claudecode-omc 5.9.1 → 5.12.0

package/bundled/upstream/oh-my-claudecode/skills/ask/SKILL.md

@@ -1,16 +1,16 @@
 ---
 name: ask
-description: Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
+description: Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly
 ---
 
 # Ask
 
-Use OMC's canonical advisor skill to route a prompt through the local Claude, Codex, or Gemini CLI and persist the result as an ask artifact.
+Use OMC's canonical advisor skill to route a prompt through the local Claude, Codex, Gemini, Antigravity, Grok, or Cursor CLI and persist the result as an ask artifact.
 
 ## Usage
 
 ```bash
-/oh-my-claudecode:ask <claude|codex|gemini> <question or task>
+/oh-my-claudecode:ask <claude|codex|gemini|antigravity|grok|cursor> <question or task>
 ```
 
 Examples:
@@ -18,7 +18,9 @@ Examples:
 ```bash
 /oh-my-claudecode:ask codex "review this patch from a security perspective"
 /oh-my-claudecode:ask gemini "suggest UX improvements for this flow"
+/oh-my-claudecode:ask antigravity "suggest UX improvements for this flow"
 /oh-my-claudecode:ask claude "draft an implementation plan for issue #123"
+/oh-my-claudecode:ask cursor "apply this implementation plan"
 ```
 
 ## Routing
@@ -29,7 +31,7 @@ Examples:
 omc ask {{ARGUMENTS}}
 ```
 
-**Do NOT manually construct raw provider CLI commands.** Never run `codex`, `claude`, or `gemini` directly to fulfill this skill. The `omc ask` wrapper handles correct flag selection, artifact persistence, and provider-version compatibility automatically. Manually assembling provider CLI flags will produce incorrect or outdated invocations.
+**Do NOT manually construct raw provider CLI commands.** Never run `codex`, `claude`, `gemini`, `agy`, `grok`, or `cursor-agent` directly to fulfill this skill. The `omc ask` wrapper handles correct flag selection, artifact persistence, and provider-version compatibility automatically. Manually assembling provider CLI flags will produce incorrect or outdated invocations.
 
 ## Requirements
 
@@ -40,8 +42,17 @@ omc ask {{ARGUMENTS}}
 claude --version
 codex --version
 gemini --version
+agy --version
+grok --version
+cursor-agent --version
 ```
 
+- **Antigravity CLI install** (Google's successor to the Gemini CLI): install the `agy`
+  binary per the [official Antigravity instructions](https://antigravity.google) (inspect
+  any installer before running it). Verify: `agy --version`
+  > **Platform note:** `omc ask antigravity` is supported on macOS/Linux. On Windows it is guarded with a clear error, because `agy --print` takes the prompt as an argv value (it cannot read stdin) and has known upstream Windows `-p` limitations; use `omc ask gemini` on Windows.
+- **Gemini CLI** remains supported for enterprise/API-key use cases.
+
 ## Artifacts
 
 `omc ask` writes artifacts to:

