By rajasekarm
Raja's agentic team — a collection of specialized agents, skills, and commands for high-velocity engineering.
Velo — Structured debug loop. Symptom → hypothesis → root cause → handoff.
Velo — Start new work. Mandates planning before any code is written.
Velo Engineering Manager — delegates tasks to your agentic team
Velo — Open discussion. Get advice before deciding to build.
You are a senior Automation Engineer specialising in test automation. You report to Velo (Engineering Manager).
You are a senior Automation Reviewer. You review test code for quality, coverage, reliability, and maintainability.
You are a Principal Backend Engineer. You report to Velo (Engineering Manager).
You are a senior Backend Reviewer. You review Node.js/TypeScript and Go code for correctness, security, and performance.
You are a Commit Agent. You generate precise commit messages and create git commits. In PR mode, you open pull requests. You report to Velo (Engineering Manager).
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.
Rajasekar's high-velocity engineering team, portable across Claude Code and Codex.
Velo is an agentic engineering team — a full squad of specialised role agents coordinated by an Engineering Manager. Describe what you want built. Velo plans it, gets your approval at the right gates, runs work in parallel, and ships with review baked in.
task-breakdown.md alongside the engineering design doc — who does what, in what order, what can run in parallel. Build phase executes it directly, no guessing./security-review.deep-reasoning. PM, builders, and reviewers use balanced. ADAPTER.md maps these classes to the active runtime.| Agent | Model Class | Responsibility |
|---|---|---|
| Velo (Engineering Manager) | — | Orchestrates the team, owns delivery, never implements |
| Distinguished Engineer | deep-reasoning | Peer to EM — sets technical bar, reviews architecture |
| Agent | Model Class | Responsibility |
|---|---|---|
| Product Manager | balanced | Requirements, user stories, scope decisions, PRD |
| Agent | Model Class | Responsibility |
|---|---|---|
| Tech Lead | deep-reasoning | Technical design, API surface, engineering design doc |
| Agent | Model Class | Responsibility |
|---|---|---|
| Observability Engineer | balanced | Implements observability infra — reviews all BE tasks for metrics, logging, tracing gaps |
| Security Engineer | balanced | On-demand vulnerability review (via /security-review); not auto-attached to BE/FE reviews |
| Agent | Model Class | Responsibility |
|---|---|---|
| Frontend Engineer | balanced | React components, routing, client-side logic |
| Backend Engineer | balanced | APIs, business logic, Node.js services |
| Database Engineer | balanced | Schema design, migrations, query optimisation |
| Infrastructure Engineer | balanced | Docker, Kubernetes, AWS, Kafka, CI/CD |
| Automation Engineer | balanced | Playwright e2e tests, Vitest unit tests |
| Agent | Model Class | Responsibility |
|---|---|---|
| Frontend Reviewer | balanced | UI quality, component correctness, React patterns |
| Backend Reviewer | balanced | API design, error handling, Node.js correctness |
| Database Reviewer | balanced | Schema correctness, index coverage, query safety |
| Infrastructure Reviewer | balanced | Config hygiene, security posture, cost |
| Automation Reviewer | balanced | Test coverage, reliability, flakiness |
| Agent | Model Class | Responsibility |
|---|---|---|
| Commit | balanced | Analyse diff, generate commit message, create git commit |
| Spec Writer | balanced | Write technical specifications from PRDs when needed |
| Learnings Agent | balanced | Extract codebase-specific learnings after rework cycles |
See WORKFLOW.md for detailed flow diagrams.
/velo:new — New featuresStructured workflow: PM → Tech Lead → DE review → Build → Review → Commit. Mandatory planning and approval gates before any code is written.
/velo:task — Day-to-day tasksLightweight delegated flow for bug fixes, refactors, and small changes: validate scope, announce the plan, use an inline transient task-spec when needed, then build, review, and ship.
/velo:yo — AdvisoryAsk Velo anything. Get a direct answer, a TL + DE panel, or a full PM + TL + DE panel depending on the question.
/velo:hunt — Structured debug loopSymptom → hypothesis → root cause → handoff. Tight, iterative debugging mode that ends with a confirmed root cause and a handoff brief to /velo:task — or an explicit dead-end with what was ruled out.
npx claudepluginhub rajasekarm/velo --plugin veloAn engineering team in a box for Claude Code. 12 specialized subagents (planner, fullstack-engineer, refactor-specialist, migration-engineer, frontend-designer, critic, vuln-verifier, debugger, db-expert, onboarder, tool-expert, web-researcher) plus 15 automation hooks (pre-commit secret scan, MCP health tracking, cost tracking, test runner, branch protection, large file warner, session summary, batch format, design quality, config protection, and more) wired by the P7/P9/P10 methodology with three red lines: closure discipline, fact-driven, exhaustiveness.
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Full-stack agents — frontend, backend, API, DevOps architects
Give soul to your workflow. 58 AI-powered skills across 17 roles — PM, Dev, Backend, Frontend, QA, UX, Data, Detect, WordPress, Release, Security, DevOps, and Core. Spec-to-ship pipeline: scaffold, implement, test, secure, deploy. Features two-phase workflow with human approval, quality-reviewer agent, token optimization, and continuous improvement via LEARN.md system.
Engineering team — 15 agents: Apex, Forge, Relay, Spine, Flux, Warden, Vigil, Prism, Cortex, Touch, Volt, Atlas, Lens, Proof, Pave
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.