v1.7.0: Advanced SDLC Workflow & Skill Enhancements 🚀

Release v1.7.0: Advanced SDLC Workflow & Skill Enhancements 🚀

Version 1.7.0 focuses on significantly upgrading the Software Development Life Cycle (SDLC) workflows, introducing advanced planning and execution protocols, and expanding platform compatibility to include Google Antigravity.

🚀 Enhancements & New Features

• Advanced SDLC Workflow Integration: Introduced comprehensive documentation and guides for the new Advanced Skills SDLC Workflow, bridging the gap between planning, codebase exploration, and execution. (Links added to README.md and landing pages).
• Google Antigravity Support: Installation scripts have been updated to seamlessly include and support Google Antigravity deployments, along with improved backup handling for existing configurations.
• Expanded Skill Sets & Protocols: Added robust workflows for execution agents (such as the /implement agent and sdlc-write-code skill) equipped with strict communication and context verification protocols.
• Ponytail / Lazy Senior Dev: Deeply refactored the ponytail-lazy-senior-dev skill documentation. Emphasized the "lazy senior developer" mindset, focusing on minimalism, code reuse, and smarter decision-making.
• Clean Architecture & Security: Added comprehensive references for code review, security hardening procedures, and clean code/architecture instructions to improve development standards.

🛠️ Architecture & Under-the-Hood Fixes

• Planning & Execution Directives: Refined the planning skill directives to enforce vertical slicing, strict task sizing limits, prefactoring strategies, and improved dependency mapping.
• Documentation & Standards Compliance: Updated the documentation standards path for all agents to ensure artifact consistency. Implemented strict adherence to SDLC documentation protocols across all skills.
• Memory & Agent Configuration: Streamlined the instruction directory search paths for clarity and efficiency. Added detailed memory configuration and Base Persona Activation guidance in AGENTS.md.
• Script Robustness: Implemented robust merging scripts for stages (Tahap) 3 to 9, significantly improving the skill extraction and cleanup processes.
• Cleanups: Removed obsolete scratch search files and simplified recursive search instructions by stripping redundant directory paths for memory file discovery.

---

Upgrade Guide:
As always, you can pull the latest changes or run the interactive installation scripts to sync these refinements across your preferred IDE platforms.

---

v1.6.0: Document Traceability & Orchestrator Refinements 📝

Release v1.6.0: Document Traceability & Orchestrator Refinements 📝

Version 1.6.0 focuses heavily on standardizing the reporting mechanisms for our Quality Gate agents (@ArtifactConsistencyChecker and @ClarificationAnalyst), implementing the robust Orchestrator-Reference architectural pattern, and resolving critical cross-platform synchronization bugs.

🚀 Enhancements & New Features

• Mandatory File Output for Quality Gates: Both @ArtifactConsistencyChecker and @ClarificationAnalyst are now explicitly empowered (via exception rules) to generate and save their final reports directly as markdown files in the docs/audit/ directory. This ensures critical project alignment data is never lost in chat history.
• AGENTS.md Policy Update: The overarching Source of Truth (AGENTS.md) has been updated. The specific pushback rules for the Quality Gate agents now include official exception clauses permitting file generation for audit reports.

🛠️ Architecture & Under-the-Hood Fixes

• Orchestrator-Reference Pattern Applied:
  • The artifact-consistency-checker skill has been refactored. Its heavy audit template is now securely isolated in references/AUDIT-REPORT-TEMPLATE.md.
  • The clarification-analyst skill has similarly been refactored to use references/CLARIFICATION-REPORT-TEMPLATE.md.
• Markdownlint Compliance: Resolved multiple linting violations (MD041: first-line-h1 and MD001: heading-increment) within the Clarification Report template, ensuring pristine document generation right out of the box.
• Global Path Translation Bug Fix: Fixed a critical bug in the synchronization engine. Previously, internal SKILL.md paths incorrectly referenced the .agents/rules/ directory when synced to other platforms. Now, paths dynamically translate to the correct {platform}/agents/ convention across all IDE integrations.
• GitHub Copilot Ecosystem Compliance (.github): Corrected a synchronization issue where agents deployed to the .github ecosystem were lacking the required .agent.md file extension. The deployment engine now enforces strict GitHub Copilot naming standards to prevent duplicate or unrecognized agents.