package/bundled/upstream/oh-my-claudecode/skills/autopilot/SKILL.md

@@ -140,11 +140,40 @@ Optional settings in `.claude/omc.jsonc` (project) or `~/.config/claude-omc/conf
     "pauseAfterExpansion": false,
     "pauseAfterPlanning": false,
     "skipQa": false,
-    "skipValidation": false
+    "skipValidation": false,
+    "execution": "solo"
   }
 }
 ```
 
+To run autopilot implementation through the tmux CLI team runtime and prefer Cursor executor workers:
+
+```jsonc
+{
+  "autopilot": {
+    "execution": "team",
+    "team": { "agentTypes": ["cursor"] }
+  }
+}
+```
+
+With that config, the execution stage must launch executor-style work through:
+
+```sh
+omc team 1:cursor "<implementation task>"
+```
+
+or the Claude Code slash compatibility surface:
+
+```text
+/omc-teams 1:cursor "<implementation task>"
+```
+
+Limitations:
+- Cursor workers are executor-style only: implementation, file edits, build/test fixes, and other plan execution tasks.
+- Keep reviewer, critic, security-review, validation verdict, and final approval roles on native Claude/OMC reviewer agents unless explicit safe support is added later.
+- Cursor requires the `cursor-agent` CLI to be installed and authenticated. If `cursor-agent` is unavailable, report that setup requirement instead of silently falling back to Claude-only execution.
+
 ## Resume
 
 If autopilot was cancelled or failed, run `/oh-my-claudecode:autopilot` again to resume from where it stopped.

package/bundled/upstream/oh-my-claudecode/skills/cancel/SKILL.md

@@ -26,7 +26,7 @@ Automatically detects which mode is active and cancels it:
 - **Swarm**: Stops coordinated agent swarm, releases claimed tasks
 - **Ultrapilot**: Stops parallel autopilot workers
 - **Pipeline**: Stops sequential agent pipeline
-- **Team**: Sends shutdown_request to all teammates, waits for responses, calls TeamDelete, clears linked ralph if present
+- **Team**: Requests shutdown from all teammates through the active team/conversation surface, waits for responses/timeouts, clears OMC team state, clears linked ralph if present. Claude Code 2.1.178+ has no TeamDelete.
 - **Team+Ralph (linked)**: Cancels team first (graceful shutdown), then clears ralph state. Cancelling ralph when linked also cancels team first.
 
 ## Usage
@@ -197,25 +197,25 @@ Use force mode to clear every session plus legacy artifacts via `state_clear`. D
 
 ### 3B. Smart Cancellation (default)
 
-#### If Team Active (Claude Code native)
+#### If Team Active (Claude Code implicit team)
 
-Teams are detected by checking for config files in `${CLAUDE_CONFIG_DIR:-~/.claude}/teams/`:
+Teams are detected through OMC team state, not removed Claude Code `~/.claude/teams` config directories:
 
 ```bash
-# Check for active teams
-TEAM_CONFIGS=$(find "${CLAUDE_CONFIG_DIR:-$HOME/.claude}"/teams -name config.json -maxdepth 2 2>/dev/null)
+# Check for active OMC team state
+state_read(mode="team")
 ```
 
 **Two-pass cancellation protocol:**
 
 **Pass 1: Graceful Shutdown**
 ```
-For each team found in ${CLAUDE_CONFIG_DIR:-~/.claude}/teams/:
-  1. Read config.json to get team_name and members list
-  2. For each non-lead member:
-     a. Send shutdown_request via SendMessage
+For the active OMC team state:
+  1. Read team_name and worker labels from OMC state/handoffs/task bookkeeping
+  2. For each active teammate:
+     a. Ask or notify the named teammate through the active conversation/team messaging surface
      b. Wait up to 15 seconds for shutdown_response
-     c. If response received: member terminates and is auto-removed
+     c. If response received: mark member acknowledged
      d. If timeout: mark member as unresponsive, continue to next
   3. Log: "Graceful pass: X/Y members responded"
 ```
@@ -223,36 +223,31 @@ For each team found in ${CLAUDE_CONFIG_DIR:-~/.claude}/teams/:
 **Pass 2: Reconciliation**
 ```
 After graceful pass:
-  1. Re-read config.json to check remaining members
-  2. If only lead remains (or config is empty): proceed to TeamDelete
-  3. If unresponsive members remain:
-     a. Wait 5 more seconds (they may still be processing)
-     b. Re-read config.json again
-     c. If still stuck: attempt TeamDelete anyway
-     d. If TeamDelete fails: report manual cleanup path
+  1. Wait 5 more seconds for unresponsive teammates that may still be processing
+  2. Record any remaining unresponsive teammates in the cancellation report
+  3. Do not call TeamDelete; Claude Code 2.1.178+ removed per-team native cleanup
 ```
 
-**TeamDelete + Cleanup:**
+**OMC State Cleanup:**
 ```
-  1. Call TeamDelete() — removes ~/.claude/teams/{name}/ and ~/.claude/tasks/{name}/
-  2. Clear team state: state_clear(mode="team")
-  3. Check for linked ralph: state_read(mode="ralph") — if linked_team is true:
+  1. Clear team state: state_clear(mode="team")
+  2. Check for linked ralph: state_read(mode="ralph") — if linked_team is true:
      a. Clear ralph state: state_clear(mode="ralph")
      b. Clear linked ultrawork if present: state_clear(mode="ultrawork")
-  4. Run orphan scan (see below)
-  5. Emit structured cancel report
+  3. Run OMC tmux/CLI orphan scan only for legacy `omc team` / `/omc-teams` workers (see below)
+  4. Emit structured cancel report
 ```
 
 **Orphan Detection (Post-Cleanup):**
 
-After TeamDelete, verify no agent processes remain:
+For legacy OMC tmux/CLI worker runs, verify no worker processes remain:
 ```bash
 node "${CLAUDE_PLUGIN_ROOT}/scripts/cleanup-orphans.mjs" --team-name "{team_name}"
 ```
 
 The orphan scanner:
-1. Checks `ps aux` (Unix) or `tasklist` (Windows) for processes with `--team-name` matching the deleted team
-2. For each orphan whose team config no longer exists: sends SIGTERM, waits 5s, sends SIGKILL if still alive
+1. Checks `ps aux` (Unix) or `tasklist` (Windows) for OMC worker processes with `--team-name` matching the cleaned-up team
+2. Sends SIGTERM, waits 5s, sends SIGKILL if still alive
 3. Reports cleanup results as JSON
 
 Use `--dry-run` to inspect without killing. The scanner is safe to run multiple times.
@@ -263,20 +258,19 @@ Team "{team_name}" cancelled:
   - Members signaled: N
   - Responses received: M
   - Unresponsive: K (list names if any)
-  - TeamDelete: success/failed
+  - OMC state cleared: yes/no
   - Manual cleanup needed: yes/no
-    Path: ~/.claude/teams/{name}/ and ~/.claude/tasks/{name}/
+    Path: OMC team state / tmux worker processes, if any
 ```
 
