@trac3er/oh-my-god 2.0.0 → 2.0.2

package/README.md

@@ -1,85 +1,106 @@
-# OMG v2 Bun Runtime
+# OMG 2.0.2
 
-OMG `v2.0.0` runs on Bun + TypeScript. The public product surface stays stable:
+[![Compat Gate](https://github.com/trac3er00/OMG/actions/workflows/omg-compat-gate.yml/badge.svg)](https://github.com/trac3er00/OMG/actions/workflows/omg-compat-gate.yml)
+[![npm version](https://img.shields.io/npm/v/%40trac3er%2Foh-my-god)](https://www.npmjs.com/package/@trac3er/oh-my-god)
+[![License](https://img.shields.io/github/license/trac3er00/OMG)](LICENSE)
 
-- `omg` remains the CLI entrypoint
-- Claude hooks still write to `.omg/`
-- standalone install, plugin install, update, and uninstall still go through `OMG-setup.sh`
-- team routing, compat, provider status, and release readiness keep the same subcommands
+OMG upgrades your agent host instead of replacing it. It gives Claude Code, Codex, OpenCode, and other supported CLIs a tighter setup flow, stronger orchestration, native adoption from older plugin stacks, and proof-backed verification.
 
-## Requirements
+- Brand: `OMG`
+- Repo: `https://github.com/trac3er00/OMG`
+- npm: `@trac3er/oh-my-god`
+- Plugin id: `omg`
+- Marketplace id: `omg`
+- Version: `2.0.2`
 
-- Bun `>= 1.3`
-- Claude Code or a compatible `~/.claude` config
-- optional provider CLIs for multi-provider routing: `codex`, `gemini`, `kimi`
+## Why OMG
 
-## Install
+- Small front door: install, run `/OMG:setup`, then `/OMG:crazy <goal>`.
+- Multi-host support: Claude Code, Codex, OpenCode, Gemini CLI, and Kimi CLI.
+- Native adoption: setup detects OMC, OMX, and Superpowers-style environments without exposing copycat public migration commands.
+- Proof-first delivery: verification, provider coverage, HUD artifacts, and transcripts are published instead of implied.
+
+![OMG HUD](docs/assets/omg-hud.svg)
+
+## Quickstart
+
+Install with npm:
 
 ```bash
-bun install
-./OMG-setup.sh install
+npm install @trac3er/oh-my-god
 ```
 
-Plugin bundle mode:
+Or clone and run the setup manager:
 
 ```bash
-./OMG-setup.sh install --install-as-plugin
+git clone https://github.com/trac3er00/OMG
+cd OMG
+chmod +x OMG-setup.sh
+./OMG-setup.sh install --mode=omg-only --preset=balanced
 ```
 
-Upgrade or remove:
+Then run:
 
