@trac3er/oh-my-god 2.0.4 → 2.0.5

package/docs/install/codex.md

@@ -0,0 +1,29 @@
+# Install OMG for Codex
+
+## Fast Path
+
+```bash
+npm install -g @openai/codex
+npm install @trac3er/oh-my-god
+```
+
+Then run:
+
+```text
+/OMG:setup
+```
+
+## Manual Path
+
+```bash
+git clone https://github.com/trac3er00/OMG
+cd OMG
+chmod +x OMG-setup.sh
+./OMG-setup.sh install --mode=omg-only --preset=interop
+```
+
+## Verify
+
+- OMG detects `codex` during setup and configures shared MCP state.
+- `interop` is the recommended preset when Codex is part of a multi-host workflow.
+- Run `/OMG:crazy <goal>` once setup confirms host detection and MCP wiring.

package/docs/migration/native-adoption.md

@@ -0,0 +1,57 @@
+# Native Adoption for OMC, OMX, and Superpowers
+
+OMG keeps adoption native to OMG. There is no public `migrate` command to memorize or map back to another project.
+
+Use either:
+
+- `/OMG:setup`
+- `./OMG-setup.sh install --adopt=auto`
+
+## What Setup Detects
+
+Setup can detect compatibility markers from:
+
+- OMC-style environments
+- OMX-style environments
+- Superpowers-style command, skill, or workspace surfaces
+
+Those detections are treated as adoption context, not as public implementation detail.
+
+## Adoption Modes
+
+### OMG-only
+
+Recommended for most users.
+
+- OMG becomes the primary hooks, HUD, MCP, and orchestration layer.
+- Portable state is preserved where safe and overlapping surfaces are backed up before replacement.
+- `compat` remains available for legacy skill routing only.
+
+### coexist
+
+Advanced mode for careful landings.
+
+- OMG avoids claiming ownership of third-party namespaces.
+- Existing HUD and hook ownership stays intact unless you explicitly switch later.
+- Conflicts are recorded in the adoption report instead of being overwritten.
+
+## Output
+
+Native adoption writes:
+
+- `.omg/state/adoption-report.json`
+- `.omg/state/cli-config.yaml`
+- `.mcp.json`
+
+## Choosing a Preset
+
+- `safe`: conservative OMG baseline
+- `balanced`: recommended daily workflow
+- `interop`: stronger shared-memory and multi-host interop
+- `labs`: enables the most opinionated experimentation surfaces
+
+## What Changes for Existing Users
+
+- OMG-native setup language replaces public migration language.
+- Compatibility references remain documented so users coming from OMC, OMX, or Superpowers can understand what setup detected.
+- Public onboarding stays focused on `/OMG:setup` and `/OMG:crazy`.

package/docs/proof.md

@@ -0,0 +1,55 @@
+# OMG Proof Surface
+
+[![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)
+
+## Verification Status
+
+OMG keeps verification visible instead of burying it in implementation details.
+
+- Current local full-suite result: `2466 passed, 2 skipped` on March 7, 2026.
+- Releases are expected to pass the compat gate, the standalone verification path, and the public-readiness check.
+- Setup, presets, and native adoption behavior have targeted regression tests.
+- `security-check`, `api-twin`, runtime profiles, and the stdio `omg-control` MCP have targeted regression coverage.
+- `compat` remains covered, but it is not the public onboarding path.
+
+## Provider Matrix
+
+| Provider | Detect | Auth Check | MCP Config | Host Priority |
+|----------|--------|------------|------------|---------------|
+| Claude Code | host-native | host-native | yes | primary |
+| Codex | yes | yes | yes | primary |
+| Gemini | yes | yes | yes | supported |
+| Kimi | yes | yes | yes | supported |
+
+## Adoption Evidence
+
+- Native setup writes `.omg/state/adoption-report.json`
+- Native setup writes `.omg/state/cli-config.yaml`
+- `OMG-only` and `coexist` are both covered in setup tests
+- OMC, OMX, and Superpowers references stay limited to compatibility and adoption guidance
+
+## HUD Artifact
+
+![OMG HUD](assets/omg-hud.svg)
+
+## Benchmark Tasks
+
+Representative benchmark tasks for this release:
+
+- host detection and auth wiring
+- canonical security-check routing and evidence emission
+- stdio OMG control MCP wiring
+- adoption detection with overlapping ecosystems
+- plugin install and uninstall correctness
+- `crazy` orchestration smoke coverage
+
+## Sample Transcripts
+
+- Setup: [docs/transcripts/setup.md](transcripts/setup.md)
+- Crazy: [docs/transcripts/crazy.md](transcripts/crazy.md)
+
+## Release Discipline
+
+- Public launch checklist: [docs/release-checklist.md](release-checklist.md)
+- Changelog: [CHANGELOG.md](../CHANGELOG.md)