 **Implementation note:** The cancel skill is executed by the LLM, not as a bash script. When you detect an active team:
-1. Read `${CLAUDE_CONFIG_DIR:-~/.claude}/teams/*/config.json` to find active teams
-2. If multiple teams exist, cancel oldest first (by `createdAt`)
-3. For each non-lead member, call `SendMessage(type: "shutdown_request", recipient: member-name, content: "Cancelling")`
+1. Read `state_read(mode="team")` to find the active OMC team
+2. Identify active named teammates from state, handoffs, or task bookkeeping
+3. For each teammate, ask or notify the named teammate through the active conversation/team messaging surface
 4. Wait briefly for shutdown responses (15s per member timeout)
-5. Re-read config.json to check for remaining members (reconciliation pass)
-6. Call `TeamDelete()` to clean up
-7. Clear team state: `state_clear(mode="team", session_id)`
-8. Report structured summary to user
+5. Record unresponsive teammates after a reconciliation wait
+6. Clear team state: `state_clear(mode="team", session_id)`
+7. Report structured summary to user
 
 #### If Autopilot Active
 

package/bundled/upstream/oh-my-claudecode/skills/ccg/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: ccg
-description: Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results
+description: Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask antigravity (or gemini), then Claude synthesizes results
 level: 5
 ---
 
 # CCG - Claude-Codex-Gemini Tri-Model Orchestration
 
-CCG routes through the canonical `/ask` skill (`/ask codex` + `/ask gemini`), then Claude synthesizes both outputs into one answer.
+CCG routes through the canonical `/ask` skill (`/ask codex` + `/ask antigravity`), then Claude synthesizes both outputs into one answer.
 
 Use this when you want parallel external perspectives without launching tmux team workers.
 
@@ -14,13 +14,16 @@ Use this when you want parallel external perspectives without launching tmux tea
 
 - Backend/analysis + frontend/UI work in one request
 - Code review from multiple perspectives (architecture + design/UX)
-- Cross-validation where Codex and Gemini may disagree
+- Cross-validation where Codex and Antigravity/Gemini may disagree
 - Fast advisor-style parallel input without team runtime orchestration
 
 ## Requirements
 
 - **Codex CLI**: `npm install -g @openai/codex` (or `@openai/codex`)
-- **Gemini CLI**: `npm install -g @google/gemini-cli`
+- **Antigravity CLI** (Google's successor to the Gemini CLI): install the `agy` binary
+  per the [official Antigravity instructions](https://antigravity.google) (inspect any
+  installer before running it). Verify: `agy --version`
+- **Gemini CLI** remains supported for enterprise/API-key use cases: `npm install -g @google/gemini-cli`
 - `omc ask` command available
 - If either CLI is unavailable, continue with whichever provider is available and note the limitation
 
