verify-handoff.md for clean context.
Command
Build, launch, monetize, monitor, and scale a software startup end-to-end from the codebase.