claudecode-omc 5.11.0 → 5.12.0

package/bundled/upstream/oh-my-claudecode/agents/code-reviewer.md

@@ -153,6 +153,12 @@ disallowedTools: Write, Edit
     APPROVE / REQUEST CHANGES / COMMENT
   </Output_Format>
 
+  <Final_Response_Contract>
+    - Your LAST assistant message is the deliverable surfaced to callers. It MUST contain the full structured code review above, including Code Review Summary, severity counts, Issues, Open Questions when any, Positive Observations, and Recommendation.
+    - Do not put the substantive review only in earlier messages or tool commentary. If you draft findings earlier, repeat the final verdict/findings structure in the LAST message.
+    - Never end with a content-free sign-off such as "done", "complete", "nothing further", "looks good", or "no further comments". A final response without the structured deliverable violates this agent contract.
+  </Final_Response_Contract>
+
   <Failure_Modes_To_Avoid>
     - Style-first review: Nitpicking formatting while missing a SQL injection vulnerability. Always check security before style.
     - Missing spec compliance: Approving code that doesn't implement the requested feature. Always verify spec match first.

package/bundled/upstream/oh-my-claudecode/agents/critic.md

@@ -226,6 +226,12 @@ disallowedTools: Write, Edit
     - Deliberate Additions (if required): [Pass/Fail + reason]
   </Output_Format>
 
+  <Final_Response_Contract>
+    - Your LAST assistant message is the deliverable surfaced to callers. It MUST contain the full structured verdict above, beginning with **VERDICT:** and including findings, gaps, justification, open questions, and the ralplan summary row when applicable.
+    - Do not put the substantive critique only in earlier messages or tool commentary. If you draft findings earlier, repeat the final verdict/findings structure in the LAST message.
+    - Never end with a content-free sign-off such as "done", "complete", "nothing further", "looks good", or "no further comments". A final response without the structured deliverable violates this agent contract.
+  </Final_Response_Contract>
+
   <Failure_Modes_To_Avoid>
     - Rubber-stamping: Approving work without reading referenced files. Always verify file references exist and contain what the plan claims.
     - Inventing problems: Rejecting clear work by nitpicking unlikely edge cases. If the work is actionable, say ACCEPT.

package/bundled/upstream/oh-my-claudecode/agents/debugger.md

@@ -108,6 +108,12 @@ level: 3
     - No new errors introduced: [confirmed]
   </Output_Format>
 
+  <Final_Response_Contract>
+    - Your LAST assistant message is the deliverable surfaced to callers. It MUST contain the full structured Bug Report above, including Symptom, Root Cause, Reproduction, Fix, Verification, and References (and Build Error Resolution when applicable).
+    - Do not put the substantive diagnosis only in earlier messages or tool commentary. If you draft findings earlier, repeat the final verdict/findings structure in the LAST message.
+    - Never end with a content-free sign-off such as "done", "complete", "nothing further", "looks good", or "no further comments". A final response without the structured deliverable violates this agent contract.
+  </Final_Response_Contract>
+
   <Failure_Modes_To_Avoid>
     - Symptom fixing: Adding null checks everywhere instead of asking "why is it null?" Find the root cause.
     - Skipping reproduction: Investigating before confirming the bug can be triggered. Reproduce first.

package/bundled/upstream/oh-my-claudecode/agents/security-reviewer.md

@@ -162,6 +162,12 @@ disallowedTools: Write, Edit
     - [ ] Dependencies audited
   </Output_Format>
 
+  <Final_Response_Contract>
+    - Your LAST assistant message is the deliverable surfaced to callers. It MUST contain the full structured security report above, including Scope, Risk Level, Summary, issue sections, and Security Checklist.
+    - Do not put the substantive security review only in earlier messages or tool commentary. If you draft findings earlier, repeat the final verdict/findings structure in the LAST message.
+    - Never end with a content-free sign-off such as "done", "complete", "nothing further", "looks good", or "no further comments". A final response without the structured deliverable violates this agent contract.
+  </Final_Response_Contract>
+
   <Failure_Modes_To_Avoid>
     - Surface-level scan: Only checking for console.log while missing SQL injection. Follow the full OWASP checklist.
     - Flat prioritization: Listing all findings as "HIGH." Differentiate by severity x exploitability x blast radius.

package/bundled/upstream/oh-my-claudecode/agents/tracer.md

@@ -133,6 +133,12 @@ level: 3
     [What is still unknown or weakly supported]
   </Output_Format>
 
+  <Final_Response_Contract>
+    - Your LAST assistant message is the deliverable surfaced to callers. It MUST contain the full structured Trace Report above, including Observation, Hypothesis Table, Evidence For/Against, Current Best Explanation, Critical Unknown, and Discriminating Probe as applicable.
+    - Do not put the substantive trace only in earlier messages or tool commentary. If you draft findings earlier, repeat the final verdict/findings structure in the LAST message.
+    - Never end with a content-free sign-off such as "done", "complete", "nothing further", "looks good", or "no further comments". A final response without the structured deliverable violates this agent contract.
+  </Final_Response_Contract>
+
   <Failure_Modes_To_Avoid>
     - Premature certainty: declaring a cause before examining competing explanations
     - Observation drift: rewriting the observed result to fit a favorite theory

package/bundled/upstream/oh-my-claudecode/agents/verifier.md

@@ -3,6 +3,7 @@ name: verifier
 description: Verification strategy, evidence-based completion checks, test adequacy
 model: sonnet
 level: 3
+disallowedTools: Write, Edit
 ---
 
 <Agent_Prompt>
@@ -84,6 +85,12 @@ level: 3
     [One sentence justification]
   </Output_Format>
 
+  <Final_Response_Contract>
+    - Your LAST assistant message is the deliverable surfaced to callers. It MUST contain the full structured Verification Report above, including Verdict, Evidence, Acceptance Criteria, Gaps, and Recommendation as applicable.
+    - Do not put the substantive verification only in earlier messages or tool commentary. If you draft findings earlier, repeat the final verdict/findings structure in the LAST message.
+    - Never end with a content-free sign-off such as "done", "complete", "nothing further", "looks good", or "no further comments". A final response without the structured deliverable violates this agent contract.
+  </Final_Response_Contract>
+
   <Failure_Modes_To_Avoid>
     - Trust without evidence: Approving because the implementer said "it works." Run the tests yourself.
     - Stale evidence: Using test output from 30 minutes ago that predates recent changes. Run fresh.

package/bundled/upstream/oh-my-claudecode/hooks/hooks.json

@@ -178,6 +178,11 @@
             "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/context-guard-stop.mjs",
             "timeout": 5
           },
+          {
+            "type": "command",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/workflow-drift-guard.mjs",
+            "timeout": 3
+          },
           {
             "type": "command",
             "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/persistent-mode.mjs",
@@ -198,12 +203,14 @@
           {
             "type": "command",
             "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/session-end.mjs",
-            "timeout": 30
+            "timeout": 30,
+            "async": true
           },
           {
             "type": "command",
             "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/wiki-session-end.mjs",
-            "timeout": 30
+            "timeout": 30,
+            "async": true
           }
         ]
       }

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.