Agyflow

Structured, standards-aware development workflows for Google Antigravity CLI

Describe what you want to build, and the plugin handles the rest - from specification through implementation to verification - while enforcing your project's coding standards at every step.

Started as an OpenCode fork of Maister Claude Code plugin (originally known as Owflow), Agyflow is a plugin for Google Antigravity CLI (agy) designed to deliver production-ready workflows using Antigravity's plugin architecture.

What You Get

• Guided workflows for features, bug fixes, enhancements, performance, migrations, research, and product design
• Auto-discovered standards from your codebase - config files, source patterns, and documentation are analyzed and enforced throughout every workflow
• Test-driven implementation with automated planning, incremental verification, and full test suite runs before completion
• Pause and resume any workflow - state is preserved across sessions
• Production readiness checks including code review, reality assessment, and pragmatic over-engineering detection

Getting Started

Prerequisites

• Google Antigravity CLI (agy) installed and configured
• Node.js >= 25

Installation

Install Agyflow using the Antigravity CLI:

Remote Installation

Install directly from the GitHub repository:

agy plugin install https://github.com/palucdev/agyflow

Local Installation

Clone the repository and install it from the local directory:

# Clone the repository
git clone https://github.com/palucdev/agyflow.git
cd agyflow

# Install dependencies and build (requires Bun)
bun install
bun run build

# Install the plugin locally via the CLI
agy plugin install .

Managing the Plugin

Verify that the plugin is installed and active:

agy plugin list

You can also enable, disable, or uninstall Agyflow using:

agy plugin enable agyflow
agy plugin disable agyflow
agy plugin uninstall agyflow

Initial project setup

Initialize your project to auto-detect coding standards and generate project documentation. Run this inside an active agy session:

/flow-init

This scans your codebase and creates .agyflow/ with standards, docs, and task folders. May take a few minutes on larger projects.

If you have another project already using Agyflow, you can reuse its standards as a starting point:

/flow-init --standards-from=/path/to/other-project

First Workflow

Start a workflow by running this inside an active agy session:

/development Add user profile page with avatar upload

Or just discuss your task with Agent and then run:

/development

The plugin picks up context from your conversation - no arguments needed.

How It Works

1. You describe a task - either as an argument or just in conversation
2. The plugin classifies it (feature, bug, enhancement, etc.) and proposes a workflow
3. You confirm, and it guides you through phases: requirements → spec → plan → implement → verify
4. At each phase, it asks for your input and decisions
5. You get tested, verified code with a detailed work log

All artifacts are saved in .agyflow/tasks/ organized by type and date.

Context-Aware Commands

Every workflow command works without arguments. The plugin reads your current conversation to extract the task description and auto-detect the task type:

You: "The login page throws a 500 error when the session expires"
You: /development
→ Auto-detects: bug fix, extracts description from conversation

You: /standards-update
→ Scans conversation for patterns like "we always use..." or "prefer X over Y"

You can always be explicit when you prefer - arguments and flags simply override the auto-detection.

Supported Workflows

Command	Use When
/development	Features, bug fixes, enhancements
/research	Research with synthesis and solution design
/performance	Optimizing speed or resource usage
/migration	Changing technologies or patterns
/product-design	Product and feature design

Task type (feature/bug/enhancement) is auto-detected from context. Override with --type=feature|bug|enhancement if needed. Or use /work as a single entry point that routes to the right workflow.

Quick Commands

For smaller tasks that don't need a full workflow:

Command	Use When	Artifacts
/quick-plan	You want a plan with standards awareness before coding	task.yml, findings.md
/quick-dev	You know what to do - just implement with standards applied	task.yml, summary.md
/quick-bugfix	Quick TDD-driven bug fix — write failing test, fix, verify	task.yml, findings.md, summary.md

All quick commands create lightweight task directories under .agyflow/tasks/quick-{type}/ with a task.yml for traceability.

Standards-Aware Development

This is the key differentiator. Agyflow doesn't just run workflows - it learns your project's conventions and enforces them:

• flow-init scans config files, source code, and documentation to auto-detect your coding standards
• Continuous checking - standards are consulted before specification, during planning, and while coding (not just at the start)
• /standards-discover refreshes standards from your evolving codebase
• /standards-update lets you add or refine standards manually, or sync from another project with --from=PATH

Standards live in .agyflow/docs/standards/ and are indexed in .agyflow/docs/INDEX.md.

Important: Do not use planning mode with workflows (see Best Practices below).

Best Practices

Don't use Antigravity's Planning Mode when starting a workflow. Planning is a built-in part of every workflow — the orchestrator creates specs, plans, and other files as it goes. Google Antigravity's planning/planning mode restricts file creation, which conflicts with this. Let the workflow handle planning on its own.

Start workflows in a fresh session. This is especially useful when chaining workflows (e.g., research → development). Research and product-design artifacts already contain all the context needed, so a clean session avoids noise from prior conversation.

Chain workflows by passing a task folder. If you've completed a research or product-design workflow and want to build on those results, pass the task folder directly:

/development .agyflow/tasks/research/2026-01-12-oauth-research

You can also append additional instructions to narrow scope or guide the workflow:

/development .agyflow/tasks/product-design/2026-03-10-dashboard-redesign Implement only phase 1

Known Issues

Orchestrator may stall after long phases. After context compaction (which typically happens after lengthy phases like implementation), the main agent may stop progressing automatically. If you notice it's idle, just type something like "continue" or "proceed" — it will pick up where it left off. You can also re-invoke the workflow in resume mode to reload the orchestrator state:

/development .agyflow/tasks/development/2026-03-24-my-feature

Learn More

• Workflow Details - phases, examples, and task structure for each workflow type
• Full Command Reference - all workflow, review, utility, and quick commands