---

Upgrade Guide:
As always, you can pull the latest changes or run the interactive installation scripts to sync these refinements across your preferred IDE platforms.

v1.5.3: Project Researcher Utility Skill & Path Refinements 🔍

Release v1.5.3: Project Researcher Utility Skill & Path Refinements 🔍

Version 1.5.3 introduces the official integration of the project-researcher skill as a core Utility Skill and rectifies platform-specific path references to ensure a bulletproof multi-agent ecosystem.

🚀 Enhancements & New Features

• Promoted project-researcher to Utility Skill: The project-researcher skill has been successfully converted into a true Utility Skill (Cross-Cutting). The Dynamic Persona Activation block has been entirely removed to prevent Session Lock clashes. Now, any active persona (like @GodModeDev or @BrainstormingExplorerAnalyst) can securely invoke the architectural scanning workflow mid-session without losing their primary identity.
• Mandatory Pre-Flight Architecture Scan: @BrainstormingExplorerAnalyst has been updated with a strict directive to invoke the project-researcher skill at the beginning of Phase 0. If docs/ARCHITECTURE.md does not exist or is outdated, the analyst will automatically scan and document the repository architecture before generating the Discovery Draft, ensuring deep structural context.

🛠️ Architecture & Under-the-Hood Fixes

• Codex Ecosystem Synchronization (.codex): Fixed a critical pathing discrepancy in the Codex ecosystem. The .codex platform utilizes .toml formats for agents instead of .md. All SKILL.md internal references across .codex/skills/ have been bulk-updated to correctly point to their respective agents/*.toml files (e.g., brainstorming-explorer-analyst.toml), ensuring seamless skill-to-agent mapping.
• Skill Scope Constraints: The strict restriction prohibiting project-researcher from modifying application source code has been explicitly preserved within its Core Directives, ensuring that code-executing agents (like @GodModeDev) are safely restricted while performing exploratory scans.

📝 Documentation Updates

• README.md: Added project-researcher to the global Skills table to formally document its capabilities for repository architecture scanning.
• AGENTS.md: Registered project-researcher as a recognized cross-cutting Utility Skill within the overarching SDLC workflow.

---

Upgrade Guide:
As always, you can pull the latest changes or run the interactive installation scripts to sync these refinements across your preferred IDE platforms.

v1.5.2: Claude Code Native Support & Orchestrator Pattern

Release v1.5.2: Claude Code Native Support & Orchestrator Pattern

We are thrilled to announce version 1.5.2 of the Awesome Copilot ID ecosystem! This release brings a massive architectural upgrade to our core agents and officially introduces native support for Claude Code.

🚀 What's New

1. Claude Code Ecosystem Integration (.claude)

Awesome Copilot ID now officially supports Anthropic's Claude Code CLI!

• Native Directory Structure: Added a full .claude/ ecosystem, complete with agents/, skills/, standards/, and instructions/.
• YAML Frontmatter Injection: Custom agents (like GodModeDev.md) are now perfectly formatted with the exact name: and description: YAML tags required by Claude Code to register them as custom subagents.
• Context Isolation: Zero cross-platform leakage. All internal references strictly point to the .claude directory.
• Installer Support: The interactive install.sh and install.ps1 scripts now feature Claude Code as option 8 in the setup menu.

2. The "Orchestrator-Reference" Agent Architecture

We have completely overhauled the way our top-tier agents (@GodModeDev and @ExpertCodeReviewer) manage their instructions to prevent token bloat and context loss.

