microsoft/hve-core

Public

mirrored fromhttps://github.com/microsoft/hve-coreAvailable

CodeCommitsIssuesPull requestsActionsInsightsSecurity
hve-core-v3.2.2

Branches

Tags

  • No tags available.
0Branches0Tags
Go to file
Add file
Code

Clone

HTTPS

Download ZIP

docs/agents/README.md

94lines · modecode

1---
2title: Agent Systems Catalog
3description: Overview of all hve-core agent systems with workflow documentation and quick links
4sidebar_position: 1
5author: Microsoft
6ms.date: 2026-02-12
7ms.topic: overview
8keywords:
9 - github copilot
10 - agents
11 - agent catalog
12estimated_reading_time: 5
13---
14
15hve-core organizes specialized agents into functional groups. Each group combines agents, prompts, and instruction files into cohesive workflows for specific engineering tasks.
16
17| Group | Agents | Complexity | Documentation |
18|-----------------------------------------|----------|-------------|---------------------------------------------------------------------------------|
19| RPI Orchestration | 5 | High | [RPI Documentation](../rpi/README.md) |
20| GitHub Backlog Management | 1 active | Very High | [Backlog Manager](github-backlog/README.md) |
21| ADO Backlog Management | 1 active | Very High | [Backlog Manager](ado-backlog/README.md) |
22| Project Planning | 5 | Medium-High | [Project Planning](project-planning/README.md) |
23| [Security Planning](#security-planning) | 2 active | Very High | [Security Planner](security/README.md), [SSSC Planner](sssc-planning/README.md) |
24| [RAI Planning](#rai-planning) | 1 active | Very High | [RAI Planner](rai-planning/README.md) |
25| Data Pipeline | 4 | Medium | Planned |
26| DevOps Quality | 2 | High | Planned |
27| Meta/Engineering | 1 | High | Planned |
28| Infrastructure | 1 | Very High | Planned |
29| Utility | 1 | Low-Medium | [Memory Agent](github-backlog/using-together.md#session-persistence) |
30| [Design Thinking](#design-thinking) | 2 | High | Active |
31
32## RPI Orchestration
33
34The Research, Plan, Implement methodology separates complex tasks into specialized phases. Five agents (task-researcher, task-planner, task-implementor, task-reviewer, and the RPI orchestrator) coordinate through planning files to deliver structured engineering workflows. See the [RPI Documentation](../rpi/) for the full guide.
35
36## GitHub Backlog Management
37
38Automates issue discovery, triage, sprint planning, and execution across GitHub repositories. The backlog manager agent orchestrates five distinct workflows with three-tier autonomy control. See the [Backlog Manager Documentation](github-backlog/) for workflow guides.
39
40## ADO Backlog Management
41
42Automates work item discovery, triage, sprint planning, execution, PR creation, build monitoring, and task planning across Azure DevOps projects. The ADO Backlog Manager agent orchestrates nine distinct workflows with three-tier autonomy control. See the [Backlog Manager Documentation](ado-backlog/README.md) for workflow guides.
43
44## Project Planning
45
46Five specialized agents for project planning activities. Includes builders for Business Requirements Documents, Product Requirements Documents, Architecture Decision Records, architecture diagrams, and security plans. See the [Project Planning Agents](project-planning/README.md) for detailed documentation.
47
48## Data Pipeline
49
50Processes and transforms data across formats and systems. Four agents handle data extraction, transformation, validation, and loading workflows.
51
52## DevOps Quality
53
54Two agents focused on code quality and deployment reliability. Covers PR review automation and build pipeline analysis.
55
56## Meta/Engineering
57
58The prompt builder agent creates and validates prompt engineering artifacts. Supports interactive authoring with sandbox testing for prompts, instructions, agents, and skills.
59
60## Infrastructure
61
62Manages cloud infrastructure provisioning and configuration. Handles Bicep and Terraform deployments with validation and drift detection.
63
64## Utility
65
66General-purpose agents for cross-cutting concerns such as session persistence and context management across workflows.
67
68## Security Planning
69
70Guides teams through a six-phase security assessment covering system scoping, operational bucketing, standards mapping, security model analysis, impact assessment, and backlog handoff. The security planner agent conducts interactive sessions with structured state tracking and produces dual-platform work items for ADO and GitHub. See the [Security Planner Documentation](security/) for phase details and entry modes.
71
72The **SSSC Planner** guides teams through a structured six-phase supply chain security assessment. It inventories 27 supply chain capabilities, maps against OpenSSF Scorecard, SLSA, Sigstore, and SBOM standards, performs gap analysis with adoption categories, and generates priority-sorted backlog items. Supports four entry modes: capture, from-PRD, from-BRD, and from-security-plan. See [SSSC Planning](sssc-planning/README.md) for details.
73
74## RAI Planning
75
76Guides teams through a six-phase responsible AI assessment covering AI system scoping, sensitive uses screening, RAI standards mapping, security model analysis, impact assessment, and review with backlog handoff. The RAI planner agent builds on security plan outputs when available and produces scored assessments with dual-platform work items. See the [RAI Planner Documentation](rai-planning/) for phase details and entry modes.
77
78## Design Thinking
79
80The Design Thinking agents provide AI-assisted coaching through a nine-method, three-space framework for human-centered design.
81
82| Agent | Purpose |
83|---------------------|--------------------------------------------------------------|
84| `dt-coach` | Coaches teams through all 9 DT methods with session tracking |
85| `dt-learning-tutor` | Teaches DT curriculum with exercises and assessments |
86
87> Brought to you by microsoft/hve-core
88
89---
90
91<!-- markdownlint-disable MD036 -->
92*🤖 Crafted with precision by ✨Copilot following brilliant human instruction,
93then carefully refined by our team of discerning human reviewers.*
94<!-- markdownlint-enable MD036 -->
95