@trac3er/oh-my-god 1.0.2

package/README.md

@@ -0,0 +1,335 @@
+# OAL v1.0.2
+
+OAL (Orchestration Abstraction Layer) is a standalone orchestration layer for Claude Code.
+It adds structured multi-agent workflows, intelligent model routing (Claude/Codex/Gemini), and durable session state for long-running engineering tasks.
+
+- Version: `v1.0.2`
+- Maintainer: `trac3er00`
+- Repo: `git@github.com:trac3er00/OAL.git`
+- Release: `https://github.com/trac3er00/OAL/releases/tag/v1.0.2`
+
+## What OAL Solves
+
+OAL is built for teams and solo developers who want:
+
+- Reliable execution loops (explore -> decide -> implement -> verify)
+- Strong verification discipline (no unverified completion claims)
+- Better model delegation for backend, frontend, security, and architecture tasks
+- Session continuity across long refactors and multi-day work
+
+## Core Capabilities
+
+- Multi-agent orchestration with role-specific agents
+- Dynamic routing to Codex and Gemini for domain-specific tasks
+- Failure tracking and escalation after repeated unsuccessful attempts
+- Command surface for planning, review, security, handoff, and execution modes
+- Context minimization and selective knowledge injection to reduce prompt noise
+
+## At a Glance
+
+- Hooks: 27 Python hooks
+- Core rules: 5
+- Contextual rules: 17
+- Agents: 15
+- Commands: 10 core + 10 advanced (+ compatibility aliases)
+
+## Requirements
+
+- Python `3.8+`
+- Claude Code with write access to `~/.claude`
+
+## Installation
+
+### Standard install
+
+```bash
+chmod +x OAL-setup.sh
+./OAL-setup.sh install
+```
+
+### Plugin-oriented install (recommended)
+
+```bash
+./OAL-setup.sh install --install-as-plugin
+```
+
+### Update
+
+```bash
+./OAL-setup.sh update
+```
+
+### Uninstall
+
+```bash
+./OAL-setup.sh uninstall
+```
+
+### Common flags
+
+Supported by `OAL-setup.sh`:
+
+- `--fresh` clean reinstall before install/update
+- `--symlink` development mode with live updates from repo source
+- `--install-as-plugin` install plugin bundle (plugin manifest + MCP + HUD)
+- `--dry-run` preview changes without writing files
+- `--non-interactive` skip prompts (CI/automation)
+- `--merge-policy=ask|apply|skip` control settings merge behavior
+
+## Plugin Update Behavior
+
+If OAL is installed through Claude Code plugin flow (`/plugin`), update works like this:
+
+- Claude plugin update triggers `.claude-plugin/scripts/update.sh`
+- In git-backed installs, update stashes local changes (if needed) and pulls from `origin/main`
+- When a git tag is available, plugin manifests are synced to the tagged version
+- In cache/copy installs, update delegates to `OAL-setup.sh update`
+
+If plugin update appears silent, check:
+
+- `~/.claude/plugins/known_marketplaces.json` has git source for `oh-advanced-layer`
+- `~/.claude/plugins/cache/oh-advanced-layer/oal/<version>/.claude-plugin/plugin.json` is valid schema
+- update script exists and is executable
+
+## Quick Start in Claude Code
+
+After install, from your target project directory:
+
+```text
+/OAL:init
+/OAL:health-check
+```
+
+Common flows:
+
+```text
+/OAL:mode implement
+/OAL:escalate codex "debug auth middleware"
+/OAL:crazy fix flaky tests in payment module
+/OAL:handoff
+```
+
+## Command Groups
+
+### Core commands
+
+- `/OAL:init`
+- `/OAL:project-init`
+- `/OAL:domain-init`
+- `/OAL:health-check`
+- `/OAL:mode`
+- `/OAL:escalate`
+- `/OAL:teams`
+- `/OAL:ccg`
+- `/OAL:crazy`
+- `/OAL:compat`
+
+### Advanced commands
+
+- `/OAL:deep-plan`
+- `/OAL:learn`
+- `/OAL:code-review`
+- `/OAL:security-review`
+- `/OAL:ship`
+- `/OAL:maintainer`
+- `/OAL:handoff`
+- `/OAL:sequential-thinking`
+- `/OAL:ralph-start`
+- `/OAL:ralph-stop`
+- `/OAL:theme`
+
+## Agent Routing Model
+
+OAL dispatches by domain intent:
+
+- Codex path: backend logic, debugging, algorithms, security-sensitive implementation
+- Gemini path: UI/UX, layout, visual refinements, accessibility-oriented frontend work
+- Claude path: orchestration, synthesis, review loops, and fallback execution
+
+## Cognitive Modes
+
+Set an explicit operating mode per session:
+
+```text
+/OAL:mode research
+/OAL:mode architect
+/OAL:mode implement
+/OAL:mode clear
+```
+
+Modes are persisted to `.oal/state/mode.txt`.
+
+## Verification and Safety
+
+OAL enforces practical completion gates:
+
+- Prevents unverified completion claims
+- Tracks repeated failures and recommends escalation
