oh-my-copilot 4.11.4 → 4.11.6

package/.claude-plugin/marketplace.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://github.com/copilot-cli/marketplace.schema.json",
-  "name": "omg",
+  "name": "omcp",
   "description": "Copilot CLI native multi-agent orchestration - intelligent model routing, 18 agents, 32 skills",
   "owner": {
     "name": "Robin Norberg",
@@ -10,7 +10,7 @@
     {
       "name": "oh-my-copilot",
       "description": "Copilot CLI native multi-agent orchestration with intelligent model routing, 18 agent variants, and 32 powerful skills. Zero learning curve. Maximum power.",
-      "version": "4.11.4",
+      "version": "4.11.6",
       "author": {
         "name": "Robin Norberg",
         "email": "github@platypus.se"
@@ -27,5 +27,5 @@
       ]
     }
   ],
-  "version": "4.11.4"
+  "version": "4.11.6"
 }

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-copilot",
-  "version": "4.11.4",
+  "version": "4.11.6",
   "description": "Multi-agent orchestration system for Copilot CLI",
   "author": {
     "name": "Robin Norberg and oh-my-copilot contributors"

package/README.md

@@ -69,26 +69,6 @@ The deep interview uses Socratic questioning to clarify your thinking before any
 - **Persistent execution** — won't give up until the job is verified complete
 - **Azure DevOps/GitHub native** — auto-detection, work item management, PR operations, triage workflows
 - **Stop your yolo abuse** — using a layered permission model to help your agents perform safe work without your interference
----
-
-## Team Mode
-
-**Team** is the canonical orchestration surface. It runs a staged pipeline:
-
-`team-plan → team-prd → team-exec → team-verify → team-fix (loop)`
-
-```bash
-/team 3:executor "fix all TypeScript errors"
-```
-
-Spawn real tmux workers for cross-model tasks:
-
-```bash
-omc team 2:codex "review auth module for security issues"
-omc team 2:gemini "redesign UI components for accessibility"
-```
-
-[Full Team Mode docs →](docs/guides/team-mode.md)
 
 ---
 
@@ -99,11 +79,12 @@ Optional shortcuts for power users. Natural language works fine without them.
 | Keyword | Category | Effect | Example |
 | ------- | -------- | ------ | ------- |
 | `team` | ![orchestration](https://img.shields.io/badge/orchestration-blue) | Canonical Team orchestration | `team 3:executor "fix all TypeScript errors"` |
+| `ask copilot` | ![orchestration](https://img.shields.io/badge/orchestration-blue) | Delegate to Copilot CLI | `ask claude "review auth architecture"` |
 | `ask claude` | ![orchestration](https://img.shields.io/badge/orchestration-blue) | Delegate to Claude Code CLI | `ask claude "review auth architecture"` |
 | `ask codex` | ![orchestration](https://img.shields.io/badge/orchestration-blue) | Delegate to Codex CLI | `ask codex "security analysis"` |
 | `ask gemini` | ![orchestration](https://img.shields.io/badge/orchestration-blue) | Delegate to Gemini CLI | `ask gemini "suggest UX improvements"` |
-| `ccg` | ![orchestration](https://img.shields.io/badge/orchestration-blue) | Quadri-model orchestration | `ccg review this PR` |
-| `omc team` | ![orchestration](https://img.shields.io/badge/orchestration-blue) | tmux CLI workers (codex/gemini/copilot) | `omc team 2:codex "security review"` |
+| `c3g` | ![orchestration](https://img.shields.io/badge/orchestration-blue) | Quadri-model orchestration | `c3g review this PR` |
+| `omcp team` | ![orchestration](https://img.shields.io/badge/orchestration-blue) | tmux CLI workers (codex/gemini/copilot) | `omcp team 2:codex "security review"` |
 | `code review` | ![analysis](https://img.shields.io/badge/analysis-purple) | Code review mode | `code review the auth module` |
 | `deep-analyze` | ![analysis](https://img.shields.io/badge/analysis-purple) | Deep analysis mode | `deep-analyze why tests are failing` |
 | `deep-dive` | ![analysis](https://img.shields.io/badge/analysis-purple) | Trace → interview pipeline | `deep-dive why auth is slow` |
@@ -138,6 +119,39 @@ Optional shortcuts for power users. Natural language works fine without them.
 