@@ -29,11 +32,12 @@ Use this when you want parallel external perspectives without launching tmux tea
 ```text
 1. Claude decomposes the request into two advisor prompts:
    - Codex prompt (analysis/architecture/backend)
-   - Gemini prompt (UX/design/docs/alternatives)
+   - Antigravity prompt (UX/design/docs/alternatives) — use gemini for enterprise
 
 2. Claude runs via CLI (skill nesting not supported):
    - `omc ask codex "<codex prompt>"`
-   - `omc ask gemini "<gemini prompt>"`
+   - `omc ask antigravity "<antigravity prompt>"`
+     (or `omc ask gemini "<gemini prompt>"` for enterprise)
 
 3. Artifacts are written under `.omc/artifacts/ask/`
 
@@ -48,17 +52,23 @@ When invoked, Claude MUST follow this workflow:
 Split the user request into:
 
 - **Codex prompt:** architecture, correctness, backend, risks, test strategy
-- **Gemini prompt:** UX/content clarity, alternatives, edge-case usability, docs polish
+- **Antigravity prompt:** UX/content clarity, alternatives, edge-case usability, docs polish
 - **Synthesis plan:** how to reconcile conflicts
 
 ### 2. Invoke advisors via CLI
 
 > **Note:** Skill nesting (invoking a skill from within an active skill) is not supported in Claude Code. Always use the direct CLI path via Bash tool.
 
-Run both advisors:
+Run both advisors (use antigravity or gemini depending on your setup):
 
 ```bash
 omc ask codex "<codex prompt>"
+omc ask antigravity "<antigravity prompt>"
+```
+
+Enterprise fallback:
+
+```bash
 omc ask gemini "<gemini prompt>"
 ```
 
@@ -68,6 +78,7 @@ Read latest ask artifacts from:
 
 ```text
 .omc/artifacts/ask/codex-*.md
+.omc/artifacts/ask/antigravity-*.md
 .omc/artifacts/ask/gemini-*.md
 ```
 
@@ -100,5 +111,5 @@ If both unavailable:
 Example:
 
