@trac3er/oh-my-god 1.0.2

package/commands/OMG:init.md

@@ -0,0 +1,134 @@
+---
+description: "Unified initializer — auto-detects: project setup (if no .omg/state), domain scaffolding (if argument given), or health check."
+allowed-tools: Read, Write, Edit, MultiEdit, Bash(mkdir:*), Bash(cat:*), Bash(find:*), Bash(ls:*), Bash(head:*), Bash(grep:*), Bash(tree:*), Bash(node:*), Bash(python*:*), Bash(tee:*), Grep, Glob
+argument-hint: "[optional: domain name like 'payment', or 'check' for health check]"
+---
+
+# /OMG:init — Unified Project & Domain Initializer
+
+## Auto-Detection Logic
+
+```
+if argument is a domain name (e.g. "payment", "user-profile"):
+  → DOMAIN INIT (create new domain from existing patterns)
+elif .omg/state directory does not exist:
+  → PROJECT INIT (first-time project setup)
+elif .omg/state/profile.yaml exists:
+  → HEALTH CHECK (verify everything works, offer upgrades)
+```
+
+---
+
+## MODE A: PROJECT INIT (no .omg/state found)
+
+### Step 1: Create .omg/state/profile.yaml (MOST IMPORTANT)
+Detect from code. Ask user for anything undetectable.
+
+```yaml
+# .omg/state/profile.yaml — injected every session (keep under 20 lines)
+name: "[from package.json/Cargo.toml/pyproject.toml]"
+description: "[1 sentence]"
+repo: "[from git remote -v]"
+
+language: "[detect]"
+framework: "[detect]"
+database: "[detect or ask]"
+infra: "[detect from Dockerfile/terraform/etc]"
+key_deps: "[top 5]"
+
+conventions:
+  naming: "[detect: camelCase/snake_case]"
+  test_cmd: "[detect: npm test/pytest/cargo test]"
+  lint_cmd: "[detect: eslint/ruff/clippy]"
+
+ai_behavior:
+  communication: "[ask user: language preference]"
+  when_stuck: "Ask user after 2 failed attempts"
+  testing: "User-journey focused, not boilerplate"
+```
+
+### Step 2: Create knowledge structure + OMG v1 contract dirs
+```
+mkdir -p .omg/state/ledger .omg/knowledge/decisions .omg/knowledge/patterns .omg/knowledge/rules
+mkdir -p .omg/trust .omg/evidence .omg/shadow .omg/migrations
+```
+
+Copy OMG v1 templates when missing:
+- `.omg/idea.yml`
+- `.omg/policy.yaml`
+- `.omg/runtime.yaml`
+
+### Step 3: Auto-detect quality gate
+```json
+// .omg/state/quality-gate.json — only include commands that exist
+{
+  "format": "[detect: prettier/black/gofmt or null]",
+  "lint": "[detect: eslint/ruff/clippy or null]",
+  "typecheck": "[detect: tsc/mypy or null]",
+  "test": "[detect: npm test/pytest/cargo test or null]"
+}
+```
+
+### Step 4: Copy relevant contextual rules
+Based on detected project type, copy relevant rules from templates:
+- Web project → security-domains.md, code-hygiene.md
+- Backend → infra-safety.md, dependency-safety.md
+- DDD project → ddd-sdd.md, outside-in.md
+
+### Step 5: Verify
+Run `/OMG:health-check` to confirm setup.
+
+---
+
+## MODE B: DOMAIN INIT (argument = domain name)
+
+### Step 1: Find Reference Pattern
+```bash
+find . -type f -name "*.ts" -o -name "*.py" | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -10
+```
+Read the most complete existing domain. Extract:
+- Directory structure (routes, services, models, tests)
+- Naming conventions, error handling, data flow patterns
+
+### Step 2: Define the New Domain
+Ask the user:
+- "What entities does [domain] have?"
+- "What actions can be performed?"
+- "What external services does it talk to?"
+- "What are the business rules?"
+
+### Step 3: Generate Domain Structure
+Match the reference pattern EXACTLY. Create:
+```
+src/[domain]/
+  ├── [domain].model.ts
+  ├── [domain].service.ts
+  ├── [domain].repository.ts
+  ├── [domain].controller.ts (or routes)
+  ├── [domain].types.ts
+  └── __tests__/
+      └── [domain].service.test.ts
+```
+
+### Step 4: Document the Pattern
+Save to `.omg/knowledge/patterns/[domain]-pattern.md`
+
+---
+
+## MODE C: HEALTH CHECK (already initialized)
+
+Run `/OMG:health-check` and additionally:
+- Verify profile.yaml is up-to-date with current project state
+- Check if new contextual rules should be added
+- Offer to update quality-gate.json if tools changed
+
+---
+
+## File Write Method
+Use `Write` tool first. If it fails (file exists), fall back to:
+```bash
+cat > .omg/state/profile.yaml << 'EOF'
+[content]
+EOF
+```
+Always READ the file after writing to confirm.

