- Make browser tester generic to support for chrome devotols mcp, playwright, agentic browser tools.
- Add Team lead and energetci peronsality to Orchestrator
- Add progress updates between phases/ waves
* feat: Prd/ steer support
- Add supprot for PRD
- Vscode steer/ queue support
- Consistent artifacts
- Improved parallel running; for researchers too
* chore: improve prd update support
* chore: Make reviewer use prd for compaince
* chore: imrpvoe websearch in researcher
* fix(gem-team): revert gem-team plugin version from 1.5.0 to 1.2.0
Updated agent guidelines to specify the use of accessibility_snapshot over visual screenshots for element identification. Accessibility snapshots provide structured DOM/ARIA data, which is more reliable for browser automation than pixel-based visual analysis.
Remove redundant `<operating_rules>`, agent-specific parameters, and
`<delegation_validation>` sections. This removes duplicate content
to ensure a single source of truth for the agent's behavior protocols
and configuration.
- Refined `gem-browser-tester` workflow to separate initialization from
execution and enforce an Observation-First loop.
- Added retry logic for transient failures (e.g., timeouts, network issues)
in browser automation tasks.
- Standardized artifact generation paths to `docs/plan/{plan_id}/`
across multiple agents.
- Updated failure actions to specify evidence capture locations
(logs, network) for improved debugging and traceability.
Introduce explicit sections for input, output, and verification criteria.
Define structured JSON output including detailed evidence paths and error counts.
Update workflow to reference new guides and move Observation-First loop to operating rules.
Clarify verification steps with specific pass/fail conditions for console, network, and accessibility checks.
- Remove redundant `<mission>` section from gem-browser-tester
- Add "Reflect" step to gem-documentation-writer for self-review on high-priority or failed tasks
- Refactor gem-orchestrator completion phase to generate a walkthrough markdown file instead of a review
- Update orchestrator rules to allow direct execution for creating walkthrough files
- Bump plugin version to 1.1.0 in marketplace and plugin.json
- Rename agent from "Chrome Tester" to "Browser Tester" in plugin.json
- Update agent description to focus on browser automation tools instead of Chrome DevTools
- Add symlink for the Browser Tester agent in the plugin's agents directory
Remove "detailed thinking on" directive and consolidate operating_rules sections for consistency. Both gem-browser-tester.agent.md and gem-devops.agent.md now share standardized rules: unified tool activation phrasing ("Always activate tools before use"), merged context-efficient reading instructions, and removed agent-specific variations. This simplifies maintenance and ensures consistent behavior across different agent types while preserving core functionality like evidence storage, error handling, and output constraints.
Rename the Chrome-specific testing agent to a browser-agnostic version
to support multiple automation tools (Playwright, Chrome DevTools, etc.).
Updates all references in orchestrator and planner configurations, and
broadens the description and execution workflow to be tool-flexible.
Evidence storage rule clarified to apply primarily on failures.
- Introduced new agents: gem-chrome-tester, gem-devops, gem-documentation-writer, gem-implementer, gem-orchestrator, gem-planner, gem-researcher, and gem-reviewer.
- Updated README.collections.md to include the new Gem Team Multi-Agent Orchestration collection.
- Created gem-team.collection.yml and gem-team.md for structured documentation of the multi-agent orchestration framework.
- Each agent includes detailed descriptions, workflows, operating rules, and final anchors for clarity on their functionalities and usage.
* UPDATE: Upgrade Blueprint Mode to v39 with improved directives and model specification
* CREATE: Add Blueprint Mode Codex v1 with core directives and guiding principles
* Update blueprint-mode-codex.chatmode.md
* Modify model name and enhance description
Updated model name to include 'copilot' and refined description for clarity.
* Update Blueprint Mode documentation to reflect version 36 changes and enhance clarity on workflows and directives.
* Update chatmodes/blueprint-mode.chatmode.md
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Refine directives in Blueprint Mode documentation for clarity and accuracy
* Update Blueprint Mode documentation to version 37, enhancing clarity and detail in core directives and tool usage policies.
* Update Blueprint Mode documentation to version 37, enhancing clarity on workflows and directives.