• Skill Orchestration: SKILL.md files have been stripped of heavy text and converted into lightweight orchestrators.
• Reference Delegation: Heavy instructions (like the SDLC Execution Workflow and Communication Protocols) are now cleanly separated into a references/ subdirectory.
• Macro/Micro Safeguards: Introduced a strict Three-Point execution mandate:
  1. Tests are Mandatory
  2. No Lazy Placeholders (// ... keep existing code ...)
  3. Strict Traceability

3. Global Ecosystem Synchronization

• The memory-manager skill across all 8 platforms (GitHub Copilot, OpenCode, CommandCode, Codex, Pi, Omp, Antigravity, and Claude) has been updated to seamlessly track project memories in .claude/instructions/.
• Updated AGENTS.md, README.md, dan index.html (along with localized translations) to reflect the new expanded multi-platform capabilities.

🛠️ Upgrading

To upgrade your existing project to v1.5.2, you can re-run the interactive installer or manually pull the latest changes and copy your preferred platform folder (e.g., .github, .claude) into your workspace.

# Linux/macOS
curl -fsSL https://raw.githubusercontent.com/GulajavaMinistudio/awesome-copilot-id/main/install.sh | bash

# Windows PowerShell
iwr -useb https://raw.githubusercontent.com/GulajavaMinistudio/awesome-copilot-id/main/install.ps1 | iex

As always, remember to back up your memory.instructions.md before overwriting!

v1.5.1: Strict SDLC Handoff & Anti-Scope Creep Enforcement

Release v1.5.1: Strict SDLC Handoff & Anti-Scope Creep Enforcement 🛡️

Version 1.5.1 focuses on fortifying the SDLC workflow architecture by enforcing strict Anti-Scope Creep boundaries on all planning, analysis, and review agents.

Moving forward, all non-executor agents are strictly mandated to halt execution once their respective design or documentation is complete. They are explicitly prohibited from independently writing or editing production code. Instead, these agents will automatically guide you through a standardized handoff process to the appropriate agent for the next phase.

🚀 Enhancements & New Features

• Mandatory Handoff Implementation: Introduced a formal handoff phase within the SKILL.md instructions, ensuring a structured and sequential agent workflow.
• Strict Execution Boundaries (Pushback Rules): Updated agent rule files and the project constitution (AGENTS.md) to guarantee that planning agents do not overstep their boundaries into functional coding.

🛠️ Agent-Specific Updates

• 🤖 @BrainstormingExplorerAnalyst (Phase 0):
  • Implemented Rule #4: Handoff After Discovery Draft Approval.
  • The agent will now explicitly request you to switch to @ProductManagerPRD upon the completion of the discovery draft.
• 🤖 @ProductManagerPRD (Phase PRD):
  • Implemented Rule #5: Handoff After PRD Approval.
  • Once Acceptance Criteria are approved, the agent will direct you to the @ClarificationAnalyst checkpoint and then to @SpecificationArchitect for technical design.
• 🤖 @ExpertCodeReviewer (Supplementary):
  • Restructured the workflow into 3 distinct phases (Code Review, Plan Generation, Handoff).
  • Implemented Rule #5: Handoff After Plan Approval.
  • Upon finalizing the Refactoring Plan, the agent will provide a ready-to-use prompt for you to pass to @GodModeDev for executing the fixes.
• 🤖 Boundary Maintenance for Other Agents:
  • The strict "No Coding" boundaries have also been tested and maintained across @SpecificationArchitect, @PlannerArchitect, and @BugRemediationArchitect.

🔄 Cross-Platform Propagation

All rule updates and workflow instructions (SKILL.md) mentioned above have been synchronized and validated across all 7 supported platform integrations:

• ✅ .agents (Standard)
• ✅ .github (GitHub Copilot)
• ✅ .codex (ChatGPT Codex)
• ✅ .commandcode (CommandCode)
• ✅ .omp (Oh My Pi)
• ✅ .opencode (OpenCode)
• ✅ .pi (Pi)

---

Release Notes:
This update is critical for users employing strict Sequential Development workflows, ensuring that no documentation, approval, or design steps are bypassed before @GodModeDev executes the code.

v1.5.0: Mandatory Context Injection, Language Policy Enforcement & Procedural Workflow Enhancements

Release v1.5.0: Mandatory Context Injection, Language Policy Enforcement & Procedural Workflow Enhancements

This release focuses on enforcing rigorous context traceability through the Mandatory Context Injection Protocol, ensuring consistent language policy across all agent interactions, and refining procedural workflows for advanced agent skills.