package/docs/release-checklist.md

@@ -0,0 +1,38 @@
+# Public Release Checklist
+
+Use this checklist before making OMG public or cutting a release tag.
+
+## Identity
+
+- README, `package.json`, plugin manifests, and CLI version output agree on the version
+- repo URL is `https://github.com/trac3er00/OMG`
+- plugin and marketplace id are `omg`
+
+## Public Safety
+
+- `python3 scripts/check-omg-public-ready.py` passes
+- no internal planning docs ship in `docs/plans/`
+- no absolute local paths or stale internal path references remain
+
+## Verification
+
+- `python3 scripts/omg.py contract validate` passes
+- `python3 scripts/omg.py contract compile --host claude --host codex --channel public --output-root <tmp>` passes
+- `python3 scripts/omg.py contract compile --host claude --host codex --channel enterprise --output-root <tmp>` passes
+- `python3 scripts/omg.py release readiness --channel dual --output-root <tmp>` passes
+- `python3 scripts/check-omg-standalone-clean.py` passes
+- `./scripts/verify-standalone.sh` passes
+- `python3 -m pytest tests -q` passes
+
+## Docs
+
+- README matches the current product surface
+- install guides for Claude Code and Codex are current
+- proof page includes current verification evidence
+- changelog includes the release entry
+
+## Release Ops
+
+- `package.json` version matches the tag you will create
+- npm publishing credentials are configured for `publish-npm.yml`
+- GitHub Actions required checks are green

package/docs/transcripts/crazy.md

@@ -0,0 +1,17 @@
+# Sample Transcript: /OMG:crazy
+
+```text
+/OMG:crazy stabilize auth and dashboard flows
+
+Workers:
+- architect-mode
+- backend-engineer
+- frontend-designer
+- security-auditor
+- testing-engineer
+
+Execution:
+- parallel
+- evidence-aware
+- verification required before completion
+```

package/docs/transcripts/setup.md

@@ -0,0 +1,25 @@
+# Sample Transcript: /OMG:setup
+
+```text
+/OMG:setup
+
+Detected hosts:
+- codex: installed, authenticated
+- gemini: not found
+- kimi: not found
+
+Detected ecosystems:
+- omc
+- superpowers
+
+Recommended mode: omg-only
+Selected preset: balanced
+
+Configured:
+- .mcp.json
+- .omg/state/cli-config.yaml
+- .omg/state/adoption-report.json
+
+Next step:
+/OMG:crazy stabilize auth and dashboard flows
+```

package/hooks/shadow_manager.py

@@ -182,6 +182,9 @@ def create_evidence_pack(
     provenance: list[dict[str, Any]] | None = None,
     trust_scores: dict[str, Any] | None = None,
     api_twin: dict[str, Any] | None = None,
+    route_metadata: dict[str, Any] | None = None,
+    trace_ids: list[str] | None = None,
+    lineage: dict[str, Any] | None = None,
 ) -> str:
     ensure_shadow_dirs(project_dir)
     run_id = _validated_run_id(run_id)
@@ -197,6 +200,9 @@ def create_evidence_pack(
         "provenance": provenance or [],
         "trust_scores": trust_scores or {},
         "api_twin": api_twin or {},
+        "route_metadata": route_metadata or {},
+        "trace_ids": trace_ids or [],
+        "lineage": lineage or {},
     }
     evidence_path = ensure_path_within_dir(
         _evidence_root(project_dir),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trac3er/oh-my-god",
-  "version": "2.0.4",
+  "version": "2.0.5",
   "description": "OMG (Oh My God) — Multi-agent orchestration, intelligent model routing, and durable session state for Claude Code",
   "main": "OMG-setup.sh",
   "scripts": {

package/plugins/__init__.py

@@ -0,0 +1 @@
+"""OMG plugin packages."""