 ---
 
+## Orchestration between agents
+
+### Team Mode
+
+**Team** is the canonical orchestration surface. It runs a staged pipeline:
+
+`team-plan → team-prd → team-exec → team-verify → team-fix (loop)`
+
+```bash
+/team 3:executor "fix all TypeScript errors"
+```
+
+### C3G
+**C3g** uses multi-model advisor synthesis — fans out via `ask-claude` + `ask-codex` + `ask-gemini`, then Copilot synthesizes the results:
+
+```bash
+/c3g "review this branch — architecture, security, and UI components"
+```
+
+### OMC Team Mode
+**Omc team** spawn real tmux CLI workers for cross-model tasks:
+
+```bash
+omcp team 1:copilot "review the ingestion module for performance issues"
+omcp team 2:claude "review the database module for sql issues"
+omcp team 3:codex "review the auth module for security issues"
+omcp team 5:gemini "redesign UI components for accessibility"
+```
+
+[Full Team Mode docs →](docs/guides/team-mode.md)
+
+---
+
 ## Documentation
 
 - [Documentation Home](docs/index.md)
@@ -161,7 +175,7 @@ Optional shortcuts for power users. Natural language works fine without them.
 
 ### Platform & tmux
 
-OMC features like `omc team` and rate-limit detection require **tmux**:
+OMC features like `omcp team` and rate-limit detection require **tmux**:
 
 | Platform       | tmux provider                                          | Install                 |
 | -------------- | ------------------------------------------------------ | ----------------------- |
@@ -186,10 +200,10 @@ OMC can orchestrate multiple AI CLI providers as tmux workers for cross-validati
 | [Codex CLI](https://github.com/openai/codex)                  | `npm install -g @openai/codex`         | Architecture validation, code review cross-check |
 
 ```bash
-omc team 2:claude "review auth architecture"
-omc team 2:codex "security analysis"
-omc team 2:gemini "UI consistency check"
-omc team 1:copilot "review existing tests"
+omcp team 2:claude "review auth architecture"
+omcp team 2:codex "security analysis"
+omcp team 2:gemini "UI consistency check"
+omcp team 1:copilot "review existing tests"
 ```
 Only Copilot CLI is required — the others are optional and add cross-provider validation.
 

package/agents/analyst.agent.md

@@ -98,7 +98,7 @@ disallowedTools: Write, Edit
     ```
 
     Do NOT attempt to write these to a file (Write and Edit tools are blocked for this agent).
-    The orchestrator or planner will persist open questions to `.omg/plans/open-questions.md` on your behalf.
+    The orchestrator or planner will persist open questions to `.omcp/plans/open-questions.md` on your behalf.
   </Open_Questions>
 
   <Final_Checklist>
@@ -123,7 +123,7 @@ When analyzing requirements in Azure DevOps projects:
 - `mcp__azure-devops__search_workitem` — Search work items by keyword
 
 ### Requirements Workflow
-1. Read `.omg/config.json` for ADO org/project settings
+1. Read `.omcp/config.json` for ADO org/project settings
 2. Query work items to understand existing requirements
 3. Check linked PRs and commits for implementation context
 4. Review work item comments for stakeholder discussions

package/agents/architect.agent.md

@@ -131,7 +131,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **Work Items:** `wit_get_work_item`, `wit_list_backlog_work_items`, `wit_get_work_items_for_iteration`
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/code-reviewer.agent.md

@@ -257,7 +257,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **PR Management:** `repo_get_pull_request_by_id`, `repo_update_pull_request`, `repo_update_pull_request_reviewers`
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/designer.agent.md

@@ -112,7 +112,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **Work Items:** `wit_get_work_item` (for reading design-related work items)
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/executor.agent.md

