@trac3er/oh-my-god 2.0.4 → 2.0.7

package/dist/public/bundle/.agents/skills/omg/codex-rules.md

@@ -0,0 +1,29 @@
+# OMG Codex Rules (channel: public)
+
+## Defaults
+
+- `cached_web_search: prefer_cached`
+- `live_network: deny_by_default`
+- `destructive_approval: required`
+
+## Protected Paths
+
+- `.omg/**`
+- `.agents/**`
+- `.codex/**`
+- `.claude/**`
+
+## Required Skills
+
+- `omg/control-plane`
+- `omg/mcp-fabric`
+
+## Approval Matrix
+
+| Action | Approval Required |
+|--------|------------------|
+| Read / Grep | No |
+| Write to protected paths | Yes |
+| Bash (python3:*) | Yes (balanced+ tier) |
+| git push --force | Yes |
+| Production deploy | Yes |

package/dist/public/bundle/.agents/skills/omg/data-lineage/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-data-lineage
+description: "Provenance and privacy tracking for traces, fixtures, examples, and synthetic artifacts."
+---
+
+# OMG Data Lineage
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/lineage/*.json`

package/dist/public/bundle/.agents/skills/omg/data-lineage/openai.yaml

@@ -0,0 +1,12 @@
+name: omg-data-lineage
+description: "Provenance and privacy tracking for traces, fixtures, examples, and synthetic artifacts."
+allow_implicit_invocation: true
+metadata:
+  channel: public
+  bundle_id: data-lineage
+  title: "OMG Data Lineage"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"
+  - "Bash(python3:*)"

package/dist/public/bundle/.agents/skills/omg/delta-classifier/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-delta-classifier
+description: "Change classifier that attaches risk-aware checks, approvals, and packs."
+---
+
+# OMG Delta Classifier
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/tracebank/events.jsonl`

package/dist/public/bundle/.agents/skills/omg/delta-classifier/openai.yaml

@@ -0,0 +1,12 @@
+name: omg-delta-classifier
+description: "Change classifier that attaches risk-aware checks, approvals, and packs."
+allow_implicit_invocation: true
+metadata:
+  channel: public
+  bundle_id: delta-classifier
+  title: "OMG Delta Classifier"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"
+  - "Grep"

package/dist/public/bundle/.agents/skills/omg/eval-gate/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-eval-gate
+description: "Reproducible evaluation gate that blocks regressions before release."
+---
+
+# OMG Eval Gate
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/evals/latest.json`

package/dist/public/bundle/.agents/skills/omg/eval-gate/openai.yaml

@@ -0,0 +1,12 @@
+name: omg-eval-gate
+description: "Reproducible evaluation gate that blocks regressions before release."
+allow_implicit_invocation: false
+metadata:
+  channel: public
+  bundle_id: eval-gate
+  title: "OMG Eval Gate"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"
+  - "Bash(python3:*)"

package/dist/public/bundle/.agents/skills/omg/health/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-health
+description: "Health-sensitive approvals, provenance, and replay attachments."
+---
+
+# OMG Health Pack
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/lineage/*.json`

package/dist/public/bundle/.agents/skills/omg/health/openai.yaml

@@ -0,0 +1,11 @@
+name: omg-health
+description: "Health-sensitive approvals, provenance, and replay attachments."
+allow_implicit_invocation: false
+metadata:
+  channel: public
+  bundle_id: health
+  title: "OMG Health Pack"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"

package/dist/public/bundle/.agents/skills/omg/incident-replay/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-incident-replay
+description: "Replayable bug packs built from logs, failing tests, traces, and diffs."
+---
+
+# OMG Incident Replay
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/incidents/*.json`

package/dist/public/bundle/.agents/skills/omg/incident-replay/openai.yaml

@@ -0,0 +1,12 @@
+name: omg-incident-replay
+description: "Replayable bug packs built from logs, failing tests, traces, and diffs."
+allow_implicit_invocation: false
+metadata:
+  channel: public
+  bundle_id: incident-replay
+  title: "OMG Incident Replay"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"
+  - "Bash(python3:*)"

package/dist/public/bundle/.agents/skills/omg/preflight/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-preflight
+description: "Repo-aware route selection based on diff, manifests, and classified risk."
+---
+
+# OMG Preflight
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/tracebank/events.jsonl`

package/dist/public/bundle/.agents/skills/omg/preflight/openai.yaml

@@ -0,0 +1,12 @@
+name: omg-preflight
+description: "Repo-aware route selection based on diff, manifests, and classified risk."
+allow_implicit_invocation: true
+metadata:
+  channel: public
+  bundle_id: preflight
+  title: "OMG Preflight"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"
+  - "Grep"