package/plugins/core/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "omg-core",
-  "version": "2.0.4",
+  "version": "2.0.5",
   "description": "Core OMG commands - native setup, routing, orchestration, and verification surfaces",
   "type": "omg-plugin",
   "commands": {

package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "oh-my-god"
-version = "2.0.4"
+version = "2.0.5"
 description = "OMG (Oh My God) — Multi-agent orchestration, intelligent model routing, and durable session state for Claude Code"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -42,7 +42,43 @@ Repository = "https://github.com/trac3er00/OMG.git"
 Issues = "https://github.com/trac3er00/OMG/issues"
 
 [tool.setuptools]
-packages = ["hooks", "runtime", "agents", "commands"]
+include-package-data = true
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["agents*", "commands*", "control_plane*", "hooks*", "plugins*", "registry*", "runtime*"]
+
+[tool.setuptools.package-data]
+agents = ["*.md"]
+commands = ["*.md"]
+control_plane = ["*.yaml"]
+plugins = ["**/*.json", "**/*.md"]
+registry = ["*.json", "bundles/*.yaml"]
+runtime = ["*.json"]
+
+[tool.setuptools.data-files]
+"." = ["OMG_COMPAT_CONTRACT.md", "settings.json", ".mcp.json"]
+".claude-plugin" = [".claude-plugin/plugin.json", ".claude-plugin/marketplace.json"]
+"docs" = ["docs/release-checklist.md"]
+".agents/skills/omg" = [".agents/skills/omg/AGENTS.fragment.md", ".agents/skills/omg/codex-mcp.toml"]
+".agents/skills/omg/control-plane" = [".agents/skills/omg/control-plane/SKILL.md", ".agents/skills/omg/control-plane/openai.yaml"]
+".agents/skills/omg/hook-governor" = [".agents/skills/omg/hook-governor/SKILL.md", ".agents/skills/omg/hook-governor/openai.yaml"]
+".agents/skills/omg/lsp-pack" = [".agents/skills/omg/lsp-pack/SKILL.md", ".agents/skills/omg/lsp-pack/openai.yaml"]
+".agents/skills/omg/mcp-fabric" = [".agents/skills/omg/mcp-fabric/SKILL.md", ".agents/skills/omg/mcp-fabric/openai.yaml"]
+".agents/skills/omg/secure-worktree-pipeline" = [".agents/skills/omg/secure-worktree-pipeline/SKILL.md", ".agents/skills/omg/secure-worktree-pipeline/openai.yaml"]
+".agents/skills/omg/security-check" = [".agents/skills/omg/security-check/SKILL.md", ".agents/skills/omg/security-check/openai.yaml"]
+".agents/skills/omg/api-twin" = [".agents/skills/omg/api-twin/SKILL.md", ".agents/skills/omg/api-twin/openai.yaml"]
+".agents/skills/omg/preflight" = [".agents/skills/omg/preflight/SKILL.md", ".agents/skills/omg/preflight/openai.yaml"]
+".agents/skills/omg/robotics" = [".agents/skills/omg/robotics/SKILL.md", ".agents/skills/omg/robotics/openai.yaml"]
+".agents/skills/omg/vision" = [".agents/skills/omg/vision/SKILL.md", ".agents/skills/omg/vision/openai.yaml"]
+".agents/skills/omg/algorithms" = [".agents/skills/omg/algorithms/SKILL.md", ".agents/skills/omg/algorithms/openai.yaml"]
+".agents/skills/omg/health" = [".agents/skills/omg/health/SKILL.md", ".agents/skills/omg/health/openai.yaml"]
+".agents/skills/omg/tracebank" = [".agents/skills/omg/tracebank/SKILL.md", ".agents/skills/omg/tracebank/openai.yaml"]
+".agents/skills/omg/eval-gate" = [".agents/skills/omg/eval-gate/SKILL.md", ".agents/skills/omg/eval-gate/openai.yaml"]
+".agents/skills/omg/delta-classifier" = [".agents/skills/omg/delta-classifier/SKILL.md", ".agents/skills/omg/delta-classifier/openai.yaml"]
+".agents/skills/omg/incident-replay" = [".agents/skills/omg/incident-replay/SKILL.md", ".agents/skills/omg/incident-replay/openai.yaml"]
+".agents/skills/omg/data-lineage" = [".agents/skills/omg/data-lineage/SKILL.md", ".agents/skills/omg/data-lineage/openai.yaml"]
+".agents/skills/omg/remote-supervisor" = [".agents/skills/omg/remote-supervisor/SKILL.md", ".agents/skills/omg/remote-supervisor/openai.yaml"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

package/registry/__init__.py

@@ -0,0 +1 @@
+"""Registry package for OMG."""

