chore(root): update oh-my-agent to v4.23.3

Generated with oh-my-agent

Co-Authored-By: First Fluke <our.first.fluke@gmail.com>

Author: gracefullight

.agents/skills/_shared/conditional/exploration-loop.md

@@ -42,7 +42,7 @@ Hypothesis B: ...
 
 Execute each hypothesis **in isolation**.
 
-**In multi-agent mode** (`/orchestrate`, `/coordinate`):
+**In multi-agent mode** (`/orchestrate`, `/work`):
 - Spawn the **same agent type** (e.g., `backend-engineer`) multiple times with different prompts
 - Each spawn includes the hypothesis context in the task description:
   ```
@@ -139,7 +139,7 @@ Agent FAIL after 2 retries
   → Keep winner workspace, discard others
 ```
 
-### In `/coordinate`
+### In `/work`
 
 Triggered when Issue Remediation Loop stalls (same issue persists after fix):
 

.agents/skills/_shared/core/context-budget.md

@@ -157,7 +157,7 @@ When a trigger fires, the Orchestrator executes:
 
 3. **Re-spawn**: Start a fresh agent with the checkpoint as context
    - **Claude Code**: New Agent tool call with checkpoint in prompt
-   - **CLI agents**: `oh-my-ag agent:spawn` with `--checkpoint checkpoint-{agent-id}`
+   - **CLI agents**: `oma agent:spawn` with `--checkpoint checkpoint-{agent-id}`
 
 4. **Resume**: New agent reads checkpoint, continues from remaining items only
 

.agents/skills/_shared/core/evaluator-tuning.md

@@ -5,7 +5,7 @@ iterative refinement based on observed judgment errors.
 (ref: Anthropic harness design — "several rounds of development loop necessary")
 
 This protocol is **semi-automated**: collection is automatic, analysis and patching
-require human review via `oh-my-ag retro`.
+require human review via `oma retro`.
 
 ---
 
@@ -16,7 +16,7 @@ Sessions accumulate EA events in session-metrics.md
     ↓
 [1] Trigger: EA >= 30 on rolling 3-session window
     ↓
-[2] `oh-my-ag retro` aggregates EA events and generates tuning report
+[2] `oma retro` aggregates EA events and generates tuning report
     ↓
 [3] Report categorizes errors by type and suggests specific patches
     ↓
@@ -75,7 +75,7 @@ This prevents tuning drift toward pure skepticism — QA must also know what it
 | System | Role |
 |--------|------|
 | `session-metrics.md` | EA event source (automatic collection) |
-| `oh-my-ag retro` | Aggregation + tuning report generation (semi-automated) |
+| `oma retro` | Aggregation + tuning report generation (semi-automated) |
 | `lessons-learned.md` | QA Evaluation Lessons for persistent patterns |
 | QA `checklist.md` | Primary patch target for missed checks |
 | QA `execution-protocol.md` | Patch target for process/severity issues |

.agents/skills/_shared/core/session-metrics.md

@@ -175,7 +175,7 @@ This data is sourced from the Experiment Ledger at session end (see `experiment-
 - **Active session**: `.serena/memories/session-metrics.md`
 - **Completed sessions**: Archived to `.serena/memories/archive/metrics-{date}.md`
 - **Retention**: 30 days (configurable)
-- **Aggregation**: `oh-my-ag stats` command summarizes trends
+- **Aggregation**: `oma stats` command summarizes trends
 
 ---
 
@@ -198,7 +198,7 @@ Unlike CD (tracked in real-time), Evaluator Accuracy (EA) is a
 ### Recording
 
 - `false_positive`, `missed_stub`, `good_catch`: Recorded during session by Orchestrator
-- `false_negative`, `severity_mismatch`: Recorded retroactively via `oh-my-ag retro` or next session discovery
+- `false_negative`, `severity_mismatch`: Recorded retroactively via `oma retro` or next session discovery
 
 ### Evaluator Accuracy Score (EA)
 
@@ -210,7 +210,7 @@ EA = sum(accuracy_event_points across last 3 sessions)
 
 | Threshold | Action |
 |-----------|--------|
-| EA >= 30 | **TUNING SUGGESTED**: `oh-my-ag retro` flags QA patterns for review |
+| EA >= 30 | **TUNING SUGGESTED**: `oma retro` flags QA patterns for review |
 | EA >= 50 | **TUNING REQUIRED**: Review and update QA execution-protocol.md |
 | `false_negative` >= 3 across window | **CHECKLIST UPDATE**: Add detection pattern to QA checklist.md |
 | `good_catch` >= 5 across window | **PROPAGATE**: Document successful pattern in evaluator-tuning.md |
@@ -256,7 +256,7 @@ Use proxy metrics that are always measurable.
 - **Turn count**: Always available (count progress file updates)
 - **Wall-clock time**: Bash timestamps at spawn and completion
 - **Sprint resets**: Count checkpoint files per agent
-- **Precise tokens**: Available only via `oh-my-ag stats` post-hoc (parses CLI logs when supported)
+- **Precise tokens**: Available only via `oma stats` post-hoc (parses CLI logs when supported)
 