package/commands/OMG:mode.md

@@ -0,0 +1,44 @@
+---
+description: "Set cognitive mode (research/architect/implement) for the current session."
+allowed-tools: Read, Write, Edit, Bash
+argument-hint: "[research|architect|implement|clear]"
+---
+
+# /OMG:mode — Set Cognitive Mode
+
+Switch Claude's operating mode for the current session.
+
+## Usage
+
+```
+/OMG:mode research     # Focus on reading, searching, synthesizing
+/OMG:mode architect    # Focus on system design, no implementation
+/OMG:mode implement    # Focus on coding with TDD and verification
+/OMG:mode clear        # Clear current mode (return to default)
+```
+
+## What It Does
+
+1. Writes `.omg/state/mode.txt` with the selected mode name
+2. The `prompt-enhancer` hook reads this file and injects `@mode:` context on every subsequent prompt
+3. The corresponding rule file (`rules/contextual/{mode}-mode.md`) activates
+
+## Modes
+
+| Mode | Focus | When to Use |
+|------|-------|-------------|
+| `research` | Read, search, synthesize | Exploring unfamiliar territory |
+| `architect` | Design, plan, no code | Before starting a complex feature |
+| `implement` | Code, test, verify | Active development sprint |
+
+## Example
+
+```
+/OMG:mode architect
+→ Sets mode to architect
+→ Every prompt now gets: @mode:ARCHITECT — Map system first. Specs only, no implementation.
+
+/OMG:mode clear
+→ Removes .omg/state/mode.txt
+→ Mode injection stops
+```

package/commands/OMG:project-init.md

@@ -0,0 +1,11 @@
+---
+description: "Alias for /OMG:init (project setup mode). Use /OMG:init instead."
+allowed-tools: Read, Write, Edit, MultiEdit, Bash(mkdir:*), Bash(cat:*), Bash(find:*), Bash(ls:*), Bash(head:*), Bash(grep:*), Bash(tree:*), Bash(node:*), Bash(python*:*), Bash(tee:*), Grep, Glob
+argument-hint: "[optional: project description]"
+---
+
+# /OMG:project-init → Redirects to /OMG:init
+
+This command is now part of `/OMG:init`. Execute `/OMG:init` (project setup mode).
+
+Follow the **MODE A: PROJECT INIT** instructions in /OMG:init.

package/commands/OMG:ralph-start.md

@@ -0,0 +1,43 @@
+---
+description: "Start Ralph autonomous loop — continues working until all tasks complete or max iterations reached."
+allowed-tools: Read, Write, Edit, Bash, Grep, Glob
+argument-hint: "[goal description]"
+---
+
+# /OMG:ralph-start — Start Ralph Autonomous Loop
+
+## Purpose
+Starts a Ralph loop that autonomously continues working until all tasks in the goal are complete or max iterations reached.
+
+## Usage
+```
+/OMG:ralph-start [goal description]
+```
+
+## How it Works
+1. Ask the user for a goal description if not provided
+2. Create `.omg/state/ralph-loop.json` with:
+   - `active: true`
+   - `iteration: 0`
+   - `max_iterations: 50`
+   - `original_prompt: [goal]`
+   - `started_at: [ISO8601 timestamp]`
+   - `checklist_path: ".omg/state/_checklist.md"` (if exists)
+3. Confirm: "Ralph loop started. Will continue working on: [goal]"
+
+## State File Format
+```json
+{
+  "active": true,
+  "iteration": 0,
+  "max_iterations": 50,
+  "original_prompt": "fix all failing tests",
+  "started_at": "2026-02-28T10:00:00Z",
+  "checklist_path": ".omg/state/_checklist.md"
+}
+```
+
+## Stop Condition
+- Reaches max_iterations (50 by default)
+- User runs `/OMG:ralph-stop`
+- User deletes `.omg/state/ralph-loop.json`

package/commands/OMG:ralph-stop.md

@@ -0,0 +1,23 @@
+---
+description: "Stop Ralph autonomous loop — deactivates the state file."
+allowed-tools: Read, Write, Edit, Bash
+argument-hint: ""
+---
+
+# /OMG:ralph-stop — Stop Ralph Autonomous Loop
+
+## Purpose
+Stops an active Ralph loop by deactivating the state file.
+
+## Usage
+```
+/OMG:ralph-stop
+```
+
+## How it Works
+1. Read `.omg/state/ralph-loop.json`
+2. Set `active: false` in the state file (preserve iteration count for review)
+3. Report: "Ralph loop stopped after N iterations. Gomg was: [original_prompt]"
+
+## If No Active Loop
+Report: "No active Ralph loop found. Nothing to stop."