package/registry/bundles/algorithms.yaml

@@ -0,0 +1,45 @@
+id: algorithms
+kind: domain-pack
+version: 2.0.5
+title: OMG Algorithms Pack
+description: Determinism and benchmark attachments for algorithm-heavy work.
+hosts:
+  - claude
+  - codex
+assets:
+  references:
+    - runtime/domain_packs.py
+invocation_policy:
+  user_invocable: true
+  model_invocable: true
+  allow_implicit_invocation: false
+tool_policy:
+  side_effect_level: medium
+  allowed_tools:
+    claude:
+      - Read
+    codex:
+      - Read
+lifecycle_hooks:
+  native:
+    - PostToolUse
+  emulated:
+    - TaskCompleted
+mcp_contract:
+  servers:
+    - omg-control
+lsp_contract:
+  languages:
+    - python
+evidence_outputs:
+  artifacts:
+    - .omg/evals/latest.json
+execution_contract:
+  modes:
+    - embedded
+    - local_supervisor
+channel_overrides:
+  public:
+    benchmarks: advisory
+  enterprise:
+    benchmarks: required

package/registry/bundles/api-twin.yaml

@@ -0,0 +1,48 @@
+id: api-twin
+kind: simulation
+version: 2.0.5
+title: OMG API Twin
+description: Versioned endpoint cassette replay with latency, drift, and cost reporting.
+hosts:
+  - claude
+  - codex
+assets:
+  references:
+    - runtime/api_twin.py
+    - commands/OMG:api-twin.md
+invocation_policy:
+  user_invocable: true
+  model_invocable: true
+  allow_implicit_invocation: false
+tool_policy:
+  side_effect_level: medium
+  allowed_tools:
+    claude:
+      - Read
+      - Bash(python3:*)
+    codex:
+      - Read
+      - Bash(python3:*)
+lifecycle_hooks:
+  native:
+    - PostToolUse
+  emulated:
+    - TaskCompleted
+mcp_contract:
+  servers:
+    - omg-control
+lsp_contract:
+  languages:
+    - python
+evidence_outputs:
+  artifacts:
+    - .omg/state/api_twin.json
+execution_contract:
+  modes:
+    - embedded
+    - local_supervisor
+channel_overrides:
+  public:
+    fidelity: validated
+  enterprise:
+    fidelity: policy-required

package/registry/bundles/control-plane.yaml

@@ -0,0 +1,61 @@
+id: control-plane
+kind: skill
+version: 2.0.5
+title: OMG Control Plane
+description: Canonical production control plane bundle for Claude and Codex.
+hosts:
+  - claude
+  - codex
+assets:
+  references:
+    - OMG_COMPAT_CONTRACT.md
+    - docs/release-checklist.md
+invocation_policy:
+  user_invocable: true
+  model_invocable: false
+  allow_implicit_invocation: false
+tool_policy:
+  side_effect_level: medium
+  allowed_tools:
+    claude:
+      - Read
+      - Grep
+      - Bash(python3:*)
+    codex:
+      - Read
+      - Grep
+      - Bash(python3:*)
+lifecycle_hooks:
+  native:
+    - SessionStart
+    - PreToolUse
+    - PostToolUse
+  emulated:
+    - PreCompact
+    - WorktreeCreate
+    - WorktreeRemove
+mcp_contract:
+  servers:
+    - omg-control
+    - omg-memory
+  prompts:
+    - omg_contract_summary
+  resources:
+    - resource://omg/contract
+    - resource://omg/release-checklist
+lsp_contract:
+  languages:
+    - python
+    - typescript
+evidence_outputs:
+  artifacts:
+    - .omg/evidence/control-plane-compile.json
+execution_contract:
+  modes:
+    - embedded
+    - local_supervisor
+channel_overrides:
+  public:
+    posture: self-serve
+  enterprise:
+    posture: managed

