diff --git a/.agents/skills/mework/SKILL.md b/.agents/skills/mework/SKILL.md
new file mode 100644
index 0000000..a26498a
--- /dev/null
+++ b/.agents/skills/mework/SKILL.md
@@ -0,0 +1,417 @@
+---
+name: mework-conventions
+description: Development conventions and patterns for mework. Python project with conventional commits.
+---
+
+# Mework Conventions
+
+> Generated from [jaayslaughter-cpu/mework](https://github.com/jaayslaughter-cpu/mework) on 2026-03-20
+
+## Overview
+
+This skill teaches Claude the development patterns and conventions used in mework.
+
+## Tech Stack
+
+- **Primary Language**: Python
+- **Architecture**: hybrid module organization
+- **Test Location**: separate
+
+## When to Use This Skill
+
+Activate this skill when:
+- Making changes to this repository
+- Adding new features following established patterns
+- Writing tests that match project conventions
+- Creating commits with proper message format
+
+## Commit Conventions
+
+Follow these commit message conventions based on 55 analyzed commits.
+
+### Commit Style: Conventional Commits
+
+### Prefixes Used
+
+- `feat`
+- `fix`
+- `chore`
+
+### Message Guidelines
+
+- Average message length: ~58 characters
+- Keep first line concise and descriptive
+- Use imperative mood ("Add feature" not "Added feature")
+
+
+*Commit message example*
+
+```text
+feat: PropIQ complete implementation [fix/sync-worker-bugs]
+```
+
+*Commit message example*
+
+```text
+fix(docker): Add REDIS_PASSWORD env var to hub service
+```
+
+*Commit message example*
+
+```text
+chore: Tighten CORS origins, remove wildcard
+```
+
+*Commit message example*
+
+```text
+Merge pull request #25 from jaayslaughter-cpu/ticket-6.4-defensive-contrast
+```
+
+*Commit message example*
+
+```text
+Merge branch 'main' into ticket-6.4-defensive-contrast
+```
+
+*Commit message example*
+
+```text
+chore: Remove Streamlit dashboard
+```
+
+*Commit message example*
+
+```text
+feat(scripts): Enhanced training pipeline with multi-source data
+```
+
+*Commit message example*
+
+```text
+feat(api): Defensive Contrast Engine for batted-ball profile mismatches
+```
+
+## Architecture
+
+### Project Structure: Single Package
+
+This project uses **hybrid** module organization.
+
+### Configuration Files
+
+- `.github/workflows/npm-publish-github-packages.yml`
+- `api/Dockerfile`
+- `docker-compose.yml`
+- `hub/Dockerfile`
+- `hub/package.json`
+
+### Guidelines
+
+- This project uses a hybrid organization
+- Follow existing patterns when adding new code
+
+## Code Style
+
+### Language: Python
+
+### Naming Conventions
+
+| Element | Convention |
+|---------|------------|
+| Files | snake_case |
+| Functions | camelCase |
+| Classes | PascalCase |
+| Constants | SCREAMING_SNAKE_CASE |
+
+### Import Style: Mixed Style
+
+### Export Style: Mixed Style
+
+
+## Error Handling
+
+### Error Handling Style: Try-Catch Blocks
+
+
+*Standard error handling pattern*
+
+```typescript
+try {
+  const result = await riskyOperation()
+  return result
+} catch (error) {
+  console.error('Operation failed:', error)
+  throw new Error('User-friendly message')
+}
+```
+
+## Common Workflows
+
+These workflows were detected from analyzing commit patterns.
+
+### Database Migration
+
+Database schema changes with migration files
+
+**Frequency**: ~10 times per month
+
+**Steps**:
+1. Create migration file
+2. Update schema definitions
+3. Generate/update types
+
+**Example commit sequence**:
+```
+fix: CI bot feedback - placeholder files, security, and schema fixes
+Merge pull request #4 from jaayslaughter-cpu/ticket-1.4-bets-log-views-indexes
+fix: change npm ci to npm install, reorder USER before EXPOSE
+```
+
+### Feature Development
+
+Standard feature implementation workflow
+
+**Frequency**: ~17 times per month
+
+**Steps**:
+1. Add feature implementation
+2. Add tests for feature
+3. Update documentation
+
+**Files typically involved**:
+- `**/api/**`
+
+**Example commit sequence**:
+```
+fix: CI bot feedback - placeholder files, security, and schema fixes
+Merge pull request #4 from jaayslaughter-cpu/ticket-1.4-bets-log-views-indexes
+fix: change npm ci to npm install, reorder USER before EXPOSE
+```
+
+### Refactoring
+
+Code refactoring and cleanup workflow
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Ensure tests pass before refactor
+2. Refactor code structure
+3. Verify tests still pass
+
+**Files typically involved**:
+- `src/**/*`
+
+**Example commit sequence**:
+```
+fix: 8 architecture improvements from CI bot review
+fix: 5 architecture refinements from CI bot review
+feat(api): FastAPI bootstrap with async SQLAlchemy
+```
+
+### Add Or Update Database Table Or Schema
+
+Adds or updates a database table, view, or index, often for new features or analytics. Includes SQL migration files and sometimes updates to related backend code.