package/commands/OMG:teams.md

@@ -0,0 +1,39 @@
+---
+description: OMG internal team routing (standalone). Replaces /omc-teams dependency.
+allowed-tools: Read, Grep, Glob, Bash(git:*), Bash(rg:*), Bash(find:*), Bash(cat:*), Bash(python3:*)
+argument-hint: "[codex|gemini|ccg|auto] 'problem statement'"
+---
+
+# /OMG:teams — Standalone Internal Router
+
+Use OMG's internal router without requiring OMC.
+
+## Input contract
+- target: `auto|codex|gemini|ccg`
+- problem: clear issue statement
+- context: optional constraints
+- files: optional focus paths
+- expected_outcome: optional acceptance target
+
+## Execution
+Use internal CLI router:
+
+```bash
+OMG_CLI="${OMG_CLI_PATH:-$HOME/.claude/omg-runtime/scripts/omg.py}"
+if [ ! -f "$OMG_CLI" ] && [ -f "scripts/omg.py" ]; then OMG_CLI="scripts/omg.py"; fi
+python3 "$OMG_CLI" teams --target auto --problem "[problem]"
+```
+
+For explicit target:
+
+```bash
+python3 "$OMG_CLI" teams --target codex --problem "[problem]"
+```
+
+## Output schema
+`TeamDispatchResult { status, findings[], actions[], evidence{} }`
+
+## Full-power sub-agent protocol
+- For non-trivial tasks, launch multiple sub-agents in parallel (`run_in_background=true`) for independent tracks.
+- Collect all task outputs before responding (`background_output` per task id).
+- Run a `sequential-thinking` merge step to produce one dependency-ordered execution plan.

package/commands/ai-commit.md

@@ -0,0 +1,113 @@
+---
+description: "Analyze uncommitted git changes and propose logical atomic commits grouped by concern."
+allowed-tools: Read, Bash(python*:*), Grep, Glob
+argument-hint: "[optional: working directory path]"
+---
+
+# /OMG:ai-commit — AI Commit Splitter
+
+Analyze uncommitted git changes and propose logical atomic commits grouped by concern.
+
+## Usage
+
+```
+/OMG:ai-commit
+```
+
+## What It Does
+
+1. Reads hunk-level git diffs via `git_hunk()` from `tools/git_inspector.py`
+2. Groups hunks by file type/category (python, javascript, config, docs, tests, etc.)
+3. Separates test files from source code automatically
+4. Generates conventional commit messages: `{type}({scope}): {description}`
+5. Displays a human-readable preview of proposed commits
+
+## Feature Flag
+
+- **Flag name**: `OMG_AI_COMMIT_ENABLED`
+- **Default**: `False` (disabled)
+- **Enable**: `export OMG_AI_COMMIT_ENABLED=1`
+
+Or set in `settings.json`:
+
+```json
+{
+  "_omg": {
+    "features": {
+      "ai_commit": true
+    }
+  }
+}
+```
+
+## Output Example
+
+```
+============================================================
+  OMG AI Commit Splitter — Proposed Commit Plan
+============================================================
+
+  Total proposed commits: 3
+
+  Commit 1: feat(tools): update commit_splitter.py
+  ──────────────────────────────────────────────────
+    • tools/commit_splitter.py
+    (2 hunks)
+
+  Commit 2: test(tests): update 2 test files
+  ──────────────────────────────────────────────────
+    • tests/tools/test_commit_splitter.py
+    • tests/tools/test_git_inspector.py
+    (4 hunks)
+
+  Commit 3: docs(commands): update ai-commit.md
+  ──────────────────────────────────────────────────
+    • commands/ai-commit.md
+    (1 hunk)
+
+============================================================
+  NOTE: This is a preview only. No commits were made.
+============================================================
+```
+
+## Commit Type Mapping
+
+| Category   | Default Type | Description              |
+|------------|-------------|--------------------------|
+| python     | `feat`      | Python source files      |
+| javascript | `feat`      | JS/TS source files       |
+| tests      | `test`      | Test files (any language) |
+| docs       | `docs`      | Documentation files      |
+| config     | `chore`     | Configuration files      |
+| shell      | `chore`     | Shell scripts            |
+| styles     | `style`     | CSS/SCSS/LESS files      |
+| markup     | `feat`      | HTML/XML/SVG files       |
+| other      | `chore`     | Unclassified files       |
+
+## CLI Usage
+
+```bash
+# Preview commit plan from terminal
+python3 tools/commit_splitter.py --dry-run
+```
+
+## Safety
+
+- **Read-only**: Never executes `git commit` or modifies the working tree
+- **Feature-gated**: Returns empty results when disabled
+- **Non-destructive**: Safe to run at any time
+
+## API
+
+```python
+from tools.commit_splitter import analyze_changes, generate_commit_plan, preview_commit_plan
+
+# Get grouped hunks
+groups = analyze_changes(cwd=".")
+
+# Get full commit plan with messages
+plan = generate_commit_plan(cwd=".")
+
+# Get human-readable preview string
+preview = preview_commit_plan(cwd=".")
+```

