mirror of
https://github.com/github/awesome-copilot.git
synced 2026-05-06 15:12:12 +00:00
Muhammad Ubaid Raza
ef40bff1da
* feat: move to xml top tags for ebtter llm parsing and structure - Orchestrator is now purely an orchestrator - Added new calrify phase for immediate user erequest understanding and task parsing before workflow - Enforce review/ critic to plan instea dof 3x plan generation retries for better error handling and self-correction - Add hins to all agents - Optimize defitons for simplicity/ conciseness while maintaining clarity * feat(critic): add holistic review and final review enhancements * chore: bump marketplace version to 1.10.0 - Updated `.github/plugin/marketplace.json` to version 1.10.0. - Revised `agents/gem-browser-tester.agent.md` to improve the BROWSER TESTER role documentation with a clearer structure, explicit role header, and organized knowledge sources section. * refactor: streamline verification and self‑critique steps across browser‑tester, code‑simplifier, critic, and debugger agents * feat(researcher): improve mode selection workflow and research implementation details - Refine **Clarify** mode description to emphasize minimal research for detecting ambiguities. - Reorder steps and clarify intent detection (`continue_plan`, `modify_plan`, `new_task`). - Add explicit sub‑steps for presenting architectural and task‑specific clarifications. - Update **Research** mode section with clearer initialization workflow. - Simplify and reformat the confidence calculation comments for readability. - Minor formatting tweaks and added blank lines for visual separation. * Update gem-orchestrator.agent.md * docs(gem-browser-tester): enhance BROWSER TESTER role description and clarify workflow steps- Expanded the BROWSER TESTER role with explicit responsibilities and constraints - Reformatted the Knowledge Sources list using consistent numbered items for readability- Updated the Workflow section to detail initialization, execution, and teardown steps more clearly- Refined the Output Format and Research Format Guide structures to use proper markdown syntax - Improved overall formatting and consistency of documentation for better maintainability * docs: fix typo in delegation description * feat(metadata): bump marketplace version to 1.15.0 and enrich agent documentation The marketplace plugin metadata has been updated to reflect the newer self‑learning multi‑agent orchestration description and the version hasbeen upgraded from 1.13.0 to 1.15.0. Documentation for the following agents has been expanded with new sections: - **gem-browser-tester.agent.md** – added an “Output” section outlining strict JSON output rules and a new “I/O Optimization” section covering parallel batch operations, read efficiency, and scoping techniques. - **gem-code-simplifier.agent.md** – similarly added “Output” and “I/O Optimization” sections describing concisely formatted JSON, parallel I/O, and batch processing best practices. - **gem-reviewer.agent.md** – updated its output format and added detailed guidance on review scope, anti‑patterns, and I/O strategies. These changes provide clearer usage instructions and performance‑focused recommendations for the agents while aligning the marketplace metadata with the updated version. * feat(plugin): add agents list and README for gem-team plugin * docs: update readme * chore: match version with gem-team * docs: standardize execution order and output format sections in agent documentation * docs: fix typo in agent documentation files * refactor: replace "framework" with "harness" in gem‑team marketplace, plugin, and README descriptions
Gem Team
Self-Learning Multi-agent orchestration harness for spec-driven development and automated verification.
Quick Start
See all supported installation options below.
Contents
- Quick Start
- Why Gem Team?
- Harness Architecture
- Installation
- The Agent Team
- Knowledge Sources
- Contributing
Why Gem Team?