🚀 Features & Enhancements

• Mandatory Context Injection Protocol: Implemented strict context check protocols across all agents. Agents now require explicit attachment or mention of upstream documents (PRD, Spec, Plan) in the user's prompt before proceeding with analysis or generation. Added bypass options for minor, ad-hoc tasks.
• Global Language Policy Override: Introduced a global translation override rule in AGENTS.md and updated SKILL.md files to mandate that all user-facing responses strictly comply with the project's language policy, preventing agents from breaking character or using hardcoded English responses.
• Supplementary Skills Expansion: Added new supplementary skills including ponytail-lazy-senior-dev, memory-manager, and karpathy-guidelines to improve code reuse, context persistence, and adherence to AI coding best practices.

🛠️ Architecture & Under-the-Hood Fixes

• Procedural Workflow Strictness: Enhanced the sequential development steps and updated skill execution guidelines (especially for @ClarificationAnalyst, @ArtifactConsistencyChecker, and @GodModeDev) to enforce mandatory procedural workflows and the usage of standardized report templates.
• Context Protocol Refactoring: Refactored the context check protocols across multiple agent documents to ensure consistency in user prompts for required upstream documents. Removed redundant escape characters and improved phrasing for clarity.

📝 Documentation Updates

• AGENTS.md: Overhauled communication guidelines, testing policies, and table formatting for mandatory upstream documents. Added reminders for saving progress before session changes.
• README.md: Updated the table of contents, consolidated "Instructions" and "Prompts" into "Supplementary Skills", and added a section detailing dynamic persona activation for skill-driven agents.
• Agent Skill Refinement: Mass refactoring of skill documentation (SKILL.md) for @PlannerArchitect, @GodModeDev, @ExpertCodeReviewer, and bug remediation templates for improved clarity, consistency, and alignment with AI-optimized standards.

Full Changelog: v1.4.0...v1.5.0

v1.4.0: Agent Session Architecture, Documentation Standards & Utility Skills

Release v1.4.0: Agent Session Architecture, Documentation Standards & Utility Skills

This release focuses on multi-agent session stability, preventing persona lock clashes, and refining both the Grilling protocol and project documentation standards to ensure a seamless and robust SDLC workflow.

🚀 Features & Enhancements

• Domain Glossary & ADR Integration: Agents are now strictly bound to the newly implemented documentation standards. They will automatically enforce the use of CONTEXT.md (Domain Glossary) and docs/adr/ (Architecture Decision Records) during requirement analysis and technical specification to ensure architectural traceability and ubiquitous language.
• Promoted grilling to Utility Skill: The grilling skill is now officially a Utility Skill (Cross-Cutting). The @ClarificationAnalyst and @SpecificationArchitect can safely execute the "Grill Me" or "Grill with Docs" protocol mid-session without triggering a Persona Hijacking or session lock conflict.
• BYOS (Bring Your Own Skill) Support: Simplified integration for custom user-created skills. Any custom or downloaded skill that lacks the Dynamic Persona Activation block is automatically treated as a Utility Skill, allowing it to be invoked seamlessly without locking the active chat session.

🛠️ Architecture & Under-the-Hood Fixes

• Session Lock Clash Prevention: Conducted a massive cleanup (removing duplicated ## 🎭 Dynamic Persona Activation blocks) across 77 SKILL.md files for all supported platforms. This prevents double-overriding instructions and eliminates potential session lock clashes between agents.
• Precision Pathing for All Platforms: Updated target agent references inside all skill files to point specifically and precisely to their respective platform rules directories (e.g., .agents/rules, .github/agents, .codex/agents) instead of relying on generic wildcard paths.

📝 Documentation Updates

• README.md: Added a new "Session Locking & Utility Skills (Cross-Cutting)" section to document session lock rules, clarify the difference between Persona-Bound Skills and Utility Skills, and provide guidelines for custom skills.
• AGENTS.md: Updated the global state rules by explicitly adding grilling alongside memory-manager and fable-protocol as a Utility Skills Exception.