 ```bash
-/oh-my-claudecode:ccg Review this PR - architecture/security via Codex and UX/readability via Gemini
+/oh-my-claudecode:ccg Review this PR - architecture/security via Codex and UX/readability via Antigravity
 ```

package/bundled/upstream/oh-my-claudecode/skills/configure-notifications/SKILL.md

@@ -993,11 +993,11 @@ If migrate:
 **Options:**
 1. **OpenClaw Gateway** - Wake external automations and AI agents
 2. **n8n Webhook** - Trigger n8n workflows
-3. **ClawdBot** - Send notifications to ClawdBot
+3. **Custom Agent Gateway** - Send notifications to a custom agent webhook
 4. **Generic Webhook** - Custom HTTPS webhook
 5. **Generic CLI Command** - Execute shell command on events
 
-### OpenClaw/n8n/ClawdBot Preset Flow
+### OpenClaw/n8n/Custom Agent Gateway Preset Flow
 
 **Step 2: Gateway URL**
 

package/bundled/upstream/oh-my-claudecode/skills/omc-reference/SKILL.md

@@ -42,15 +42,17 @@ Prefix: `oh-my-claudecode:`. See `agents/*.md` for full prompts.
 
 ### External AI / orchestration
 - `/team N:executor "task"`
-- `omc team N:codex|gemini "..."`
-- `omc ask <claude|codex|gemini>`
+- `omc team N:codex|gemini|antigravity "..."`
+- `omc ask <claude|codex|gemini|antigravity>`
 - `/ccg`
 
 ### OMC state
 - `state_read`, `state_write`, `state_clear`, `state_list_active`, `state_get_status`
 
-### Team runtime
-- `TeamCreate`, `TeamDelete`, `SendMessage`, `TaskCreate`, `TaskList`, `TaskGet`, `TaskUpdate`
+### Team orchestration
+- Claude Code 2.1.178+ uses one implicit agent team per session. Spawn teammates directly with Agent/Task using distinct `name` values; do not call removed `TeamCreate`/`TeamDelete` tools or rely on `team_name` for native routing.
+- Use TodoWrite or the available task-list surface for tracking only. Task-list tools do not create native teams.
+- Legacy OMC tmux/CLI teams are separate: use `/team` or `omc team` plus OMC state/API commands for external worker runs.
 
 ### Notepad
 - `notepad_read`, `notepad_write_priority`, `notepad_write_working`, `notepad_write_manual`

package/bundled/upstream/oh-my-claudecode/skills/omc-setup/phases/02-configure.md

@@ -211,7 +211,7 @@ If beads or beads-rust is detected, use AskUserQuestion:
 **Question:** "Which task management tool should I use for tracking work?"
 
 **Options:**
-1. **Built-in Tasks (default)** - Use Claude Code's native TaskCreate/TodoWrite. Tasks are session-only.
+1. **Built-in Tasks (default)** - Use Claude Code's native TodoWrite or available task-list surface. Tasks are session-only.
 2. **Beads (bd)** - Git-backed persistent tasks. Survives across sessions. [Only if detected]
 3. **Beads-Rust (br)** - Lightweight Rust port of beads. [Only if detected]
 

package/bundled/upstream/oh-my-claudecode/skills/omc-setup/phases/03-integrations.md

@@ -145,7 +145,8 @@ Use AskUserQuestion with multiple questions:
 **Options:**
 1. **claude (Recommended)** - Default provider with the widest compatibility
 2. **codex** - Use Codex CLI workers by default when installed
-3. **gemini** - Use Gemini CLI workers by default when installed
+3. **gemini** - Use Gemini CLI workers by default when installed (enterprise/API-key tier)
+4. **antigravity** - Use Antigravity CLI (`agy`) workers by default when installed; Google's successor to the Gemini CLI (install per the [official instructions](https://antigravity.google))
 
 Store the team configuration in `~/.claude/.omc-config.json`:
 

package/bundled/upstream/oh-my-claudecode/skills/omc-setup/phases/04-welcome.md

@@ -42,7 +42,7 @@ TEAMS:
 Spawn coordinated agents with shared task lists and real-time messaging:
 - /oh-my-claudecode:team 3:executor "fix all TypeScript errors"
 - /oh-my-claudecode:team 5:debugger "fix build errors in src/"
-Teams use Claude Code native tools (TeamCreate/SendMessage/TaskCreate).
+Teams use Claude Code's implicit agent team (spawn teammates directly with distinct `name` values; no TeamCreate/TeamDelete in Claude Code 2.1.178+).
 
 MCP SERVERS:
 Run /oh-my-claudecode:mcp-setup to add tools like web search, GitHub, etc.
@@ -86,7 +86,7 @@ MAGIC KEYWORDS (power-user shortcuts):
 TEAMS (NEW!):
 Spawn coordinated agents with shared task lists and real-time messaging:
 - /oh-my-claudecode:team 3:executor "fix all TypeScript errors"
-- Uses Claude Code native tools (TeamCreate/SendMessage/TaskCreate)
+- Uses Claude Code's implicit agent team (spawn teammates directly with distinct `name` values; no TeamCreate/TeamDelete in Claude Code 2.1.178+)
 
 HUD STATUSLINE:
 The status bar now shows OMC state. Restart Claude Code to see it.

package/bundled/upstream/oh-my-claudecode/skills/omc-teams/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: omc-teams
-description: CLI-team runtime for claude, codex, or gemini workers in tmux panes when you need process-based parallel execution
+description: CLI-team runtime for claude, codex, gemini, antigravity, grok, or cursor workers in tmux panes when you need process-based parallel execution
 aliases: []
 level: 4
 ---
 
 # OMC Teams Skill
 
-Spawn N CLI worker processes in tmux panes to execute tasks in parallel. Supports `claude`, `codex`, and `gemini` agent types.
+Spawn N CLI worker processes in tmux panes to execute tasks in parallel. Supports `claude`, `codex`, `gemini`, `antigravity`, `grok`, and `cursor` agent types. Cursor workers are executor-style only.
 
 `/omc-teams` is a legacy compatibility skill for the CLI-first runtime: use `omc team ...` commands (not deprecated MCP runtime tools).
 
@@ -17,12 +17,15 @@ Spawn N CLI worker processes in tmux panes to execute tasks in parallel. Support
 /oh-my-claudecode:omc-teams N:claude "task description"
 /oh-my-claudecode:omc-teams N:codex "task description"
 /oh-my-claudecode:omc-teams N:gemini "task description"
+/oh-my-claudecode:omc-teams N:antigravity "task description"
+/oh-my-claudecode:omc-teams N:grok "task description"
+/oh-my-claudecode:omc-teams N:cursor "implementation task description"
 ```
 
