stegoro

stegoro

Automatically generate steering policies that drive purpose-built AI agents through structured, quality-assured workflows.

English • 日本語

Why

Building a purpose-built AI agent is hard. Without a structured policy, agents produce inconsistent outputs, skip critical validation steps, and lack quality assurance. Writing these policies by hand is time-consuming and error-prone.

stegoro solves this by automating the entire policy creation process — from understanding the agent's purpose to generating a complete, quality-calibrated policy set.

What

A meta-agent for Claude Code that generates steering policies for purpose-built AI agents. It produces a complete set of rule files that govern an agent's behavior through structured, multi-phase workflows.

Features

• 4-Phase Workflow — Discovery, Design, Generation, and Refinement phases ensure thorough policy creation
• Adaptive Depth — Automatically adjusts research and design depth based on domain complexity (Minimal / Standard / Comprehensive)
• 4 Agent Types — Supports Process, Task, Analytical, and Hybrid agent patterns
• AI-DLC Quality Assurance — Validates output against 11 quality dimensions including adaptive workflow, mandatory checkpoints, audit trail, and overconfidence prevention
• Interactive Dialogue — Structured question-and-answer flow with approval gates at every critical decision point
• Session Continuity — State tracking enables pause and resume across sessions
• Complete Audit Trail — ISO 8601 timestamped logging of all decisions and user inputs

Generated Output

.<agent-name>/
├── <agent-name>-rules/
│   └── core-workflow.md              # Master orchestrator
└── <agent-name>-rule-details/
    ├── common/                       # Cross-phase rules
    │   ├── welcome-message.md
    │   ├── process-overview.md
    │   ├── question-format-guide.md
    │   ├── content-validation.md
    │   ├── session-continuity.md
    │   ├── error-handling.md
    │   ├── terminology.md
    │   └── ...
    ├── <phase-1>/                    # Phase-specific rules
    │   ├── <stage-1>.md
    │   └── ...
    └── <phase-N>/
        └── ...

How

Prerequisites

• Claude Code installed and configured

Installation

Add the marketplace and install the plugin (one-time setup):

/plugin marketplace add yoshidashingo/steering-policy-generator
/plugin install stegoro@steering-policy-generator

Usage

1. Start the steering policy generator with a slash command:

/stegoro:generate a code review agent

More examples:

/stegoro:generate a proposal writing agent
/stegoro:generate a security audit agent

Or resume a previous session:

/stegoro:generate

2. The generator will guide you through the 4-phase workflow interactively:

Phase	Purpose	Key Activities
Discovery	Understand what and why	Purpose analysis, domain research, stakeholder identification, scope definition
Design	Architect the policy	Workflow architecture, common rules, phase rules, quality mechanisms
Generation	Create the policy files	Core workflow, common rules, phase rules, integration validation
Refinement	Ensure quality	Completeness review, consistency review, quality calibration

3. At each stage, review and approve before proceeding. The generator never advances without your explicit confirmation.

Example Agents Built With This Tool

This repository includes example policies generated by the tool:

Agent	Description	Directory
AI-DLC	AI-Driven Development Life Cycle	.aidlc/
Proposal Writer	RFP response and proposal generation	.proposal-writer/
Steering Policy Maker	This tool's own policy (self-referential)	.steering/

Documentation

Visit the documentation site for detailed usage guides.

License

MIT