---

Full Changelog: https://github.com/GulajavaMinistudio/awesome-copilot-id/commits/main

v1.3.0: Memory Manager v2.0 — Knowledge Base & Intelligent Compaction

🧠 Memory Manager v2.0 — Knowledge Base & Intelligent Compaction

This release brings a major upgrade to the memory-manager skill across all 7 platforms (.agents, .codex, .commandcode, .github, .omp, .opencode, .pi). Memory Manager now features a permanent Knowledge Base and an intelligent compaction system.

✨ What's New in Memory Manager v2.0

Feature	Description
🧠 Knowledge Base	A permanent section at the top of memory.instructions.md for storing architecture, patterns, dead-ends, and metrics — survives compaction, never deleted
🗜️ Workflow 4 — Compaction Mode	Promotes valuable knowledge from old checkpoints into the Knowledge Base before checkpoints are removed
⚡ Fast Path via AGENTS.md	New Step 0: checks AGENTS.md for a recorded memory path — skips recursive search across 7 folders, locks the path instantly
🔗 AGENTS.md Auto-Recording	During Write Mode, the agent offers to record the memory path into AGENTS.md
📝 Expanded Checkpoint Template	Dead-ends now include a note for promotion to the Knowledge Base
🛡️ 5 New Anti-Patterns	Prevents: deletion without promotion, dead-end duplication, promoting ephemeral data, blind trust in AGENTS.md paths, and modifying AGENTS.md without consent

🔧 Other Changes

• AGENTS.md updated with a ## Memory Configuration section for fast-path discovery
• .github/copilot-instructions.md removed — content consolidated into AGENTS.md
• README.md updated — memory-manager description aligned with new features

📦 8 Files Updated

.agents/skills/memory-manager/SKILL.md       (+165 lines)
.codex/skills/memory-manager/SKILL.md         (+166 lines, retaining Codex Migration Notes)
.commandcode/skills/memory-manager/SKILL.md   (+165 lines)
.github/skills/memory-manager/SKILL.md        (+165 lines)
.omp/skills/memory-manager/SKILL.md           (+168 lines)
.opencode/skills/memory-manager/SKILL.md      (+165 lines)
.pi/skills/memory-manager/SKILL.md            (+168 lines)
AGENTS.md                                     (+6 lines)

🗑️ 1 File Removed

.github/copilot-instructions.md

---

Full Changelog: v1.2.0...v1.3.0

---

v1.2.0: BYOK (Bring Your Own Key) Configuration for GitHub Copilot 🔑

Release v1.2.0: BYOK (Bring Your Own Key) Configuration for GitHub Copilot 🔑

Version 1.2.0 introduces a brand-new byok-copilot-config/ module that lets developers plug their own API keys from third-party model providers directly into the GitHub Copilot chat experience in Visual Studio Code. This release is purely additive — no breaking changes to existing agents, skills, or instructions.

---

🌟 Major Highlights & New Features

🔑 New byok-copilot-config/ Module

A new, self-contained folder is now shipped at the repository root to help developers use BYOK (Bring Your Own Key) with GitHub Copilot in VS Code. The module ships complete documentation, a real-world chatLanguageModels.json template, and screenshots of the actual configuration flow.

• byok-copilot-config/byok-config-copilot.md — full-length BYOK guide covering built-in providers, extensions, custom endpoints, the chatLanguageModels.json schema, the model property reference, and security best practices.
• byok-copilot-config/README.md — short entry point with the "How to Use" flow, prerequisites, folder contents table, and security notes.
• byok-copilot-config/img/ — seven annotated screenshot files covering three VS Code UI screens (Add Models dropdown, Language Models editor, Chat model picker) with multiple states of each (empty dropdown, populated editor, pinned favorites, Other Models section, etc.) used throughout the documentation.