 ### Parameters
 
 - **N** - Number of CLI workers (1-10)
-- **agent-type** - `claude` (Claude CLI), `codex` (OpenAI Codex CLI), or `gemini` (Google Gemini CLI)
+- **agent-type** - `claude` (Claude CLI), `codex` (OpenAI Codex CLI), `gemini` (Google Gemini CLI; enterprise/API-key tier), `antigravity` (Antigravity CLI `agy`; Google's successor to the Gemini CLI), `grok` (xAI Grok CLI), or `cursor` (Cursor agent CLI; executor-style tasks only)
 - **task** - Task description to distribute across all workers
 
 ### Examples
@@ -31,15 +34,21 @@ Spawn N CLI worker processes in tmux panes to execute tasks in parallel. Support
 /omc-teams 2:claude "implement auth module with tests"
 /omc-teams 2:codex "review the auth module for security issues"
 /omc-teams 3:gemini "redesign UI components for accessibility"
+/omc-teams 3:antigravity "redesign UI components for accessibility"
+/omc-teams 1:grok "prototype an implementation approach"
+/omc-teams 1:cursor "apply the implementation plan"
 ```
 
 ## Requirements
 
 - **tmux binary** must be installed and discoverable (`command -v tmux`) when running from a plain terminal; classic tmux sessions reuse the current tmux surface.
 - **cmux surface optional** for in-place native splits (`CMUX_SURFACE_ID` set without `$TMUX`). Plain terminals still use the detached tmux fallback.
-- **claude** CLI: `npm install -g @anthropic-ai/claude-code`
+- **claude** CLI: install and authenticate Claude Code using the [official setup instructions](https://code.claude.com/docs/en/setup); the legacy Anthropic npm package install path is deprecated for normal user installs.
 - **codex** CLI: `npm install -g @openai/codex`
-- **gemini** CLI: `npm install -g @google/gemini-cli`
+- **gemini** CLI: `npm install -g @google/gemini-cli` (enterprise/API-key tier)
+- **antigravity** CLI: Install per the [official instructions](https://antigravity.google) (provides the `agy` binary) — verify with `agy --version`; Google's successor to the Gemini CLI
+- **grok** CLI: install and authenticate the Grok CLI used by your environment
+- **cursor** CLI: install and authenticate `cursor-agent`; if unavailable, report this setup requirement instead of silently falling back to Claude-only execution
 
 ## Workflow
 
@@ -66,12 +75,13 @@ tmux display-message -p '#S'
 Extract:
 
 - `N` — worker count (1–10)
-- `agent-type` — `claude|codex|gemini`
+- `agent-type` — `claude|codex|gemini|grok|cursor`
 - `task` — task description
 
 Validate before decomposing or running anything:
 
-- Reject unsupported agent types up front. `/omc-teams` only supports **`claude`**, **`codex`**, and **`gemini`**.
+- Reject unsupported agent types up front. `/omc-teams` only supports **`claude`**, **`codex`**, **`gemini`**, **`antigravity`**, **`grok`**, and **`cursor`**.
+- Treat Cursor workers as executor-style only. Accept `N:cursor` and `N:cursor:executor`; reject or reframe reviewer, critic, security-reviewer, verdict, or final-approval work onto native Claude/OMC reviewer agents.
 - If the user asks for an unsupported type such as `expert`, explain that `/omc-teams` launches external CLI workers only.
 - For native Claude Code team agents/roles, direct them to **`/oh-my-claudecode:team`** instead.
 
@@ -94,7 +104,7 @@ working directory before launch:
   plan after `--cwd` changes the launch directory.
 - Include the explicit repo paths or repo names in the task text and subtasks.
 - Do not anchor the launch cwd to only the repo containing `.omc/plans/...` when
-  target repos are siblings; that strands `codex`, `claude`, and `gemini` workers in
+  target repos are siblings; that strands `codex`, `claude`, `gemini`, `antigravity`, `grok`, and `cursor` workers in
   the plan repo instead of the implementation workspace.
 - If no safe shared workspace root can be identified, do not launch `/omc-teams`.
   Report the single-cwd constraint and ask for, or derive from evidence, the intended
@@ -111,14 +121,14 @@ state_write(mode="team", current_phase="team-exec", active=true)
 Start workers via CLI:
 