+
+**Frequency**: ~4 times per month
+
+**Steps**:
+1. Create or update SQL migration file in db/init/*.sql
+2. Sometimes update related backend code (e.g., api/database.py, hub/src/sync.js) to use new/changed tables
+3. Commit migration and related code
+
+**Files typically involved**:
+- `db/init/01_core_reference.sql`
+- `db/init/02_projection_market_layer.sql`
+- `db/init/03_bets_log_views_indexes.sql`
+
+**Example commit sequence**:
+```
+Create or update SQL migration file in db/init/*.sql
+Sometimes update related backend code (e.g., api/database.py, hub/src/sync.js) to use new/changed tables
+Commit migration and related code
+```
+
+### Add Or Enhance Api Endpoint
+
+Adds or updates FastAPI endpoints, including new routers, services, and sometimes model or requirements updates.
+
+**Frequency**: ~3 times per month
+
+**Steps**:
+1. Create or update api/routers/*.py for endpoint logic
+2. Create or update api/services/*.py for business logic
+3. Update api/main.py to register new routers
+4. Update api/requirements.txt if new dependencies are needed
+5. Commit all related files
+
+**Files typically involved**:
+- `api/routers/*.py`
+- `api/services/*.py`
+- `api/main.py`
+- `api/requirements.txt`
+
+**Example commit sequence**:
+```
+Create or update api/routers/*.py for endpoint logic
+Create or update api/services/*.py for business logic
+Update api/main.py to register new routers
+Update api/requirements.txt if new dependencies are needed
+Commit all related files
+```
+
+### Add Or Train Ml Model
+
+Adds new ML models, training scripts, and updates model artifacts for predictions.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Create or update scripts/train_model.py for training logic
+2. Generate or update model artifact files in api/models/*.json
+3. Update api/services/predictor.py to use new models if needed
+4. Update api/requirements.txt if new ML dependencies are needed
+5. Commit all related files
+
+**Files typically involved**:
+- `scripts/train_model.py`
+- `api/models/*.json`
+- `api/services/predictor.py`
+- `api/requirements.txt`
+
+**Example commit sequence**:
+```
+Create or update scripts/train_model.py for training logic
+Generate or update model artifact files in api/models/*.json
+Update api/services/predictor.py to use new models if needed
+Update api/requirements.txt if new ML dependencies are needed
+Commit all related files
+```
+
+### Add Or Enhance Hub Sync Worker
+
+Implements or updates the Node.js hub's background sync worker for polling APIs and syncing betting markets.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Update or create hub/src/sync.js for polling logic
+2. Update related fetchers (hub/src/fetchers/*.js) for new data sources
+3. Update hub/src/server.js to integrate sync worker
+4. Update docker-compose.yml or .env.example if new env vars are needed
+5. Commit all related files
+
+**Files typically involved**:
+- `hub/src/sync.js`
+- `hub/src/fetchers/*.js`
+- `hub/src/server.js`
+- `docker-compose.yml`
+- `.env.example`
+
+**Example commit sequence**:
+```
+Update or create hub/src/sync.js for polling logic
+Update related fetchers (hub/src/fetchers/*.js) for new data sources
+Update hub/src/server.js to integrate sync worker
+Update docker-compose.yml or .env.example if new env vars are needed
+Commit all related files
+```
+
+### Add Or Enhance Dashboard Feature
+
+Adds or updates the Streamlit dashboard, including app logic, requirements, and Dockerfile.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Create or update dashboard/app.py for Streamlit UI
+2. Update dashboard/requirements.txt for new dependencies
+3. Update dashboard/Dockerfile if needed
+4. Update docker-compose.yml if dashboard service changes
+5. Commit all related files
+
+**Files typically involved**:
+- `dashboard/app.py`
+- `dashboard/requirements.txt`
+- `dashboard/Dockerfile`
+- `docker-compose.yml`
+
+**Example commit sequence**:
+```
+Create or update dashboard/app.py for Streamlit UI
+Update dashboard/requirements.txt for new dependencies
+Update dashboard/Dockerfile if needed
+Update docker-compose.yml if dashboard service changes