🤝 Multi-Provider Reference Configuration

The shipped chatLanguageModels.json example combines eight provider groups into one ready-to-paste configuration, covering both free and paid models:

• OpenRouter (vendor: openrouter) — built-in vendor; models are picked up automatically from the OpenRouter account.
• Copilot & Copilot CLI (vendor: copilot) — built-in Copilot models, with per-model reasoningEffort overrides configured via the settings block.
• Deepseek Platform — custom endpoint (chat-completions) with Deepseek v4 Flash and Deepseek v4 Pro.
• Kilo Gateway — custom endpoint exposing Kilo Auto Free.
• Opencode Zen — custom endpoint with DeepSeek V4 Flash Free, MiMo-V2.5 Free, Big Pickle Free, Nemotron 3 Ultra Free.
• OpenRouter-AutoFree — custom endpoint pointing at openrouter/free.
• Opencode Go — custom endpoint with 11 models, including GLM-5.2, Kimi K2.6, Kimi K2.7 Code, DeepSeek V4 Pro, DeepSeek V4 Flash, MiMo-V2.5, MiMo-V2.5-Pro, MiniMax M3, MiniMax M2.7, Qwen3.7 Max, Qwen3.7 Plus.
• Four of the Opencode Go models (MiniMax M3, MiniMax M2.7, Qwen3.7 Max, Qwen3.7 Plus) override the provider-level apiType to messages so they correctly target Anthropic-style endpoints.

📚 Documentation Coverage

The new BYOK guide is structured as a complete reference — every screenshot is embedded directly next to the step it illustrates, and the model property table covers id, name, url, apiType, toolCalling, vision, maxInputTokens, maxOutputTokens, editTools, thinking, streaming, zeroDataRetentionEnabled, supportsReasoningEffort, reasoningEffortFormat, and requestHeaders.

Other documented areas include:

• Adding models from built-in providers (Azure, Anthropic, Gemini, OpenAI) and from the additional vendors shown in the Add Models dropdown (OpenRouter, xAI).
• Adding models via Marketplace extensions (Foundry Toolkit, AI Toolkit, Ollama).
• Adding models via the Custom Endpoint provider (replacing the deprecated "OpenAI Compatible" option) with all three supported API types: chat-completions, responses, messages.
• Updating an existing provider's API key or endpoint URL from the Language Models editor.
• Configuring inlineChat.defaultModel, the inline suggestions model, and the two utility model settings (chat.utilityModel and chat.utilitySmallModel).
• A dedicated FAQ section covering Copilot Business/Enterprise enablement, local self-hosted models, fully-offline usage, and BYOK without a Copilot plan.

🛡️ Security-First Defaults

A dedicated Security Notes section is now part of the BYOK module. The release ships with these rules baked into both the main guide and the folder README:

• All API keys in the example file are written as ${input:chat.lm.secret.XXXX} — a VS Code Secret Input pattern that resolves through Secret Storage, never in plaintext.
• Users are explicitly instructed to redact any real secret IDs before sharing the configuration to a public repository.
• The guide recommends adding a personal chatLanguageModels.json to .gitignore if it diverges from the template.
• Copilot Business/Enterprise users are reminded that the organization administrator must enable the Bring Your Own Language Model Key in VS Code policy before BYOK is usable.

🧭 Root README.md Integration

The root README.md has been updated so the new module is discoverable from the very first scroll:

• A new 🔑 BYOK Copilot Config bullet was added to the Overview list, sitting alongside Custom Agents, Skills, Rules, and Multi-Platform.
• A new ## 🔑 BYOK Copilot Config section now points readers straight at byok-copilot-config/ for the full setup guide.
• A > [!NOTE] callout clarifies that BYOK models work without a GitHub account or Copilot plan, and only cover chat + utility tasks (semantic search, inline suggestions, and embeddings still require GitHub Copilot).

