jonggrang

Deterministic AI development workflow orchestrator. Manages task boards (.jonggrang/jonggrang-tasks.json), runs 16-phase pipelines (BUGFIX/SMALL/MEDIUM/LARGE), installs lifecycle hooks for Claude Code and OpenCode, and coordinates five specialist roles (Lead/Developer/Reviewer/TestLead/Tester). Use when planning features, executing multi-step development workflows, or orchestrating AI coding agents. Run via npx jonggrang.

16-phase feature orchestration workflow. Runs in the main thread as Kernel Mode. Coordinates the Lead→Developer→Reviewer→TestLead→Tester assembly line.

Protocol for agents to write structured outputs that survive session resets and are findable by the orchestrator.

GitHub workflow automation with the gh CLI — pull requests, issues, releases, the REST/GraphQL API, and safe message escaping. Auth via GH_TOKEN (set in global settings, attached to the sandbox env).

GitLab workflow automation with the glab CLI — merge requests, issues, CI, releases, and safe message escaping. Auth via GITLAB_TOKEN (set in global settings, attached to the sandbox env).

Prevents premature exit and infinite loops. Three mechanisms: Completion Promises, Scratchpads, Loop Detection.

Deep knowledge about deploying applications to AWS (EC2, ECS, S3, CloudFront, Cloud Run).

Deep knowledge about deploying applications to Cloudflare (Pages, Workers, Wrangler).

Deep knowledge about deploying applications to Coolify (self-hosted PaaS).

Deep knowledge about building and pushing container images to Docker registries (DockerHub, GHCR, ECR, GCR).

Deep knowledge about deploying applications to Fly.io (MicroVMs, Docker).

Deep knowledge about deploying applications to Google Cloud Platform (Cloud Run, App Engine, Compute Engine).

Deep knowledge about deploying applications to Kubernetes clusters using kubectl, helm, and manifests.

Deep knowledge about deploying applications to Netlify (static sites, edge functions, serverless functions).

Deep knowledge about deploying applications to Railway (PaaS, Docker, Nixpacks).

Deep knowledge about deploying applications to Baremetal servers or Virtual Private Servers (VPS) using SSH, SCP, Rsync, and PM2/Systemd.

Deep knowledge about deploying applications to Vercel (Next.js, static sites, edge functions).

Route deployment tasks to the right library skill. Detects intent and returns specific platform skill file paths to load.

Generate deployment configuration files (Dockerfile, vercel.json, wrangler.toml, etc.) based on target type.

Map UI elements and code relationships (affordances).

Cross-reference diffs to update README, ARCHITECTURE, CHANGELOG.

Eng manager-mode plan review. Lock in the execution plan, data flow, diagrams, edge cases.

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises.

Iteratively define problem and solution shapes.

Run linters/typecheckers to calculate health score.

Evaluate error handling, i18n, text overflow, and edge cases.

Comprehensive UI/UX compliance check (A11y, performance, responsive).

Infrastructure-first security audit (OWASP, secrets, dependencies).

Used by the Lead agent during Phase 6 (Brainstorm) to collaboratively explore user intent, requirements, and alternative approaches before locking in the architecture. Helps turn raw ideas into fully formed specs through natural dialogue.

Used by the Developer agent during Phase 8 (Implement) when building web components, pages, or UI features. Provides strict aesthetic guidelines to create distinctive, production-grade frontend interfaces that avoid generic 'AI slop' aesthetics.

Used by the Reviewer agent during Phase 9 (DesignVerify) and Phase 11 (Quality) to evaluate frontend code. Assesses visual hierarchy, spacing consistency, accessibility, and detects formulaic 'AI slop' design patterns, providing actionable feedback to the Developer.

Resume an interrupted orchestration run across Claude Code sessions using MANIFEST.yaml

Generate Product Requirements Document from feature intent/description

Setup authentication flow (register, login, session/JWT, middleware)

Generate UI component with component file, test, and story (optional)

Identify independent failures and spawn concurrent agents. Turns sequential N×time into 1×time.

Route API design/implementation tasks to the right library skill.

Route backend tasks to the right library skill. Detects intent and returns specific skill file paths to load.

Route database tasks to the right library skill. Covers migrations, query optimization, ORM, transactions.

Route frontend tasks to the right library skill. Detects React/Vue/CSS intent and returns specific skill file paths.