-```bash
-./OMG-setup.sh update
-./OMG-setup.sh uninstall
+```text
+/OMG:setup
+/OMG:crazy stabilize auth and dashboard flows
 ```
 
-## CLI
+Success looks like:
 
-Local source execution:
+- supported hosts are detected
+- `.mcp.json` is configured
+- `.omg/state/adoption-report.json` is written when another ecosystem is present
+- OMG reports the selected preset and next step
 
-```bash
-bun scripts/omg.ts teams --target auto --problem "debug auth regression"
-bun scripts/omg.ts ccg --problem "refactor dashboard + API contract"
-bun scripts/omg.ts compat list
-bun scripts/omg.ts providers status
-bun scripts/omg.ts release readiness
-```
+## Install Guides
 
-When installed from npm, the package exposes the same surface as:
+- Claude Code: [docs/install/claude-code.md](docs/install/claude-code.md)
+- Codex: [docs/install/codex.md](docs/install/codex.md)
+- OpenCode: [docs/install/opencode.md](docs/install/opencode.md)
 
-```bash
-omg teams --target auto --problem "debug auth regression"
-```
+## Native Adoption
 
-## Runtime Layout
+OMG uses native setup language instead of public migration commands.
 
-- `scripts/omg.ts`: Bun CLI
-- `hooks/*.ts`: Claude hook entrypoints
-- `runtime/*.ts`: routing, compat, provider, and release helpers
-- `control_plane/*.ts`: local JSON control-plane API
-- `lab/*.ts`: Bun pipeline policy and evaluation flow
-- `registry/verify_artifact.ts`: supply-artifact verification
-- `omg_natives/index.ts`: Bun-native helper surface
-- `tools/*.ts`: Bun support utilities used by commands and tests
+- `OMG-only`: recommended. OMG becomes the primary hooks, HUD, MCP, and orchestration layer.
+- `coexist`: advanced. OMG preserves non-conflicting third-party surfaces and records overlap instead of overwriting it.
+- Presets: `safe`, `balanced`, `interop`, `labs`.
 
-Stable `settings.json` only registers hooks that perform work at runtime: session start/end capture, the Bash circuit breaker, tool ledger, post-tool-failure, and stop dispatch.
+Compatibility references to OMC, OMX, and Superpowers are documented here: [docs/migration/native-adoption.md](docs/migration/native-adoption.md)
 
-## Verification
+## Proof
 
-```bash
-bun run typecheck
-bun test
-bun run check:runtime-clean
-```
+Current local verification for this release: `2452 passed, 2 skipped` on March 6, 2026.
 
-Control plane:
+- Verification and provider matrix: [docs/proof.md](docs/proof.md)
+- Sample setup transcript: [docs/transcripts/setup.md](docs/transcripts/setup.md)
+- Sample crazy transcript: [docs/transcripts/crazy.md](docs/transcripts/crazy.md)
+- Release process: [docs/release-checklist.md](docs/release-checklist.md)
 
-```bash
-bun control_plane/server.ts --port 8787
-```
+## Command Surface
+
+Primary entry points:
+
+- `/OMG:setup`
+- `/OMG:crazy`
+
+Advanced surfaces stay available for deeper workflows:
+
+- `/OMG:teams`
+- `/OMG:ccg`
+- `/OMG:compat`
+- `/OMG:ship`
+- `/OMG:security-review`
+
+## Contributing
+
+Public contributions are welcome.
+
+- Contribution guide: [CONTRIBUTING.md](CONTRIBUTING.md)
+- Security reporting: [SECURITY.md](SECURITY.md)
+- Changelog: [CHANGELOG.md](CHANGELOG.md)
 
-## Release Notes
+## Positioning
 
-- prerelease tags matching `v*-beta.*` publish to npm with the `beta` dist-tag
-- stable tags continue to publish on `latest`
-- the repo includes a legacy-runtime cleanliness gate that fails if retired runtime files or stale command references return
+OMG is a plugin and orchestration layer for supported CLIs. It is not a base-model training project. The goal is to make frontier agent hosts tighter, safer, more interoperable, and more verifiable than the default experience.

package/SECURITY.md

@@ -0,0 +1,25 @@
+# Security Policy
+
+## Reporting a Vulnerability
+
+Please use GitHub's private vulnerability reporting for this repository if it is enabled.
+
+If private reporting is not available, do not open a public issue with exploit details. Open a minimal issue asking for a private contact path through the maintainer's GitHub profile instead.
+
+Include:
+
+- affected version
+- impact
+- reproduction steps
+- proof of concept if safe to share privately
+- suggested mitigation if known
+
+## Response Expectations
+
+- We will triage reports before public discussion.
+- We may ask for additional reproduction details.
+- Coordinated disclosure is preferred over immediate public disclosure.
+
+## Supported Versions
+
+Security fixes are prioritized for the latest released version.

package/agents/__init__.py