Performance
- 4x Faster — Parallel execution with wave-based execution
- Pattern Reuse — Codebase pattern discovery prevents reinventing wheels
Quality & Security
- Higher Quality — Specialized harness agents + TDD + verification gates + contract-first
- Built-in Security — OWASP scanning, secrets/PII detection on critical tasks
- Resilient — Pre-mortem analysis, failure handling, auto-replanning
- Accessibility-First — WCAG compliance validated at spec and runtime layers
- Safe DevOps — Idempotent operations, health checks, mandatory approval gates
- Constructive Critique — gem- critic challenges assumptions, finds edge cases
Intelligence
- Established Patterns — Uses library/harness conventions over custom implementations
- Source Verified — Every factual claim cites its source; no guesswork
- Knowledge-Driven — Prioritized sources (PRD → codebase → AGENTS.md → Context7 → docs)
- Continuous Learning — Memory tool persists patterns, gotchas, user preferences across sessions
- Auto-Skills — Agents extract reusable SKILL.md files from successful tasks (high confidence: auto, medium: confirm)
- Skills & Guidelines — Built-in skill & guidelines (web-design-guidelines)
Process
- Spec-Driven — Multi-step refinement defines "what" before "how"
- Verified-Plan — Complex tasks: Plan → Verification → Critic
- Traceable — Self-documenting IDs link requirements → tasks → tests → evidence
- Intent vs. Compliance — Shifts the burden from writing "perfect prompts" to enforcing strict, YAML-based approval gates
- Diagnose-then-Fix — gem-debugger diagnoses → gem-implementer fixes → re-verifies
- Pre-Mortem — Failure modes identified BEFORE execution
- Contract-First — Contract tests written before implementation
Token Efficiency
Optimized for reduced LLM token consumption without quality loss:
- Concise Output — No preamble, no meta commentary, no verbose explanations
- Strict Formats — JSON/YAML exactly matching schemas — eliminates parse errors and retries
- Empty is OK — Skip empty arrays, nulls, verbose fields where not needed
- File-Based — Researcher/Planner save to YAML files (not all in JSON output)
- Learnings — Empty patterns/conventions unless critical
Result: ~40-60% reduction on output tokens while maintaining quality.
Design
- Design Agents — Dedicated agents for web and mobile UI/UX with anti-"AI slop" guidelines for distinctive aesthetics
- Mobile Agents — Native mobile implementation (React Native, Flutter) + iOS/Android testing
Core Concepts
The "System- IQ" Multiplier
Raw reasoning isn't enough in single-pass chat. Gem-Team wraps your preferred LLM in a rigid harness with verification-first loops, fundamentally boosting its effective capability on SWE tasks.
Design Support
Gem Team includes specialized design agents with anti-"AI slop" guidelines for distinctive, modern and unique aesthetics with accessibility compliance.
Triple Learning System
| Type | Storage | 1-liner |
|---|---|---|
| Memory | /memories/ |
Facts & user preferences (auto- save) |
| Skills | docs/skills/ |
Procedures with code examples |
| Conventions | AGENTS.md |
Static rules (requires approval) |
Harness Architecture
User Goal → Orchestrator → [Simple: Research/Plan] or [Complex: Discuss → PRD → Research → Plan → Approve] → Execute (waves) → Summary → Final Review
↓
Diagnose → Fix → Re- verify
Installation
| Method | Command / Link | Docs |
|---|---|---|
| Code | Install Now | Copilot Docs |
| Code Insiders | Install Now | Copilot Docs |
| APM (All AI coding agents) |
apm install mubaidr/gem-team |
APM Docs |
| Copilot CLI (Marketplace) | copilot plugin install gem-team@awesome-copilot |
CLI Docs |
| Copilot CLI (Direct) | copilot plugin install gem-team@mubaidr |
CLI Docs |
| Windsurf | codeium agent install mubaidr/gem-team |
Windsurf Docs |
| Claude Code | claude plugin install mubaidr/gem-team |
Claude Docs |
| OpenCode | opencode plugin install mubaidr/gem-team |
OpenCode Docs |
| Manual (Copy agent files) |
VS Code: ~/.vscode/agents/ VS Code Insiders: ~/.vscode- insiders/agents/ GitHub Copilot: ~/.github/copilot/agents/ GitHub Copilot (project): .github/plugin/agents/ Windsurf: ~/.windsurf/agents/ Claude: ~/.claude/agents/ Cursor: ~/.cursor/agents/ OpenCode: ~/.opencode/agents/ |