package/registry/bundles/data-lineage.yaml

@@ -0,0 +1,47 @@
+id: data-lineage
+kind: provenance
+version: 2.0.5
+title: OMG Data Lineage
+description: Provenance and privacy tracking for traces, fixtures, examples, and synthetic artifacts.
+hosts:
+  - claude
+  - codex
+assets:
+  references:
+    - runtime/data_lineage.py
+invocation_policy:
+  user_invocable: true
+  model_invocable: true
+  allow_implicit_invocation: true
+tool_policy:
+  side_effect_level: medium
+  allowed_tools:
+    claude:
+      - Read
+      - Bash(python3:*)
+    codex:
+      - Read
+      - Bash(python3:*)
+lifecycle_hooks:
+  native:
+    - PostToolUse
+  emulated:
+    - TaskCompleted
+mcp_contract:
+  servers:
+    - omg-control
+lsp_contract:
+  languages:
+    - python
+evidence_outputs:
+  artifacts:
+    - .omg/lineage/*.json
+execution_contract:
+  modes:
+    - embedded
+    - local_supervisor
+channel_overrides:
+  public:
+    provenance: required
+  enterprise:
+    provenance: required

package/registry/bundles/delta-classifier.yaml

@@ -0,0 +1,47 @@
+id: delta-classifier
+kind: routing
+version: 2.0.5
+title: OMG Delta Classifier
+description: Change classifier that attaches risk-aware checks, approvals, and packs.
+hosts:
+  - claude
+  - codex
+assets:
+  references:
+    - runtime/delta_classifier.py
+invocation_policy:
+  user_invocable: true
+  model_invocable: true
+  allow_implicit_invocation: true
+tool_policy:
+  side_effect_level: low
+  allowed_tools:
+    claude:
+      - Read
+      - Grep
+    codex:
+      - Read
+      - Grep
+lifecycle_hooks:
+  native:
+    - SessionStart
+  emulated:
+    - TaskCompleted
+mcp_contract:
+  servers:
+    - omg-control
+lsp_contract:
+  languages:
+    - python
+evidence_outputs:
+  artifacts:
+    - .omg/tracebank/events.jsonl
+execution_contract:
+  modes:
+    - embedded
+    - local_supervisor
+channel_overrides:
+  public:
+    classification: advisory
+  enterprise:
+    classification: required

package/registry/bundles/eval-gate.yaml

@@ -0,0 +1,47 @@
+id: eval-gate
+kind: evaluation
+version: 2.0.5
+title: OMG Eval Gate
+description: Reproducible evaluation gate that blocks regressions before release.
+hosts:
+  - claude
+  - codex
+assets:
+  references:
+    - runtime/eval_gate.py
+invocation_policy:
+  user_invocable: true
+  model_invocable: true
+  allow_implicit_invocation: false
+tool_policy:
+  side_effect_level: medium
+  allowed_tools:
+    claude:
+      - Read
+      - Bash(python3:*)
+    codex:
+      - Read
+      - Bash(python3:*)
+lifecycle_hooks:
+  native:
+    - PostToolUse
+  emulated:
+    - TaskCompleted
+mcp_contract:
+  servers:
+    - omg-control
+lsp_contract:
+  languages:
+    - python
+evidence_outputs:
+  artifacts:
+    - .omg/evals/latest.json
+execution_contract:
+  modes:
+    - embedded
+    - local_supervisor
+channel_overrides:
+  public:
+    regressions: block
+  enterprise:
+    regressions: block

package/registry/bundles/health.yaml

@@ -0,0 +1,45 @@
+id: health
+kind: domain-pack
+version: 2.0.5
+title: OMG Health Pack
+description: Health-sensitive approvals, provenance, and replay attachments.
+hosts:
+  - claude
+  - codex
+assets:
+  references:
+    - runtime/domain_packs.py
+invocation_policy:
+  user_invocable: true
+  model_invocable: true
+  allow_implicit_invocation: false
+tool_policy:
+  side_effect_level: high
+  allowed_tools:
+    claude:
+      - Read
+    codex:
+      - Read
+lifecycle_hooks:
+  native:
+    - PostToolUse
+  emulated:
+    - TaskCompleted
+mcp_contract:
+  servers:
+    - omg-control
+lsp_contract:
+  languages:
+    - python
+evidence_outputs:
+  artifacts:
+    - .omg/lineage/*.json
+execution_contract:
+  modes:
+    - embedded
+    - local_supervisor
+channel_overrides:
+  public:
+    approvals: required
+  enterprise:
+    approvals: enforced