feat: Introduce agent-agnostic architecture and multi-user personalization

- Updated vision statement to emphasize agent-agnostic design and multi-user personalization features.
- Added new functions to generate canonical command files and thin platform shims in the create-release-packages scripts.
- Enhanced documentation to reflect the new architecture, including detailed explanations of the file layout and shim behavior.
- Implemented the `/speckit.personalize` command to allow users to create personalized command overrides.
- Updated contributing guidelines to ensure compliance with the new architecture.
- Revised release notes to highlight the new features and improvements in the latest version.

Author: markhazleton

.documentation/adaptive-lifecycle.md

@@ -64,6 +64,24 @@ Systems and documentation must evolve together:
 - Documentation lifecycle managed explicitly at release boundaries
 - Historical decisions preserved for future reference
 
+### 5. Agent-Agnostic First
+
+Every AI coding assistant is a first-class citizen:
+
+- Canonical prompts live in `.documentation/commands/` — a single source of truth
+- Platform directories (`.claude/`, `.github/`, `.cursor/`, etc.) contain only thin shims
+- Teams can mix agents without workflow friction — the same governance applies to all
+- Adding new agent support requires only a shim, not content duplication
+
+### 6. Multi-User Collaboration
+
+Teams share governance while individuals retain customization freedom:
+
+- Shared constitutions, specs, plans, and quality gates provide team consistency
+- `/speckit.personalize` creates per-user prompt overrides in `.documentation/{git-user}/commands/`
+- Personalized overrides are committed to git for team transparency
+- Delete an override to revert to the shared default — no merge conflicts
+
 ---
 
 ## Functional Architecture

.documentation/index.md

@@ -2,7 +2,23 @@
 
 *Build high-quality software faster with AI-driven lifecycle management.*
 
-**An Adaptive System Life Cycle Development (ASLCD) Toolkit** - a community extension of Spec Kit that combines specification-driven development with constitution-powered quality assurance and right-sized workflows for tasks of any complexity.
+**An Adaptive System Life Cycle Development (ASLCD) Toolkit** - agent-agnostic, multi-user, and full-lifecycle. A community extension of Spec Kit that combines specification-driven development with constitution-powered quality assurance and right-sized workflows for tasks of any complexity.
+
+---
+
+## Three Pillars
+
+### 🔀 Agent-Agnostic by Default
+
+Every AI coding assistant is a first-class citizen. Canonical command prompts live in `.documentation/commands/` — a single source of truth — while each platform receives only thin shims. Switch agents, use multiple agents on the same project, or onboard new team members on different tools.
+
+### 👥 Multi-User Personalization
+
+Teams share prompts, but individuals can customize any command via `/speckit.personalize`. Personalized overrides live in `.documentation/{git-user}/commands/`, are committed to git, and take priority over shared defaults. Delete the override to revert.
+
+### 🔄 Full Lifecycle Coverage
+
+From greenfield creation through brownfield discovery, ongoing maintenance, documentation cleanup, release management, and constitution evolution — every phase of the SDLC is supported.
 
 ---
 
@@ -39,6 +55,8 @@ Traditional spec-driven development works well for greenfield projects with majo
 | `/speckit.release` | ❌ | ✅ Release documentation |
 | `/speckit.evolve-constitution` | ❌ | ✅ Constitution evolution |
 | `/speckit.harvest` | ❌ | ✅ Knowledge harvest and cleanup |
+| Agent-agnostic architecture | ❌ Duplicated prompts per agent | ✅ Canonical prompts + thin shims |
+| Multi-user personalization | ❌ | ✅ `/speckit.personalize` per-user overrides |
 | Multi-agent support | Limited | ✅ 17+ AI agents |
 
 Learn more: [Adaptive Lifecycle Documentation](adaptive-lifecycle.md)
@@ -174,6 +192,7 @@ Constitution-powered quality commands that work independently.
 | `/speckit.clarify` | Clarify specification requirements |
 | `/speckit.checklist` | Generate quality checklists |
 | `/speckit.analyze` | Artifact consistency checking |
+| `/speckit.personalize` | Create per-user prompt customizations |
 