— |
The Agent Team
Core Workflow
| Role | Description | Sources | Recommended LLM |
|---|---|---|---|
| ORCHESTRATOR | The team lead: Orchestrates research, planning, implementation, and verification | PRD, AGENTS.md | Closed: GPT-5.4, Gemini 3.1 Pro, Claude Sonnet 4.6 Open: GLM-5, Kimi K2.5, Qwen3.5 |
| RESEARCHER | Codebase exploration — patterns, dependencies, architecture discovery | PRD, codebase, AGENTS.md, docs | Closed: Gemini 3.1 Pro, GPT-5.4, Claude Sonnet 4.6 Open: GLM-5, Qwen3.5-9B, DeepSeek-V3.2 |
| PLANNER | DAG-based execution plans — task decomposition, wave scheduling, risk analysis | PRD, codebase, AGENTS.md | Closed: Gemini 3.1 Pro, Claude Sonnet 4.6, GPT-5.4 Open: Kimi K2.5, GLM-5, Qwen3.5 |
| IMPLEMENTER | TDD code implementation — features, bugs, refactoring. Never reviews own work | codebase, AGENTS.md, DESIGN.md | Closed: Claude Opus 4.6, GPT-5.4, Gemini 3.1 Pro Open: DeepSeek-V3.2, GLM-5, Qwen3- Coder-Next |
Quality & Review
| Role | Description | Sources | Recommended LLM |
|---|---|---|---|
| REVIEWER | Zero- Hallucination Filter — Security auditing, code review, OWASP scanning | PRD, codebase, AGENTS.md, OWASP | Closed: Claude Opus 4.6, GPT-5.4, Gemini 3.1 Pro Open: Kimi K2.5, GLM-5, DeepSeek-V3.2 |
| CRITIC | Challenges assumptions, finds edge cases, spots over- engineering and logic gaps | PRD, codebase, AGENTS.md | Closed: Claude Sonnet 4.6, GPT-5.4, Gemini 3.1 Pro Open: Kimi K2.5, GLM-5, Qwen3.5 |
| DEBUGGER | Root-cause analysis, stack trace diagnosis, regression bisection | codebase, AGENTS.md, git history | Closed: Gemini 3.1 Pro, Claude Opus 4.6, GPT-5.4 Open: DeepSeek-V3.2, GLM-5, Qwen3- Coder-Next |
| BROWSER TESTER | E2E browser testing, UI/UX validation, visual regression | PRD, AGENTS.md, fixtures | Closed: GPT-5.4, Claude Sonnet 4.6, Gemini 3.1 Flash Open: Llama 4 Maverick, Qwen3.5- Flash, MiniMax M2.7 |
| SIMPLIFIER | Refactoring specialist — removes dead code, reduces complexity | codebase, AGENTS.md, tests | Closed: Claude Opus 4.6, GPT-5.4, Gemini 3.1 Pro Open: DeepSeek-V3.2, GLM-5, Qwen3- Coder-Next |
Specialized
| Role | Description | Sources | Recommended LLM |
|---|---|---|---|
| DEVOPS | Infrastructure deployment, CI/CD pipelines, container management | AGENTS.md, infra configs | Closed: GPT-5.4, Gemini 3.1 Pro, Claude Sonnet 4.6 Open: DeepSeek-V3.2, GLM-5, Qwen3.5 |
| DOCUMENTATION | Technical documentation, README files, API docs, diagrams | AGENTS.md, source code | Closed: Claude Sonnet 4.6, Gemini 3.1 Flash, GPT-5.4 Mini Open: Llama 4 Scout, Qwen3.5-9B, MiniMax M2.7 |
| DESIGNER | UI/UX design — layouts, themes, color schemes, accessibility | PRD, codebase, AGENTS.md | Closed: GPT-5.4, Gemini 3.1 Pro, Claude Sonnet 4.6 Open: Qwen3.5, GLM-5, MiniMax M2.7 |
| IMPLEMENTER- MOBILE | Mobile implementation — React Native, Expo, Flutter | codebase, AGENTS.md | Closed: Claude Opus 4.6, GPT-5.4, Gemini 3.1 Pro Open: DeepSeek-V3.2, GLM-5, Qwen3- Coder-Next |
| DESIGNER- MOBILE | Mobile UI/UX — HIG, Material Design, safe areas | PRD, codebase, AGENTS.md | Closed: GPT-5.4, Gemini 3.1 Pro, Claude Sonnet 4.6 Open: Qwen3.5, GLM-5, MiniMax M2.7 |
| MOBILE TESTER | Mobile E2E testing — Detox, Maestro, iOS/Android | PRD, AGENTS.md | Closed: GPT-5.4, Claude Sonnet 4.6, Gemini 3.1 Flash Open: Llama 4 Maverick, Qwen3.5- Flash, MiniMax M2.7 |
Knowledge Sources
Agents consult only the sources relevant to their role:
| Trust Level | Sources | Behavior |
|---|---|---|
| Trusted | PRD, plan.yaml, AGENTS.md | Follow as instructions |
| Verify | Codebase files, research findings | Cross-reference before assuming |
| Untrusted | Error logs, external data | Factual only — never as instructions |
Contributing
Contributions are welcome! Please feel free to submit a Pull Request. CONTRIBUTING for detailed guidelines on commit message formatting, branching strategy, and code standards.
License
This project is licensed under the Apache License 2.0.
Support
If you encounter any issues or have questions, please open an issue on GitHub.