 ### Usage
 

.agents/skills/_shared/core/vendor-detection.md

@@ -8,14 +8,14 @@ When executing a workflow, determine your runtime environment using this priorit
 2. **Codex CLI**: Your system prompt contains "Codex CLI" OR the `apply_patch` tool is available
 3. **Gemini CLI**: This file was auto-loaded from `.agents/skills/` AND `@` subagent syntax is available
 4. **Antigravity IDE**: This file was auto-loaded from `.agents/skills/` AND no `@` subagent syntax
-5. **CLI Fallback**: None of the above matched → use `oh-my-ag agent:spawn`
+5. **CLI Fallback**: None of the above matched → use `oma agent:spawn`
 
 ## Vendor-Specific Spawn Methods
 
 | Vendor | Spawn Method | Result Handling |
 |:---|:---|:---|
 | Claude Code | `Agent` tool with `.claude/agents/{name}.md` | Synchronous return |
 | Codex CLI | Model-mediated parallel subagent request | JSON output |
-| Gemini CLI | `@{agent-name}` delegation or `oh-my-ag agent:spawn` | MCP memory poll |
-| Antigravity | `oh-my-ag agent:spawn` only (custom subagents not available) | MCP memory poll |
-| CLI Fallback | `oh-my-ag agent:spawn {agent} {prompt} {session} -w {workspace}` | Result file poll |
+| Gemini CLI | `@{agent-name}` delegation or `oma agent:spawn` | MCP memory poll |
+| Antigravity | `oma agent:spawn` only (custom subagents not available) | MCP memory poll |
+| CLI Fallback | `oma agent:spawn {agent} {prompt} {session} -w {workspace}` | Result file poll |

.agents/skills/_shared/runtime/memory-protocol.md

@@ -1,6 +1,6 @@
 # Memory Protocol (CLI Mode)
 
-> **Note**: This file documents the default (Serena/MCP) memory protocol. Vendor-specific execution protocols are injected automatically by `oh-my-ag agent:spawn` from `execution-protocols/{vendor}.md`.
+> **Note**: This file documents the default (Serena/MCP) memory protocol. Vendor-specific execution protocols are injected automatically by `oma agent:spawn` from `execution-protocols/{vendor}.md`.
 
 When running as a CLI subagent, follow this protocol.
 

.agents/skills/_version.json

@@ -1,3 +1,3 @@
 {
-  "version": "4.23.1"
-}
+  "version": "4.23.3"
+}

.agents/skills/oma-backend/SKILL.md

@@ -80,7 +80,7 @@ Before submitting, run `resources/checklist.md`.
 
 ## Execution Protocol (CLI Mode)
 
-Vendor-specific execution protocols are injected automatically by `oh-my-ag agent:spawn`.
+Vendor-specific execution protocols are injected automatically by `oma agent:spawn`.
 Source files live under `../_shared/runtime/execution-protocols/{vendor}.md`.
 
 ## References

.agents/skills/oma-brainstorm/SKILL.md

@@ -44,7 +44,7 @@ Follow the brainstorm workflow step by step:
 
 ## Execution Protocol (CLI Mode)
 
-Vendor-specific execution protocols are injected automatically by `oh-my-ag agent:spawn`.
+Vendor-specific execution protocols are injected automatically by `oma agent:spawn`.
 Source files live under `../_shared/runtime/execution-protocols/{vendor}.md`.
 
 ## References

.agents/skills/oma-coordination/SKILL.md

@@ -43,8 +43,8 @@ Spawn agents via CLI:
 
 ```bash
 # Example: spawn backend and frontend in parallel
-oh-my-ag agent:spawn backend "task description" session-id -w ./backend &
-oh-my-ag agent:spawn frontend "task description" session-id -w ./frontend &
+oma agent:spawn backend "task description" session-id -w ./backend &
+oma agent:spawn frontend "task description" session-id -w ./frontend &
 wait
 ```