package/commands/ccg.md

@@ -0,0 +1,9 @@
+---
+description: Compatibility alias for /OMG:ccg. Use /OMG:ccg instead.
+---
+
+# /ccg — Compatibility Alias
+
+> **Compatibility alias** — This command is a legacy alias. Use `/OMG:ccg` instead.
+
+Redirects to `/OMG:ccg` for tri-track synthesis in standalone mode.

package/commands/create-agent.md

@@ -0,0 +1,183 @@
+---
+description: "Wizard command for creating new custom agents in ~/.omg/agents/ or .omg/agents/."
+allowed-tools: Read, Write, Edit, Bash
+argument-hint: "[agent-name]"
+---
+
+# /OMG:create-agent — Custom Agent Creation Wizard
+
+Create a custom agent for your project or user-level configuration.
+
+## Prerequisites
+
+Enable the custom agents feature:
+
+```bash
+export OMG_CUSTOM_AGENTS_ENABLED=1
+```
+
+Or add to your project's `settings.json`:
+
+```json
+{
+  "_omg": {
+    "features": {
+      "CUSTOM_AGENTS": true
+    }
+  }
+}
+```
+
+## Agent Locations
+
+- **User-level**: `~/.omg/agents/<name>.md` — available in all projects
+- **Project-level**: `.omg/agents/<name>.md` — available in this project only
+
+Project-level agents override user-level agents with the same name.
+
+## Quick Start
+
+1. Create the agents directory:
+
+```bash
+# For project-level agents:
+mkdir -p .omg/agents
+
+# For user-level agents:
+mkdir -p ~/.omg/agents
+```
+
+2. Create your agent file (e.g., `.omg/agents/my-agent.md`):
+
+```markdown
+---
+name: my-agent
+description: Brief description of what this agent does
+model: claude-sonnet-4-5
+tools: Read, Grep, Glob, Edit, Write
+bundled: false
+---
+
+# Agent: My Agent
+
+## Role
+
+Describe the agent's primary role and responsibilities here.
+This should be a clear, concise statement of what the agent does.
+
+## Model
+
+`default` (claude-sonnet-4-5) — general-purpose model for this agent.
+
+Available roles: `smol` (haiku, fast), `default` (sonnet), `slow` (opus, deep reasoning).
+
+## Capabilities
+
+- List specific capabilities here
+- What tools does this agent use?
+- What domains does it specialize in?
+
+## Instructions
+
+Detailed behavioral instructions for the agent.
+
+**Core rules:**
+- Rule 1
+- Rule 2
+- Rule 3
+
+**Strategy:**
+1. Step 1
+2. Step 2
+3. Step 3
+
+## Example Prompts
+
+- "Example prompt 1"
+- "Example prompt 2"
+- "Example prompt 3"
+```
+
+## Required Sections
+
+Your agent **must** include these sections to pass validation:
+
+| Section | Required | Description |
+|---------|----------|-------------|
+| `# Agent: <name>` | ✅ Yes | Agent header with name |
+| `## Role` | ✅ Yes | Primary role description |
+| `## Model` | Optional | Model preference (smol/default/slow) |
+| `## Capabilities` | Optional | List of capabilities |
+| `## Instructions` | Optional | Behavioral instructions |
+
+## Validation
+
+Custom agents are validated on load. Invalid agents (missing required sections) are skipped with warnings.
+
+To verify your agent is valid:
+
+```bash
+export OMG_CUSTOM_AGENTS_ENABLED=1
+python3 -c "
+from runtime.custom_agent_loader import load_custom_agents
+agents = load_custom_agents('.')
+for a in agents:
+    status = '✅' if a['validated'] else '❌'
+    print(f\"{status} {a['name']} ({a['level']}) — {a['description'][:60]}\")
+    if a.get('issues'):
+        for issue in a['issues']:
+            print(f\"   ⚠️  {issue}\")
+"
+```
+
+## Examples
+
+### Minimal Valid Agent
+
+```markdown
+# Agent: Greeter
+
+## Role
+
+Simple greeting agent that welcomes users.
+```
+
+### Full Agent with All Sections
+
+See the template in Quick Start above.
+
+### Specialized Domain Agent
+
+```markdown
+# Agent: Data Pipeline
+
+## Role
+
+ETL pipeline specialist. Designs and optimizes data transformation workflows.
+
+## Model
+
+`slow` (claude-opus-4-5) — deep reasoning for complex pipeline design.
+
+## Capabilities
+
+- Design ETL pipelines with error handling and retry logic
+- Optimize SQL queries for large datasets
+- Schema migration planning
+- Data quality validation rules
+
+## Instructions
+
+You are a data engineering specialist.
+
+**Core rules:**
+- Always consider idempotency in pipeline design
+- Prefer incremental processing over full reloads
+- Include monitoring and alerting in every pipeline
+
+**Strategy:**
+1. Understand the data sources and sinks
+2. Design the transformation logic
+3. Add error handling and retry mechanisms
+4. Plan for monitoring and observability
+```