@@ -34,8 +34,8 @@ model: claude-sonnet-4-6
     - Do not introduce new abstractions for single-use logic.
     - Do not refactor adjacent code unless explicitly requested.
     - If tests fail, fix the root cause in production code, not test-specific hacks.
-    - Plan files (.omg/plans/*.md) are READ-ONLY. Never modify them.
-    - Append learnings to notepad files (.omg/notepads/{plan-name}/) after completing work.
+    - Plan files (.omcp/plans/*.md) are READ-ONLY. Never modify them.
+    - Append learnings to notepad files (.omcp/notepads/{plan-name}/) after completing work.
     - After 3 failed attempts on the same issue, escalate to architect agent with full context.
   </Constraints>
 
@@ -128,7 +128,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **Repos:** `repo_create_pull_request`, `repo_update_pull_request`
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/explore.agent.md

@@ -128,6 +128,6 @@ When exploring Azure DevOps codebases:
 
 ### Exploration Strategy for ADO
 1. Detect ADO via git remote URL
-2. Read `.omg/config.json` for project context
+2. Read `.omcp/config.json` for project context
 3. Use `search_code` MCP tool for cross-repo pattern discovery
 4. Check wiki for architecture docs and team conventions

package/agents/git-master.agent.md

@@ -31,7 +31,7 @@ model: claude-sonnet-4-6
     - Never rebase main/master.
     - Use --force-with-lease, never --force.
     - Stash dirty files before rebasing.
-    - Plan files (.omg/plans/*.md) are READ-ONLY.
+    - Plan files (.omcp/plans/*.md) are READ-ONLY.
   </Constraints>
 
   <Investigation_Protocol>
@@ -180,7 +180,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **PR Threads:** `repo_create_pull_request_thread`, `repo_list_pull_request_threads`, `repo_list_pull_request_thread_comments`, `repo_reply_to_comment`
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/planner.agent.md

@@ -7,7 +7,7 @@ model: claude-opus-4-6
 <Agent_Prompt>
   <Role>
     You are Planner. Your mission is to create clear, actionable work plans through structured consultation.
-    You are responsible for interviewing users, gathering requirements, researching the codebase via agents, and producing work plans saved to `.omg/plans/*.md`.
+    You are responsible for interviewing users, gathering requirements, researching the codebase via agents, and producing work plans saved to `.omcp/plans/*.md`.
     You are not responsible for implementing code (executor), analyzing requirements gaps (analyst), reviewing plans (critic), or analyzing code (architect).
 
     When a user says "do X" or "build X", interpret it as "create a work plan for X." You never implement. You plan.
@@ -21,13 +21,13 @@ model: claude-opus-4-6
     - Plan has 3-6 actionable steps (not too granular, not too vague)
     - Each step has clear acceptance criteria an executor can verify
     - User was only asked about preferences/priorities (not codebase facts)
-    - Plan is saved to `.omg/plans/{name}.md`
+    - Plan is saved to `.omcp/plans/{name}.md`
     - User explicitly confirmed the plan before any handoff
     - In consensus mode, RALPLAN-DR structure is complete and ready for Architect/Critic review
   </Success_Criteria>
 
   <Constraints>
-    - Never write code files (.ts, .js, .py, .go, etc.). Only output plans to `.omg/plans/*.md` and drafts to `.omg/drafts/*.md`.
+    - Never write code files (.ts, .js, .py, .go, etc.). Only output plans to `.omcp/plans/*.md` and drafts to `.omcp/drafts/*.md`.
     - Never generate a plan until the user explicitly requests it ("make it into a work plan", "generate the plan").
     - Never start implementation. Always hand off to `/oh-my-copilot:start-work`.
     - Ask ONE question at a time using AskUserQuestion tool. Never batch multiple questions.
@@ -64,7 +64,7 @@ model: claude-opus-4-6
     - Use AskUserQuestion for all preference/priority questions (provides clickable options).
     - Spawn explore agent (model=haiku) for codebase context questions.
     - Spawn document-specialist agent for external documentation needs.
-    - Use Write to save plans to `.omg/plans/{name}.md`.
+    - Use Write to save plans to `.omcp/plans/{name}.md`.
   </Tool_Usage>
 
   <Execution_Policy>
@@ -76,7 +76,7 @@ model: claude-opus-4-6
   <Output_Format>
     ## Plan Summary
 
-    **Plan saved to:** `.omg/plans/{name}.md`
+    **Plan saved to:** `.omcp/plans/{name}.md`
 
     **Scope:**
     - [X tasks] across [Y files]
@@ -111,7 +111,7 @@ model: claude-opus-4-6
   </Examples>
 
   <Open_Questions>
-    When your plan has unresolved questions, decisions deferred to the user, or items needing clarification before or during execution, write them to `.omg/plans/open-questions.md`.
+    When your plan has unresolved questions, decisions deferred to the user, or items needing clarification before or during execution, write them to `.omcp/plans/open-questions.md`.
 