+- Validates test quality (anti-boilerplate checks)
+- Preserves evidence and handoff state before context compaction
+
+Important behavior:
+
+- Prefer proof over assumptions
+- Run checks after modifications
+- Keep output tied to observable evidence
+
+## Project State Layout
+
+After `/OAL:init`, project state is created under `.oal/`:
+
+```text
+.oal/
+  state/
+    profile.yaml
+    working-memory.md
+    handoff.md
+    ledger/
+  knowledge/
+  trust/
+  evidence/
+  shadow/
+  migrations/
+```
+
+## Repository Layout (High Level)
+
+```text
+oal/
+  hooks/
+  rules/
+    core/
+    contextual/
+  agents/
+  commands/
+  plugins/
+  templates/
+  runtime/
+  scripts/
+  OAL-setup.sh
+```
+
+## Versioning and Releases
+
+Current version: `v1.0.2`
+
+Recommended release flow:
+
+```bash
+git tag -a v1.0.2 -m "OAL v1.0.2"
+git push origin v1.0.2
+gh release create v1.0.2 --title "OAL v1.0.2" --notes "Release notes"
+```
+
+## Compatibility Notes
+
+- OAL runs standalone (OMC not required)
+- Legacy migration utilities remain available where needed
+- Works alongside other plugins when command namespaces do not conflict
+
+## Troubleshooting
+
+### Plugin manifest invalid
+
+If Claude reports plugin manifest schema errors:
+
+- Keep `.claude-plugin/plugin.json` minimal and schema-compatible
+- Avoid unsupported keys for your Claude Code version
+- Reinstall plugin cache after manifest changes
+
+### Plugin update does nothing
+
+- Verify marketplace source is git-based (not local directory mode)
+- Verify plugin cache points to correct version directory
+- Run update script manually once to confirm output:
+
+```bash
+bash ~/.claude/plugins/cache/oh-advanced-layer/oal/*/.claude-plugin/scripts/update.sh
+```
+
+## License
+
+MIT
+
+## New in v1.1 (Enhancement Release)
+
+### Feature Flags
+
+All new features are disabled by default. Enable via environment variables or `settings.json`:
+
+| Feature | Env Var | Default |
+|---------|---------|---------|
+| IntentGate keyword detection | `OAL_INTENTGATE_ENABLED=1` | Off |
+| Multi-credential store | `OAL_MULTI_CREDENTIAL_ENABLED=1` | Off |
+| Model roles routing | `OAL_MODEL_ROLES_ENABLED=1` | Off |
+| LSP client | `OAL_LSP_ENABLED=1` | Off |
+| Hashline anchors | `OAL_HASHLINE_ENABLED=1` | Off |
+| Python REPL | `OAL_PYTHON_REPL_ENABLED=1` | Off |
+| Web search | `OAL_WEB_SEARCH_ENABLED=1` | Off |
+| Browser automation | `OAL_BROWSER_ENABLED=1` | Off |
+| SSH manager | `OAL_SSH_ENABLED=1` | Off |
+| Themes | `OAL_THEMES_ENABLED=true` | Off |
+| Rust engine | `OAL_RUST_ENGINE_ENABLED=1` | Off |
+
+You can also enable features in `settings.json` under `_oal.features`:
+
+```json
+{
+  "_oal": {
+    "features": {
+      "THEMES": true,
+      "INTENTGATE": true
+    }
+  }
+}
+```
+
+### New Commands
+
+- `/OAL:theme` — Interactive theme selector with `--list`, `--preview`, `--set`, and `--auto` modes
+
+### New Agents
+
+v1.1 ships with expanded agent coverage:
+
+- `oal-api-builder` — API scaffolding and endpoint design
+- `oal-architect` — System design and architecture decisions
+- `oal-backend-engineer` — Backend implementation tasks
+- `oal-critic` — Code review and critique
+- `oal-database-engineer` — Schema design and query optimization
+- `oal-escalation-router` — Intelligent escalation to Codex/Gemini
+- `oal-frontend-designer` — UI/UX implementation
+- `oal-infra-engineer` — Infrastructure and DevOps tasks
+- `oal-qa-tester` — Test writing and quality assurance
+- `oal-security-auditor` — Security review and vulnerability analysis
+- `oal-testing-engineer` — Test strategy and coverage
+
+## Migration Guide
+
+### Upgrading from OAL v1.0 to v1.1
+
+All new features default to `False` and are fully backward-compatible. Existing workflows continue unchanged.
+
+To adopt new features selectively:
+
+1. **Enable via env var** before launching Claude Code:
+   ```bash
+   export OAL_THEMES_ENABLED=true
+   export OAL_MODEL_ROLES_ENABLED=1
+   ```
+
+2. **Or enable in `settings.json`** for persistent config:
+   ```json
+   {
+     "_oal": {
+       "features": {
+         "THEMES": true,
+         "MODEL_ROLES": true
+       }
+     }
+   }
+   ```
+
+3. **No breaking changes** — all v1.0 commands, agents, and hooks remain intact.
+
+4. **New command**: `/OAL:theme` is available immediately after update, gated by `OAL_THEMES_ENABLED`.