@@ -0,0 +1 @@
+"""OMG agents module."""

package/agents/model_roles.py

@@ -0,0 +1,196 @@
+#!/usr/bin/env python3
+"""Model roles loader — defines role configurations for model selection.
+
+Loads role definitions from _model_roles.yaml and provides utilities for
+role-based model selection, CLI argument parsing, and feature flag control.
+"""
+import os
+import sys
+from pathlib import Path
+from typing import Optional
+
+# Try to import yaml; fall back to json if not available
+try:
+    import yaml
+    HAS_YAML = True
+except ImportError:
+    HAS_YAML = False
+    import json
+
+# Add parent directory to path for importing from hooks
+_AGENTS_DIR = Path(__file__).parent
+_HOOKS_DIR = _AGENTS_DIR.parent / "hooks"
+if str(_HOOKS_DIR) not in sys.path:
+    sys.path.insert(0, str(_HOOKS_DIR))
+
+try:
+    from _common import get_feature_flag, get_project_dir
+except ImportError:
+    # Fallback if _common is not available
+    def get_feature_flag(flag_name, default=True):
+        env_key = f"OMG_{flag_name.upper()}_ENABLED"
+        env_val = os.environ.get(env_key, "").lower()
+        if env_val in ("0", "false", "no"):
+            return False
+        if env_val in ("1", "true", "yes"):
+            return True
+        return default
+
+    def get_project_dir():
+        return os.environ.get("CLAUDE_PROJECT_DIR", os.getcwd())
+
+
+# Global roles dictionary
+ROLES: dict = {}
+
+
+def _load_roles() -> dict:
+    """Load role definitions from _model_roles.yaml.
+    
+    Returns:
+        Dictionary mapping role names to role configurations.
+        Falls back to default roles if YAML cannot be loaded.
+    """
+    roles_file = _AGENTS_DIR / "_model_roles.yaml"
+    
+    if not roles_file.exists():
+        return _get_default_roles()
+    
+    try:
+        if HAS_YAML:
+            with open(roles_file, "r") as f:
+                data = yaml.safe_load(f)
+                if data and "roles" in data:
+                    return data["roles"]
+    except Exception as e:
+        print(f"[OMG] Warning: Failed to load roles from {roles_file}: {e}", file=sys.stderr)
+
+    
+    return _get_default_roles()
+
+
+def _get_default_roles() -> dict:
+    """Return hardcoded default roles if YAML cannot be loaded."""
+    return {
+        "default": {
+            "model": "claude-opus-4-5",
+            "temperature": 1.0,
+            "max_tokens": 8192,
+            "description": "Default balanced model for general tasks"
+        },
+        "smol": {
+            "model": "claude-haiku-4-5",
+            "temperature": 0.7,
+            "max_tokens": 4096,
+            "description": "Fast cheap model for simple/trivial tasks"
+        },
+        "slow": {
+            "model": "claude-opus-4-5",
+            "temperature": 0.5,
+            "max_tokens": 16384,
+            "description": "Careful deliberate model for complex reasoning"
+        },
+        "plan": {
+            "model": "claude-sonnet-4-5",
+            "temperature": 0.8,
+            "max_tokens": 8192,
+            "description": "Planning and architecture model"
+        },
+        "commit": {
+            "model": "claude-haiku-4-5",
+            "temperature": 0.3,
+            "max_tokens": 2048,
+            "description": "Concise model for git commits and short summaries"
+        }
+    }
+
+
+def get_role(name: str) -> dict:
+    """Get role configuration by name.
+    
+    Args:
+        name: Role name (e.g., 'smol', 'slow', 'plan', 'commit', 'default')
+    
+    Returns:
+        Role configuration dictionary. Returns 'default' role if name not found.
+    """
+    if not ROLES:
+        _init_roles()
+    
+    return ROLES.get(name, ROLES.get("default", {}))
+
+
+def list_roles() -> list[str]:
+    """Get list of all available role names.
+    
+    Returns:
+        List of role names in order they appear in configuration.
+    """
+    if not ROLES:
+        _init_roles()
+    
+    return list(ROLES.keys())
+
+
+def parse_role_args(argv: list[str]) -> Optional[str]:
+    """Parse command-line arguments to detect role selection.
+    
+    Detects: --smol, --slow, --plan, --commit
+    
+    Args:
+        argv: Command-line arguments (typically sys.argv[1:])
+    
+    Returns:
+        Role name if detected, None otherwise.
+    """
+    role_map = {
+        "--smol": "smol",
+        "--slow": "slow",
+        "--plan": "plan",
+        "--commit": "commit",
+    }
+    
+    for arg in argv:
+        if arg in role_map:
+            return role_map[arg]
+    
+    return None
+
+
+def _init_roles() -> None:
+    """Initialize the global ROLES dictionary."""
+    global ROLES
+    ROLES = _load_roles()
+
+
+# Initialize on module import
+_init_roles()
+
+
+if __name__ == "__main__":
+    # CLI for testing/inspection
+    import json as json_module
+    
+    if len(sys.argv) > 1:
+        if sys.argv[1] == "list":
+            print("Available roles:")
+            for role_name in list_roles():
+                print(f"  - {role_name}")
+        elif sys.argv[1] == "get":
+            if len(sys.argv) > 2:
+                role_name = sys.argv[2]
+                role = get_role(role_name)
+                print(json_module.dumps(role, indent=2))
+            else:
+                print("Usage: python3 model_roles.py get <role_name>")
+        elif sys.argv[1] == "parse":
+            detected = parse_role_args(sys.argv[2:])
+            if detected:
+                print(f"Detected role: {detected}")
+            else:
+                print("No role detected")
+        else:
+            print("Usage: python3 model_roles.py [list|get <role>|parse <args...>]")
+    else:
+        # Default: print all roles
+        print(json_module.dumps(ROLES, indent=2))

package/agents/omg-architect-mode.md

@@ -17,11 +17,9 @@ Architect mode cognitive agent. Designs system architecture, models domains, cre
 
 ## MCP Tools Available
 
-- `mcp_lsp_symbols`: Map out module structure and exported interfaces
-- `mcp_lsp_find_references`: Trace dependencies between modules
-- `mcp_ast_grep_search`: Find architectural patterns (dependency injection, event handlers)
-- `mcp_grep`: Find cross-cutting concerns (logging, error handling, auth checks)
-- `mcp_filesystem_directory_tree`: Visualize project structure
+- `filesystem`: Visualize project structure and inspect cross-module boundaries
+- `context7`: Check official guidance for architectural patterns or framework constraints
+- `websearch`: Validate trade-offs against current ecosystem practice when needed
 
 ## Constraints
 

package/agents/omg-backend-engineer.md

@@ -17,11 +17,9 @@ Backend engineering specialist. Handles all server-side tasks: API routes, middl
 
 ## MCP Tools Available
 
-- `mcp_lsp_goto_definition`: Trace function calls through the codebase
-- `mcp_lsp_find_references`: Find all usages of an API endpoint or function
-- `mcp_lsp_diagnostics`: Check for type errors before running build
-- `mcp_ast_grep_search`: Find patterns like unhandled promises or missing error handling
-- `mcp_context7_query-docs`: Look up framework-specific API documentation
+- `context7`: Look up framework-specific API and runtime documentation
+- `filesystem`: Inspect handlers, configs, and local artifacts tied to the request path
+- `websearch`: Verify current integration guidance when third-party behavior may have changed
 
 ## Constraints
 

package/agents/omg-database-engineer.md

@@ -17,11 +17,9 @@ Database engineering specialist. Handles schema design, migrations, query optimi
 
 ## MCP Tools Available
 
-- `mcp_bash`: Run migrations, psql/mysql commands, knex/prisma/drizzle CLI
-- `mcp_grep`: Find all queries touching a specific table or column
-- `mcp_ast_grep_search`: Find raw SQL patterns, N+1 query indicators
-- `mcp_lsp_goto_definition`: Trace ORM model relationships
-- `mcp_lsp_find_references`: Find all code paths that query a table
+- `filesystem`: Inspect migrations, schema files, and query call sites across the workspace
+- `context7`: Look up ORM and database engine documentation
+- `websearch`: Check current migration or performance guidance when local docs are insufficient
 
 ## Constraints
 

package/agents/omg-frontend-designer.md

@@ -17,11 +17,10 @@ Frontend design specialist. Handles all UI/UX tasks: component design, responsiv
 
 ## MCP Tools Available
 
-- `mcp_puppeteer_puppeteer_screenshot`: Verify visual output after changes
-- `mcp_puppeteer_puppeteer_navigate`: Preview pages in browser
-- `mcp_lsp_diagnostics`: Check for TypeScript/CSS errors
-- `mcp_ast_grep_search`: Find component patterns across codebase
-- `mcp_grep_app_searchGitHub`: Find real-world UI implementation examples
+- `chrome-devtools`: Preview pages, inspect layout issues, and validate responsive behavior in a real browser
+- `filesystem`: Review component files, generated assets, and local screenshots without leaving the workspace
+- `context7`: Look up framework and component-library documentation when implementation details are unclear