 ---
 

.documentation/installation.md

@@ -3,11 +3,13 @@
 ## Prerequisites
 
 - **Linux/macOS** (or Windows; PowerShell scripts now supported without WSL)
-- AI coding agent: [Claude Code](https://www.anthropic.com/claude-code), [GitHub Copilot](https://code.visualstudio.com/), [Codebuddy CLI](https://www.codebuddy.ai/cli) or [Gemini CLI](https://github.com/google-gemini/gemini-cli)
+- Any [supported AI coding agent](https://github.com/MarkHazleton/spec-kit#-supported-ai-agents) (17+ agents supported — Claude Code, GitHub Copilot, Gemini CLI, Cursor, and more)
 - [uv](https://docs.astral.sh/uv/) for package management
 - [Python 3.11+](https://www.python.org/downloads/)
 - [Git](https://git-scm.com/downloads)
 
+> **Agent-Agnostic**: Spec Kit works identically with every supported agent. Canonical prompts live in `.documentation/commands/` — your chosen agent gets thin shims that redirect there. You can switch agents at any time or have different team members use different agents on the same project.
+
 ## Installation
 
 Spec Kit supports two installation scenarios:

.documentation/quickstart.md

@@ -5,6 +5,9 @@ This guide will help you get started with Spec-Driven Development using Spec Kit
 > [!NOTE]
 > All automation scripts now provide both Bash (`.sh`) and PowerShell (`.ps1`) variants. The `specify` CLI auto-selects based on OS unless you pass `--script sh|ps`.
 
+> [!TIP]
+> **Agent-Agnostic**: Spec Kit works identically with any of 17+ supported AI agents. The workflow below applies regardless of which agent you choose — canonical prompts live in `.documentation/commands/` and your agent gets thin shims that redirect there.
+
 ## The 6-Step Process
 
 > [!TIP]
@@ -99,6 +102,18 @@ Then, use the `/speckit.implement` slash command to execute the plan.
 /speckit.implement
 ```
 
+## Optional: Personalize Your Workflow
+
+If you want to customize any command for your individual working style without affecting your team:
+
+```markdown
+/speckit.personalize specify       # Personalize how you write specs
+/speckit.personalize plan          # Personalize your planning approach
+/speckit.personalize implement     # Personalize implementation behavior
+```
+
+This creates a copy of the shared prompt in `.documentation/{your-git-user}/commands/` that takes priority when you run the command. Your team sees the same shared defaults; you get your version. Delete the file to revert.
+
 ---
 
 ## Upgrading Spec Kit

.documentation/roadmap.md

@@ -6,9 +6,11 @@
 
 ## Vision Statement
 
-Spec Kit Spark aims to become the definitive toolkit for AI-agent driven software development lifecycle management, providing teams with:
+Spec Kit Spark aims to become the definitive toolkit for AI-agent driven software development lifecycle management, built on three pillars:
 
-- **Complete lifecycle coverage** from project initiation through ongoing maintenance
+- **Agent-agnostic by default** — every AI assistant is a first-class citizen; canonical prompts live in `.documentation/commands/` with thin platform shims
+- **Multi-user personalization** — shared governance with individual customization via `/speckit.personalize` and per-user overrides in `.documentation/{git-user}/commands/`
+- **Complete lifecycle coverage** — from project initiation through ongoing maintenance, release management, and constitution evolution
 - **Adaptive workflows** that scale from quick fixes to complex features
 - **Living governance** where constitutions evolve with the systems they govern
 - **Measurable quality** through continuous compliance tracking
@@ -61,6 +63,8 @@ Spec Kit Spark aims to become the definitive toolkit for AI-agent driven softwar
 
 #### Platform Support
 
+- ✅ Agent-agnostic architecture (canonical prompts + thin platform shims)
+- ✅ Multi-user personalization (`/speckit.personalize`)
 - ✅ 17+ AI agent integrations
 - ✅ Cross-platform scripts (Bash + PowerShell)
 - ✅ Greenfield and brownfield support