package/commands/omc-teams.md

@@ -0,0 +1,9 @@
+---
+description: Compatibility alias for /OMG:teams. Use /OMG:teams instead.
+---
+
+# /omc-teams — Compatibility Alias
+
+> **Compatibility alias** — This command is a legacy alias. Use `/OMG:teams` instead.
+
+Redirects to `/OMG:teams` for internal team routing in standalone mode.

package/commands/session-branch.md

@@ -0,0 +1,85 @@
+---
+description: "Create or manage OMG state branches for experimental workflows."
+allowed-tools: Read, Write, Edit, Bash
+argument-hint: "--name <branch-name> [--from <snapshot_id>]"
+---
+
+# /OMG:branch — Branch OMG State
+
+Create a named branch of the current OMG state for experimentation or parallel exploration.
+
+## Important
+
+Branching is **OMG state only** — it captures and restores `.omg/state/` directory contents. It does **not** fork the conversation, context window, or Claude session. Think of it as a checkpoint you can name and switch between.
+
+## Usage
+
+```
+/OMG:branch --name "experiment"
+/OMG:branch --name "refactor-v2" --from 20260302_143000_baseline
+```
+
+## What It Does
+
+1. Creates a snapshot of the current `.omg/state/` directory (or restores a specified snapshot)
+2. Writes branch metadata to `.omg/state/branches/<name>.json`
+3. Updates `.omg/state/current_branch.json` to track the active branch
+
+## Branch Metadata
+
+Each branch stores:
+
+| Field | Description |
+|-------|-------------|
+| `name` | Branch name |
+| `snapshot_id` | Associated snapshot ID |
+| `created_at` | ISO timestamp of creation |
+| `parent_branch` | Branch that was active when this branch was created |
+| `status` | Branch status (`active`) |
+
+## Managing Branches
+
+```
+# List all branches
+python3 tools/session_snapshot.py branches
+
+# Switch to a branch (restores its snapshot)
+python3 tools/session_snapshot.py switch experiment
+
+# Create branch from specific snapshot
+python3 tools/session_snapshot.py branch my-branch --from 20260302_143000_baseline
+```
+
+## Feature Flag
+
+Branching is gated behind `OMG_BRANCHING_ENABLED` (default: `False`).
+
+Enable via environment variable:
+```bash
+export OMG_BRANCHING_ENABLED=true
+```
+
+Or in `settings.json`:
+```json
+{
+  "_omg": {
+    "features": {
+      "BRANCHING": true
+    }
+  }
+}
+```
+
+## Example Workflow
+
+```
+# 1. Create a baseline branch
+/OMG:branch --name "baseline"
+
+# 2. Do some experimental work...
+# 3. Create experiment branch to save progress
+/OMG:branch --name "experiment-auth"
+
+# 4. Switch back to baseline if experiment didn't work
+python3 tools/session_snapshot.py switch baseline
+```