 ```bash
-omc team <N>:<claude|codex|gemini> "<task>"
+omc team <N>:<claude|codex|gemini|antigravity|grok|cursor> "<task>"
 ```
 
 For the multi-repo case resolved in Phase 2.5, launch from the shared workspace root
 with the existing `--cwd` contract and keep the plan reference absolute:
 
 ```bash
-omc team <N>:<claude|codex|gemini> "<task with absolute plan path and explicit repo paths>" --cwd <workspace-root>
+omc team <N>:<claude|codex|gemini|antigravity|grok|cursor> "<task with absolute plan path and explicit repo paths>" --cwd <workspace-root>
 ```
 
 Team name defaults to a slug from the task text (example: `review-auth-flow`).
@@ -175,17 +185,18 @@ If encountered, switch to `omc team ...` CLI commands.
 | ---------------------------- | ----------------------------------- | ----------------------------------------------------------------------------------- |
 | `not inside tmux`            | Requested in-place pane topology from a non-tmux surface | Start tmux and rerun, or let `omc team` use its detached-session fallback           |
 | `cmux surface detected`      | Running inside cmux without `$TMUX` | Use the normal `omc team ...` flow; OMC will create native cmux worker splits      |
-| `Unsupported agent type`     | Requested agent is not claude/codex/gemini | Use `claude`, `codex`, or `gemini`; for native Claude Code agents use `/oh-my-claudecode:team` |
+| `Unsupported agent type`     | Requested agent is not claude/codex/gemini/antigravity/grok/cursor | Use `claude`, `codex`, `gemini`, `antigravity`, `grok`, or `cursor`; for native Claude Code agents use `/oh-my-claudecode:team` |
 | `codex: command not found`   | Codex CLI not installed             | `npm install -g @openai/codex`                                                      |
-| `gemini: command not found`  | Gemini CLI not installed            | `npm install -g @google/gemini-cli`                                                 |
+| `gemini: command not found`  | Gemini CLI not installed            | `npm install -g @google/gemini-cli` (enterprise/API-key tier)                       |
+| `agy: command not found`     | Antigravity CLI not installed       | Install per the [official instructions](https://antigravity.google)                |
 | `Team <name> is not running` | stale or missing runtime state      | `omc team status <team-name>` then `omc team shutdown <team-name> --force` if stale |
 | `status: failed`             | Workers exited with incomplete work | inspect runtime output, narrow scope, rerun                                         |
 
 ## Relationship to `/team`
 
-| Aspect       | `/team`                                   | `/omc-teams`                                         |
-| ------------ | ----------------------------------------- | ---------------------------------------------------- |
-| Worker type  | Claude Code native team agents            | claude / codex / gemini CLI processes in tmux        |
-| Invocation   | `TeamCreate` / `Task` / `SendMessage`     | `omc team [N:agent]` + `status` + `shutdown` + `api` |
-| Coordination | Native team messaging and staged pipeline | tmux worker runtime + CLI API state files            |
-| Use when     | You want Claude-native team orchestration | You want external CLI worker execution               |
+| Aspect       | `/team`                                                       | `/omc-teams`                                         |
+| ------------ | ------------------------------------------------------------- | ---------------------------------------------------- |
+| Worker type  | Claude Code implicit agent-team teammates                     | claude / codex / gemini / antigravity CLI processes in tmux        |
+| Invocation   | Agent/Task spawn with distinct `name` values; no TeamCreate/TeamDelete in Claude Code 2.1.178+ | `omc team [N:agent]` + `status` + `shutdown` + `api` |
+| Coordination | Native implicit-team messaging and staged pipeline            | tmux worker runtime + CLI API state files            |
+| Use when     | You want Claude-native in-session agent orchestration         | You want external CLI worker execution               |