package/THIRD_PARTY_NOTICES.md

@@ -0,0 +1,24 @@
+# Third-Party Notices
+
+## Attribution and Inspiration
+
+No third-party source trees are vendored in this repository.
+
+OMG design and workflow ideas were informed by public projects, including:
+
+- `oh-my-claudecode` — `https://github.com/Yeachan-Heo/oh-my-claudecode`
+
+## Optional Ecosystem Sources
+
+These repositories are optional references that may be cloned with
+`omg ecosystem sync` into project-local OMG state:
+
+- `https://github.com/obra/superpowers`
+- `https://github.com/anthropics/claude-code` (sparse path: `plugins/ralph-wiggum`)
+- `https://github.com/ruvnet/claude-flow`
+- `https://github.com/thedotmack/claude-mem`
+- `https://github.com/rjyo/memory-search`
+- `https://github.com/steveyegge/beads`
+- `https://github.com/OthmanAdi/planning-with-files`
+- `https://github.com/disler/claude-code-hooks-mastery`
+- `https://github.com/EveryInc/compounding-engineering-plugin`

package/UPSTREAM_DIFF.md

@@ -0,0 +1,20 @@
+# Upstream Influence Notes
+
+- Upstream project: `oh-my-claudecode`
+- Source URL: `https://github.com/Yeachan-Heo/oh-my-claudecode`
+- Integration strategy: `OMG-native adapters and compatibility layer (no vendored source trees)`
+- Initial research baseline commit hash: `8234e6d8fe346bb518e44cb9bf1f2c7cc0f1d716`
+- First influence capture (UTC): `2026-02-27`
+
+## Local Policy
+
+1. Keep OMG runtime and compatibility behavior implemented in OMG-owned code.
+2. Use upstream repositories as references only, not as vendored source payload.
+3. Record major intentional divergence here.
+
+## Divergence Summary
+
+- OMG introduces standalone routing and state migration (`.omc -> .omg`).
+- OMG keeps command aliases (`/omc-teams`, `/ccg`) as compatibility wrappers.
+- OMG defaults to `.omg` as canonical runtime state path.
+- OMG adds optional ecosystem sync (`omg ecosystem`) for external plugin references.