     Also persist any open questions from the analyst's output. When the analyst includes a `### Open Questions` section in its response, extract those items and append them to the same file.
 
@@ -129,8 +129,8 @@ model: claude-opus-4-6
     - Does the plan have 3-6 actionable steps with acceptance criteria?
     - Did the user explicitly request plan generation?
     - Did I wait for user confirmation before handoff?
-    - Is the plan saved to `.omg/plans/`?
-    - Are open questions written to `.omg/plans/open-questions.md`?
+    - Is the plan saved to `.omcp/plans/`?
+    - Are open questions written to `.omcp/plans/open-questions.md`?
     - In consensus mode, did I provide principles/drivers/options summary for step-2 alignment?
     - In consensus mode, does the final plan include ADR fields?
     - In deliberate consensus mode, are pre-mortem + expanded test plan present?
@@ -149,7 +149,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **Search:** `search_code`, `search_workitem`, `search_wiki`
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/qa-tester.agent.md

@@ -109,7 +109,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **Pipelines:** `pipelines_get_builds`, `pipelines_get_build_status`, `pipelines_get_build_log`
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/scientist.agent.md

@@ -21,7 +21,7 @@ disallowedTools: Write, Edit
     - Analysis follows hypothesis-driven structure: Objective -> Data -> Findings -> Limitations
     - All Python code executed via python_repl (never Bash heredocs)
     - Output uses structured markers: [OBJECTIVE], [DATA], [FINDING], [STAT:*], [LIMITATION]
-    - Report saved to `.omg/scientist/reports/` with visualizations in `.omg/scientist/figures/`
+    - Report saved to `.omcp/scientist/reports/` with visualizations in `.omcp/scientist/figures/`
   </Success_Criteria>
 
   <Constraints>
@@ -34,7 +34,7 @@ disallowedTools: Write, Edit
   </Constraints>
 
   <Investigation_Protocol>
-    1) SETUP: Verify Python/packages, create working directory (.omg/scientist/), identify data files, state [OBJECTIVE].
+    1) SETUP: Verify Python/packages, create working directory (.omcp/scientist/), identify data files, state [OBJECTIVE].
     2) EXPLORE: Load data, inspect shape/types/missing values, output [DATA] characteristics. Use .head(), .describe().
     3) ANALYZE: Execute statistical analysis. For each insight, output [FINDING] with supporting [STAT:*] (ci, effect_size, p_value, n). Hypothesis-driven: state the hypothesis, test it, report result.
     4) SYNTHESIZE: Summarize findings, output [LIMITATION] for caveats, generate report, clean up.
@@ -68,7 +68,7 @@ disallowedTools: Write, Edit
 
     [LIMITATION] Missing values (15%) may introduce bias. Correlation does not imply causation.
 
-    Report saved to: .omg/scientist/reports/{timestamp}_report.md
+    Report saved to: .omcp/scientist/reports/{timestamp}_report.md
   </Output_Format>
 
   <Failure_Modes_To_Avoid>
@@ -104,7 +104,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **Work Items:** `wit_get_work_items_for_iteration`, `wit_list_backlog_work_items`
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/security-reviewer.agent.md

@@ -193,7 +193,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **Search:** `search_code` (for finding vulnerable patterns across repos)
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/test-engineer.agent.md

@@ -134,7 +134,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **Results:** `testplan_show_test_results_from_build_id`
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",

package/agents/writer.agent.md

@@ -98,7 +98,7 @@ Use `mcp__azure-devops__*` tools when available instead of CLI commands:
 - **Search:** `search_wiki`
 
 ### Configuration
-Read `.omg/config.json` for ADO settings before making assumptions:
+Read `.omcp/config.json` for ADO settings before making assumptions:
 ```json
 {
   "platform": "azure-devops",