---

📝 Enhancements & Synchronization

• Heading consistency: Fixed corrupted UTF-8 emoji bytes on two root README.md headings (## 🔑 BYOK Copilot Config and ## 🛠️ Customization) so they render correctly across Markdown viewers.
• TOC ordering: The byok-config-copilot.md Table of Contents now matches the document body — Security Notes appears immediately before Model Property Reference, matching the actual section order.
• Folder Contents table: The byok-copilot-config/README.md table now lists the img/ folder explicitly, so newcomers immediately know where the screenshots live.
• Screenshots added: Seven annotated screenshot files (screen1.png, screen1a.png, screen2.png, screen2a.png, screen3.png, screen4.png, screen5.png) are now embedded directly in the documentation at the exact steps they illustrate.
• No agent or skill behavior changed: This release only adds new documentation and a configuration template — existing agents, skills, instructions, and prompts are untouched.

---

📦 Installation & Upgrade Guide

To upgrade your existing project or set up v1.2.0:

1. Pull the latest changes:

   git pull origin main

2. (Optional) Copy the new byok-copilot-config/ folder into your project if you want to use it as a local reference, or browse it directly on GitHub.

3. Open byok-copilot-config/README.md first, then follow the step-by-step guide in byok-copilot-config/byok-config-copilot.md.

4. Copy the example chatLanguageModels.json from the Real-World Configuration Example section into your VS Code chatLanguageModels.json file:

   • Windows: %APPDATA%\Code\User\chatLanguageModels.json
   • macOS: ~/Library/Application Support/Code/User/chatLanguageModels.json
   • Linux: ~/.config/Code/User/chatLanguageModels.json

5. Replace each ${input:chat.lm.secret.XXXX} placeholder with your own VS Code Secret Input ID. VS Code will prompt you for the API key the first time each provider is loaded.

6. Restart VS Code if newly added models do not appear immediately in the model picker.

No code, agent, or skill files were changed in v1.2.0, so existing setups remain fully compatible.

Full Changelog: v1.1.0...v1.2.0

v1.1.0 - Pi Dev Coding Agent Support & Recursive Memory Discovery

🚀 Awesome Copilot Indonesia v1.1.0

Release v1.1.0 introduces official support for the Pi Dev Coding Agent, significantly enhances the memory-manager skill with recursive sub-folder discovery, and synchronizes core guidelines across all platform environments.

---

🌟 Major Highlights & New Features

🤖 Native Support for Pi Dev Coding Agent (.pi)

We are excited to announce native configuration support for the Pi Dev Coding Agent. A dedicated .pi/ ecosystem directory is now available at the repository root with a complete structural setup:

• .pi/agents/: Contains all 11 SDLC Agent personas (including @GodModeDev, @ProductManagerPRD, @SpecificationArchitect, etc.).
• .pi/skills/: Houses all 14 specialized, paired agent skills.
• .pi/instructions/: Includes global coding standards and independent session memory tracking (memory.instructions.md).

🤹 Enhanced memory-manager (Recursive Sub-folder Discovery)

The memory-manager skill across all platform configurations (.agents, .commandcode, .opencode, .github, .codex, and .pi) has received a major upgrade:

• Sub-folder Scanning: Now supports recursive scanning for memory.instructions.md files nested within deep feature or module subdirectories.
• Smart Filtering: Automatically ignores heavy build and vendor directories (node_modules, .git, dist) for optimal search speed.
• Ecosystem Prioritization: Added .pi/instructions/ as a high-priority discovery root for cross-platform context recovery.

---

📝 Enhancements & Synchronization

• Core Directives Update: Updated foundational rules in AGENTS.md and .github/copilot-instructions.md (line 127) to mandate agents to read .pi/instructions/ and .commandcode/instructions/ directories upon task initialization.
• Documentation Refinements: Updated README.md with comprehensive prerequisites, installation steps, and platform-specific directory guides for the Pi Dev Coding Agent.

---

📦 Installation & Upgrade Guide

To upgrade your existing project or set up v1.1.0:

1. Pull the latest changes:

   git pull origin main

2. Choose your platform configuration:

• For Pi Dev Coding Agent: Copy the .pi/ directory to your project root.
• For other platforms (.agents, .commandcode, .opencode, .github, .codex), update the memory-manager/ skill directory in your project.

3. Ensure the updated AGENTS.md is placed at your project root.

Full Changelog: v1.0.0...v1.1.0