Back to list
tuannvm

pagent

by tuannvm

Interactive TUI to orchestrate AI agents. Give it a PRD, get back architecture, test plan, security assessment, and working code.

0🍴 0📅 Dec 31, 2025

SKILL.md


name: pagent description: Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.

Pagent Usage Guide

Pagent orchestrates specialist AI agents to transform Product Requirement Documents (PRDs) into working code.

Quick Start

# Interactive TUI (recommended)
pagent ui

# Run with a PRD file
pagent run ./prd.md

# Check agent status
pagent status

Agents

Pagent runs 5 specialist agents in dependency order:

AgentOutputPurpose
architectarchitecture.mdTechnical design, API specs, data models
qatest-plan.mdTest cases, acceptance criteria
securitysecurity-assessment.mdThreat model, security requirements
implementercode/*Working code implementation
verifier*_test.go, verification-report.mdTests and validation

Execution Order

Level 0: architect
Level 1: qa, security (parallel)
Level 2: implementer
Level 3: verifier

Commands

Run Agents

# Run all agents (parallel by default)
pagent run ./prd.md

# Run specific agents
pagent run ./prd.md --agents architect,qa

# Sequential mode
pagent run ./prd.md --sequential

# Resume (skip up-to-date outputs)
pagent run ./prd.md --resume

# Force regeneration
pagent run ./prd.md --force

# Custom output directory
pagent run ./prd.md -o ./docs/

Interactive TUI

pagent ui              # Start fresh
pagent ui ./prd.md     # Pre-fill with PRD
pagent ui --accessible # Screen reader support

Monitor & Control

pagent status                    # Check running agents
pagent logs <agent>              # View agent output
pagent message <agent> "text"    # Send guidance
pagent stop <agent>              # Stop specific agent
pagent stop --all                # Stop all agents

MCP Server

pagent mcp                                  # Stdio (Claude Desktop)
pagent mcp --transport http --port 8080     # HTTP mode
pagent mcp --transport http --oauth \
  --issuer https://company.okta.com \
  --audience api://pagent                   # With OAuth

Personas

Control implementation style:

PersonaUse Case
minimalMVP, prototype - ship fast
balancedStandard projects (default)
productionEnterprise - comprehensive testing, security
pagent run ./prd.md --persona production

Configuration

Initialize config:

pagent init

Creates .pagent/config.yaml:

output_dir: ./outputs
timeout: 300
persona: balanced

preferences:
  api_style: rest      # rest | graphql | grpc
  language: go         # go | python | typescript
  testing_depth: unit  # none | unit | integration | e2e
  containerized: true
  include_ci: true

stack:
  cloud: aws
  compute: kubernetes
  database: postgres
  cache: redis

Writing a PRD

A good PRD includes:

# Product: [Name]

## Problem Statement
What problem are we solving?

## Features
- Feature 1: description
- Feature 2: description

## Requirements
- Functional requirements
- Non-functional requirements (performance, security)

## Constraints
- Technology constraints
- Timeline constraints

Workflows

Quick Architecture Review

pagent run ./prd.md --agents architect
# Review architecture.md, iterate on PRD

Full Pipeline

pagent ui ./prd.md
# Select production persona
# Run all agents
cd outputs/code && go build ./...

Iterative Development

pagent run ./prd.md --agents architect
# Review architecture.md
pagent run ./prd.md --resume  # Run remaining agents

Troubleshooting

IssueFix
Timeoutpagent run ./prd.md --timeout 600
Port in usepagent stop --all
Incomplete outputpagent message <agent> "Please complete..."
Agent stuckpagent stop <agent> then re-run

Score

Total Score

75/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新

+5
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

+5

Reviews

💬

Reviews coming soon