package/agents/__init__.py

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

package/agents/_model_roles.yaml

@@ -0,0 +1,26 @@
+roles:
+  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"

package/agents/designer.md

@@ -0,0 +1,67 @@
+---
+name: designer
+description: UI/UX design agent — component design, layout, accessibility, responsive design
+model: claude-opus-4-5
+tools: Read, Grep, Glob, Bash, Write, Edit
+bundled: true
+---
+
+# Agent: Designer
+
+## Role
+
+Frontend-focused UI/UX design agent. Designs and implements components, layouts, and visual systems with accessibility and responsiveness as first-class concerns.
+
+## Model
+
+`default` (claude-opus-4-5) — balanced capability for design reasoning and implementation.
+
+## Capabilities
+
+- Component design and implementation (React, Vue, HTML/CSS)
+- Layout systems (flexbox, grid, responsive breakpoints)
+- Accessibility (ARIA, keyboard navigation, color contrast, screen readers)
+- Responsive design (mobile-first, breakpoint strategy)
+- CSS and Tailwind utility class usage
+- Design system adherence and token usage
+- Animation and micro-interaction design
+- Visual hierarchy and typography
+
+## Instructions
+
+You are a frontend design agent. You design and build UI components.
+
+**Core rules:**
+- MUST NOT modify backend/API code (routes, controllers, database)
+- MUST check accessibility on every component (ARIA labels, keyboard nav, contrast)
+- MUST verify responsive behavior at 375px, 768px, and 1280px
+- MUST NOT introduce inline styles when a design system or utility classes exist
+- ALWAYS run the frontend linter/build before claiming completion
+
+**Design process:**
+1. Understand the user need — what problem does this UI solve?
+2. Check existing design system tokens, components, and patterns
+3. Design the component structure (props, state, layout)
+4. Implement with accessibility built in from the start
+5. Verify at all breakpoints
+6. Run linter and build
+
+**Accessibility checklist (every component):**
+- [ ] Semantic HTML elements used correctly
+- [ ] ARIA labels on interactive elements without visible text
+- [ ] Keyboard navigation works (Tab, Enter, Escape, Arrow keys)
+- [ ] Color contrast meets WCAG AA (4.5:1 for text, 3:1 for UI)
+- [ ] Focus indicators visible
+
+**When to defer:**
+- Backend data fetching logic → `omg-backend-engineer`
+- Complex state management → coordinate with backend agent
+- Security-sensitive forms → recommend `/OMG:escalate codex`
+
+## Example Prompts
+
+- "Design a responsive navigation component with mobile hamburger menu"
+- "Build an accessible modal dialog with focus trap"
+- "Create a data table component with sorting and pagination"
+- "Improve the color contrast on the dashboard cards"
+- "Design a multi-step form wizard with progress indicator"

package/agents/explore.md

@@ -0,0 +1,60 @@
+---
+name: explore
+description: Fast codebase search agent — grep, glob, file reading, pattern matching
+model: claude-haiku-4-5
+tools: Read, Grep, Glob
+bundled: true
+---
+
+# Agent: Explore
+
+## Role
+
+Fast, read-only codebase search agent. Finds code, files, and patterns without modifying anything.
+
+## Model
+
+`smol` (claude-haiku-4-5) — speed-optimized for quick lookups and pattern matching.
+
+## Capabilities
+
+- Grep for patterns across files and directories
+- Glob to find files by name or extension
+- Read file contents and extract relevant sections
+- Pattern matching across multiple files simultaneously
+- Symbol and reference discovery
+- Dependency tracing (imports, requires, includes)
+- Find all usages of a function, class, or variable
+
+## Instructions
+
+You are a read-only search agent. Your job is to find things, not change them.
+
+**Core rules:**
+- NEVER write, edit, or delete files
+- NEVER run commands that modify state (no git commits, no npm install, no file writes)
+- ALWAYS return file paths with line numbers when reporting findings
+- ALWAYS summarize what you found at the end
+
+**Search strategy:**
+1. Start broad with glob to find candidate files
+2. Narrow with grep to find exact patterns
+3. Read relevant sections for context
+4. Report findings with file:line references
+
+**Output format:**
+- List each finding as `file.ext:LINE — description`
+- Group related findings together
+- End with a summary count: "Found N occurrences in M files"
+
+**When to stop:**
+- Once you've found what was asked for
+- If a pattern doesn't exist, say so clearly — don't keep searching
+
+## Example Prompts
+
+- "Find all usages of `fetchUser` across the codebase"
+- "Which files import from `@/lib/auth`?"
+- "Show me all TODO comments in the src/ directory"
+- "Find every place we call `console.error`"
+- "What files define a `handleSubmit` function?"