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* feat: Revise Blueprint Mode documentation for clarity and conciseness
* feat: Update Blueprint Mode to v30 with enhanced workflows and self-correction features
* fix: Correct terminology from 'todos' to 'tasks' and improve capitalization for consistency
* feat: Upgrade model to GPT-5 Mini and enhance communication guidelines for brevity and clarity
* feat: Update model version to GPT-4.1 and clarify critical execution guidelines
* feat: Enhance Blueprint Mode with improved task handling and workflow directives
* feat: Revise Blueprint Mode directives for clarity and brevity, introducing confidence-based ambiguity resolution
* feat: Update Blueprint Mode to v16 with enhanced directives and workflows
- Changed model from Claude Sonnet 4 to GPT-4.1.
- Revised description for clarity and conciseness.
- Expanded communication guidelines for improved task management.
- Enhanced quality and engineering protocols, emphasizing SOLID principles and documentation.
- Introduced new execution principles to streamline task execution and reflection.
- Updated artifact structure to include specifications for requirements, architecture, and edge cases.
- Refined workflows for better task handling and validation processes.
- Improved debugging strategies and handling of ambiguous requests.
* refactor: streamline communication guidelines and core directives in Blueprint Mode documentation
* feat(docs): add Blueprint Mode v1 chat mode and documentation
Add Blueprint Mode v1 chat mode instructions and entry to README.
Blueprint Mode introduces specification-first engineering workflow,
artifact management standards, and escalation protocols for autonomous
agent development.
* docs(chatmode): improve formatting and clarify execution policy
- update tools list for accuracy and consistency
- enhance formatting in design and steering documents for readability
- clarify execution policy and internet research instructions
- fix minor markdown and wording issues
* docs(chatmode): add critical execution rules and update tools list
Add mandatory execution instructions and include runTests in tools for blueprint-mode chat mode.
* feat(chatmode): update Blueprint Mode to v2 with enhanced self-sufficient engineering directives and improved documentation
* fix(chatmode): correct formatting of tools list in Blueprint Mode documentation
* feat(blueprint-mode): update Blueprint Mode to v3 with enhanced directives and improved clarity
* fix(blueprint-mode): correct numbering format in main and lightweight workflows
* feat(blueprint-mode): enhance Core Directives with continuation and task review mandates
* feat(blueprint-mode): update Blueprint Mode to v4 with enhanced directives and improved clarity
* feat(docs): update Blueprint Mode documentation to v5 with enhanced directives and workflows
* fix(docs): refine thinking process directive for clarity and completeness
* feat(docs): update Blueprint Mode documentation from v5 to v6 with revised file paths and workflow steps
* feat(docs): update Blueprint Mode documentation to v6 with enhanced agent instructions
* feat(docs): enhance Blueprint Mode directives with self-reflection and retry strategies
* feat(docs): update Blueprint Mode documentation to v7 with enhanced task management and artifact tracking
* feat(docs): update Blueprint Mode documentation to v8 with enhanced specifications and directives
* feat(docs): update Blueprint Mode documentation to v9 with enhanced directives for task workflows and artifact management
* feat(docs): update artifact paths in Blueprint Mode documentation to reflect new directory structure
* feat(docs): update Blueprint Mode documentation from v9 to v10 with enhanced directives and workflow details
* feat(docs): update Blueprint Mode documentation from v10 to v11 with enhanced directives and tool usage guidelines
* feat(docs): update Blueprint Mode documentation to v12 with enhanced directives and workflow details
* feat(docs): add Blueprint Mode v1 chat mode and documentation
Add Blueprint Mode v1 chat mode instructions and entry to README.
Blueprint Mode introduces specification-first engineering workflow,
artifact management standards, and escalation protocols for autonomous
agent development.
* docs(chatmode): improve formatting and clarify execution policy
- update tools list for accuracy and consistency
- enhance formatting in design and steering documents for readability
- clarify execution policy and internet research instructions
- fix minor markdown and wording issues
* docs(chatmode): add critical execution rules and update tools list
Add mandatory execution instructions and include runTests in tools for blueprint-mode chat mode.
* feat(chatmode): update Blueprint Mode to v2 with enhanced self-sufficient engineering directives and improved documentation
* fix(chatmode): correct formatting of tools list in Blueprint Mode documentation
* feat(blueprint-mode): update Blueprint Mode to v3 with enhanced directives and improved clarity
* fix(blueprint-mode): correct numbering format in main and lightweight workflows
* feat(blueprint-mode): enhance Core Directives with continuation and task review mandates
* feat(blueprint-mode): update Blueprint Mode to v4 with enhanced directives and improved clarity
Muhammad Ubaid Raza