+- `websearch`: Check current UI patterns or browser-specific behavior when local context is insufficient
 
 ## Constraints
 

package/agents/omg-implement-mode.md

@@ -19,11 +19,10 @@ Implementation mode cognitive agent. Executes approved plans by coordinating dom
 
 ## MCP Tools Available
 
-- `mcp_bash`: Run cross-module builds, integration tests, linters
-- `mcp_lsp_diagnostics`: Check for errors across all changed files
-- `mcp_grep`: Verify changes propagated correctly across modules
-- `mcp_ast_grep_search`: Ensure patterns are consistent after refactoring
-- `mcp_lsp_find_references`: Verify no broken references after changes
+- `filesystem`: Inspect changed files and generated artifacts across modules
+- `context7`: Pull official docs when implementation details depend on library behavior
+- `websearch`: Verify current ecosystem guidance when local docs are incomplete
+- `chrome-devtools`: Validate browser-visible behavior when a change spans UI and backend flows
 
 ## Constraints
 

package/agents/omg-infra-engineer.md

@@ -17,11 +17,9 @@ Infrastructure engineering specialist. Handles deployment pipelines, Docker/cont
 
 ## MCP Tools Available
 
-- `mcp_bash`: Run `docker`, `terraform`, `kubectl`, `aws/gcloud/az` CLI, CI tools
-- `mcp_grep`: Find configuration patterns, environment variable usage
-- `mcp_ast_grep_search`: Find hardcoded URLs, ports, or environment-specific values
-- `mcp_context7_query-docs`: Look up cloud provider and tool documentation
-- `mcp_lsp_diagnostics`: Validate YAML/JSON configuration files
+- `context7`: Look up infrastructure tool and cloud-provider documentation
+- `websearch`: Check current operational guidance, release notes, and platform caveats
+- `filesystem`: Inspect configuration files, manifests, and deployment artifacts in the workspace
 
 ## Constraints
 

package/agents/omg-research-mode.md

@@ -17,12 +17,10 @@ Research mode cognitive agent. Gathers information, evaluates technologies, anal
 
 ## MCP Tools Available
 
-- `mcp_google_search`: Search for current library versions, comparisons, benchmarks
-- `mcp_websearch_web_search_exa`: Deep web search for technical articles and guides
-- `mcp_chrome-devtools`: Validate web_search findings against live browser pages when needed
-- `mcp_context7_query-docs`: Query official documentation for specific libraries
-- `mcp_context7_resolve-library-id`: Find correct library IDs for documentation queries
-- `mcp_grep_app_searchGitHub`: Find real-world usage examples on GitHub
+- `websearch`: Search for current library versions, comparisons, benchmarks, and implementation guidance
+- `context7`: Query official documentation for specific libraries and APIs
+- `chrome-devtools`: Validate web findings against live browser behavior when needed
+- `filesystem`: Cross-check local project context against external research before recommending a path
 
 ## Constraints
 

package/agents/omg-security-auditor.md

@@ -17,11 +17,9 @@ Security auditor. Reviews code for vulnerabilities, enforces security best pract
 
 ## MCP Tools Available
 
-- `mcp_grep`: Scan for secret patterns (API keys, tokens, passwords)
-- `mcp_ast_grep_search`: Find unsafe code patterns (eval, innerHTML, SQL concat)
-- `mcp_lsp_find_references`: Trace data flow from user input to sensitive operations
-- `mcp_bash`: Run `npm audit`, `semgrep`, dependency checks
-- `mcp_context7_query-docs`: Look up security guidance for specific frameworks
+- `context7`: Look up framework-specific security guidance and hardening recommendations
+- `websearch`: Check current advisories, CVEs, and secure deployment guidance
+- `filesystem`: Inspect local config and artifacts involved in the audit path
 
 ## Constraints
 

package/agents/omg-testing-engineer.md

@@ -17,11 +17,9 @@ Testing engineering specialist. Designs test strategies, writes comprehensive te
 
 ## MCP Tools Available
 
-- `mcp_bash`: Run `bun test`, `jest`, `playwright`, coverage tools
-- `mcp_grep`: Find untested functions, uncovered branches
-- `mcp_ast_grep_search`: Find patterns like functions without corresponding test files
-- `mcp_lsp_find_references`: Trace all call sites to determine test scope
-- `mcp_lsp_diagnostics`: Verify test file type-correctness
+- `chrome-devtools`: Validate UI and end-to-end flows in a real browser when tests touch frontend behavior
+- `filesystem`: Inspect fixtures, snapshots, and generated test artifacts
+- `context7`: Look up testing-framework docs and current best practices
 
 ## Constraints