package/dist/public/bundle/.agents/skills/omg/remote-supervisor/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-remote-supervisor
+description: "Local-only authenticated supervisor sessions for worker orchestration."
+---
+
+# OMG Remote Supervisor
+
+- Channel: `public`
+- Execution modes: `local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/supervisor/sessions/*.json`

package/dist/public/bundle/.agents/skills/omg/remote-supervisor/openai.yaml

@@ -0,0 +1,12 @@
+name: omg-remote-supervisor
+description: "Local-only authenticated supervisor sessions for worker orchestration."
+allow_implicit_invocation: false
+metadata:
+  channel: public
+  bundle_id: remote-supervisor
+  title: "OMG Remote Supervisor"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"
+  - "Bash(python3:*)"

package/dist/public/bundle/.agents/skills/omg/robotics/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-robotics
+description: "Robotics safety policy, replay, and evaluation attachments."
+---
+
+# OMG Robotics Pack
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/incidents/*.json`

package/dist/public/bundle/.agents/skills/omg/robotics/openai.yaml

@@ -0,0 +1,11 @@
+name: omg-robotics
+description: "Robotics safety policy, replay, and evaluation attachments."
+allow_implicit_invocation: false
+metadata:
+  channel: public
+  bundle_id: robotics
+  title: "OMG Robotics Pack"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"

package/dist/public/bundle/.agents/skills/omg/security-check/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-security-check
+description: "Canonical security audit bundle with provenance, trust scoring, and deterministic evidence."
+---
+
+# OMG Security Check
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/evidence/security-check-*.json`

package/dist/public/bundle/.agents/skills/omg/security-check/openai.yaml

@@ -0,0 +1,13 @@
+name: omg-security-check
+description: "Canonical security audit bundle with provenance, trust scoring, and deterministic evidence."
+allow_implicit_invocation: false
+metadata:
+  channel: public
+  bundle_id: security-check
+  title: "OMG Security Check"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"
+  - "Grep"
+  - "Bash(python3:*)"

package/dist/public/bundle/.agents/skills/omg/tracebank/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-tracebank
+description: "Structured plan-to-patch-to-verify trace capture for OMG routes."
+---
+
+# OMG Tracebank
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/tracebank/events.jsonl`

package/dist/public/bundle/.agents/skills/omg/tracebank/openai.yaml

@@ -0,0 +1,12 @@
+name: omg-tracebank
+description: "Structured plan-to-patch-to-verify trace capture for OMG routes."
+allow_implicit_invocation: true
+metadata:
+  channel: public
+  bundle_id: tracebank
+  title: "OMG Tracebank"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"
+  - "Bash(python3:*)"

package/dist/public/bundle/.agents/skills/omg/vision/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: omg-vision
+description: "Vision-specific lineage, drift, and replay attachments."
+---
+
+# OMG Vision Pack
+
+- Channel: `public`
+- Execution modes: `embedded, local_supervisor`
+- MCP servers: `omg-control`
+- Evidence outputs: `.omg/lineage/*.json`

package/dist/public/bundle/.agents/skills/omg/vision/openai.yaml

@@ -0,0 +1,11 @@
+name: omg-vision
+description: "Vision-specific lineage, drift, and replay attachments."
+allow_implicit_invocation: false
+metadata:
+  channel: public
+  bundle_id: vision
+  title: "OMG Vision Pack"
+mcp_servers:
+  - omg-control
+allowed_tools:
+  - "Read"

package/dist/public/bundle/.claude-plugin/marketplace.json

@@ -5,16 +5,16 @@
     "name": "trac3er00"
   },
   "metadata": {
-    "description": "OMG - Oh-My-God for Claude Code",
-    "version": "2.0.4",
+    "description": "OMG - Oh-My-God for Claude Code and supported agent hosts",
+    "version": "2.0.7",
     "homepage": "https://github.com/trac3er00/OMG",
     "repository": "https://github.com/trac3er00/OMG"
   },
   "plugins": [
     {
       "name": "omg",
-      "description": "OMG plugin layer for Claude Code with native setup, orchestration, and interop.",
-      "version": "2.0.4",
+      "description": "OMG plugin layer for Claude Code and supported agent hosts with native setup, orchestration, and interop.",
+      "version": "2.0.7",
       "source": "./",
       "author": {
         "name": "trac3er00"
@@ -32,5 +32,5 @@
       ]
     }
   ],
-  "version": "2.0.4"
+  "version": "2.0.7"
 }

package/dist/public/bundle/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "omg",
-  "version": "2.0.4",
+  "version": "2.0.7",
   "description": "OMG plugin layer for Claude Code with native setup, orchestration, and interop.",
   "author": {
     "name": "trac3er00"

package/dist/public/bundle/OMG_COMPAT_CONTRACT.md

@@ -1,6 +1,6 @@
 ---
 title: OMG Production Control Plane
-version: 2.0.4
+version: 2.0.7
 canonical_hosts:
   - claude
   - codex

package/dist/public/bundle/plugins/advanced/commands/OMG:code-review.md

@@ -0,0 +1,114 @@
+---
+description: Deep code review — reads file completely, checks line-by-line for issues, then analyzes whole-file structure. Enforces code hygiene.
+allowed-tools: Read, Bash(cat:*), Bash(grep:*), Bash(wc:*), Bash(head:*), Bash(find:*), Bash(rg:*), Grep, Glob
+argument-hint: "[file path or 'recent' for git-changed files]"
+---
+
+# /OMG:code-review — Line-by-Line + Structural Review
+
+## Philosophy
+Two passes: LINE-BY-LINE precision, then WHOLE-FILE understanding.
+Don't just scan — READ and UNDERSTAND every line.
+
+## Step 1: Determine Scope
+
+- If file specified: review that file
+- If "recent" or no argument: review uncommitted changes
+  ```bash
+  git diff --name-only HEAD 2>/dev/null
+  git diff --cached --name-only 2>/dev/null
+  ```
+
+## Step 2: Read the FULL File First
+
+Read the ENTIRE file. Not just the changed part. Not just a function.
+Understanding comes from seeing the whole context.
+
+Note:
+- What does this file DO? (its purpose in the system)
+- What are its DEPENDENCIES? (imports, calls)
+- What does it EXPORT? (public API)
+
+## Step 3: Line-by-Line Scan
+
+For each line, check:
+
+**Correctness:**
+- Logic errors (off-by-one, null checks, type mismatches)
+- Missing error handling (unhandled promises, bare except, no null check)
+- Race conditions (shared state, async without await, unchecked concurrent access)
+
+**Security (if auth/payment/database):**
+- Hardcoded secrets → CRITICAL
+- SQL injection (string concatenation in queries) → CRITICAL
+- XSS (innerHTML, dangerouslySetInnerHTML) → HIGH
+- Missing input validation → MEDIUM
+- Overly permissive CORS/cookies → MEDIUM
+
+**Hygiene:**
+- Dead code (unused imports, variables, unreachable branches)
+- Noise comments ("increment i", "return result", "constructor")
+- console.log/print left in production code
+- TODO/FIXME/HACK without tracking
+- Overly complex functions (>40 lines → suggest extract)
+- Duplicated logic (same pattern in 2+ places → suggest DRY)
+
+## Step 4: Whole-File Structure Analysis
+
+After line-by-line:
+- Does the file do ONE thing well, or is it a dumping ground?
+- Are functions ordered logically? (public first, helpers after, or lifecycle order)
+- Is naming consistent? (camelCase throughout? PascalCase for classes?)
+- Does it follow the project's domain pattern? (check .omg/knowledge/domain-patterns/)
+- Any circular dependencies?
+- Is error handling consistent across all functions?
+
+## Step 5: Report
+
+```
+Code Review — [file]
+━━━━━━━━━━━━━━━━━━━━
+
+Structure: [CLEAN | NEEDS_WORK | MESSY]
+Security:  [SAFE | REVIEW_NEEDED | CRITICAL]
+Hygiene:   [CLEAN | NEEDS_CLEANUP]
+
+Issues:
+  [line:col] CRITICAL: [description]
+  [line:col] HIGH: [description]
+  [line:col] MEDIUM: [description]
+  [line:col] LOW: [description]
+
+Dead Code:
+  [line] unused import: [name]
+  [line] unreachable after return
+
+Noise Comments (remove these):
+  [line] "// increment counter"
+  [line] "// return the value"
+
+Structural:
+  - [function] is [N] lines — consider extracting [suggestion]
+  - [pattern] duplicated at lines [X] and [Y]
+
+Recommendation: [summary of what to fix, in priority order]
+```
+
+## Step 6: For Security-Critical Files
+
+If the file touches auth, payment, or database:
+```
+/OMG:escalate codex "Line-by-line security review of [file]. Check:
+1. Every input validation point
+2. Every database query for injection
+3. Every auth check for bypass
+4. Every secret reference for hardcoding
+Report: line numbers + severity + fix suggestion"
+```
+
+## Anti-patterns
+- DON'T skim and say "looks good" — read every line
+- DON'T only check the diff — read the full file for context
+- DON'T ignore test files — they can have real issues too
+- DON'T add more noise comments as "fixes" — remove them instead
+- DON'T suggest unnecessary code as improvements