+Commit all related files
+```
+
+### Add Or Update Docker Orchestration
+
+Updates Docker Compose and service Dockerfiles to orchestrate multi-service deployments, often when adding new services or changing environment variables.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Update docker-compose.yml with new/changed services or env vars
+2. Update service Dockerfiles as needed (api/Dockerfile, dashboard/Dockerfile, hub/Dockerfile)
+3. Update .env.example for new environment variables
+4. Commit all related files
+
+**Files typically involved**:
+- `docker-compose.yml`
+- `api/Dockerfile`
+- `dashboard/Dockerfile`
+- `hub/Dockerfile`
+- `.env.example`
+
+**Example commit sequence**:
+```
+Update docker-compose.yml with new/changed services or env vars
+Update service Dockerfiles as needed (api/Dockerfile, dashboard/Dockerfile, hub/Dockerfile)
+Update .env.example for new environment variables
+Commit all related files
+```
+
+### Add Or Update Backend Service Logic
+
+Implements or enhances backend service logic, especially in api/services/*.py, often for analytics engines (fatigue, usage vacuums, defensive contrast, etc).
+
+**Frequency**: ~3 times per month
+
+**Steps**:
+1. Create or update api/services/*.py with new logic
+2. Update api/services/predictor.py to integrate new logic
+3. Update or create tests if needed
+4. Commit all related files
+
+**Files typically involved**:
+- `api/services/*.py`
+
+**Example commit sequence**:
+```
+Create or update api/services/*.py with new logic
+Update api/services/predictor.py to integrate new logic
+Update or create tests if needed
+Commit all related files
+```
+
+
+## Best Practices
+
+Based on analysis of the codebase, follow these practices:
+
+### Do
+
+- Use conventional commit format (feat:, fix:, etc.)
+- Use snake_case for file names
+- Prefer mixed exports
+
+### Don't
+
+- Don't write vague commit messages
+- Don't deviate from established patterns without discussion
+
+---
+
+*This skill was auto-generated by [ECC Tools](https://ecc.tools). Review and customize as needed for your team.*
diff --git a/.agents/skills/mework/agents/openai.yaml b/.agents/skills/mework/agents/openai.yaml
new file mode 100644
index 0000000..15eb651
--- /dev/null
+++ b/.agents/skills/mework/agents/openai.yaml
@@ -0,0 +1,6 @@
+interface:
+  display_name: "Mework"
+  short_description: "Repo-specific patterns and workflows for mework"
+  default_prompt: "Use the mework repo skill to follow existing architecture, testing, and workflow conventions."
+policy:
+  allow_implicit_invocation: true
\ No newline at end of file
diff --git a/.claude/commands/database-migration.md b/.claude/commands/database-migration.md
new file mode 100644
index 0000000..4ca5825
--- /dev/null
+++ b/.claude/commands/database-migration.md
@@ -0,0 +1,35 @@
+---
+name: database-migration
+description: Workflow command scaffold for database-migration in mework.
+allowed_tools: ["Bash", "Read", "Write", "Grep", "Glob"]
+---
+
+# /database-migration
+
+Use this workflow when working on **database-migration** in `mework`.
+
+## Goal
+
+Database schema changes with migration files
+
+## Common Files
+
+- Inspect the files touched by the related commits before editing.
+
+## Suggested Sequence
+
+1. Understand the current state and failure mode before editing.
+2. Make the smallest coherent change that satisfies the workflow goal.
+3. Run the most relevant verification for touched files.
+4. Summarize what changed and what still needs review.
+
+## Typical Commit Signals
+
+- Create migration file
+- Update schema definitions
+- Generate/update types
+
+## Notes
+
+- Treat this as a scaffold, not a hard-coded script.
+- Update the command if the workflow evolves materially.
\ No newline at end of file
diff --git a/.claude/commands/feature-development.md b/.claude/commands/feature-development.md
new file mode 100644
index 0000000..1dd3f71
--- /dev/null
+++ b/.claude/commands/feature-development.md
@@ -0,0 +1,35 @@
+---
+name: feature-development
+description: Workflow command scaffold for feature-development in mework.
+allowed_tools: ["Bash", "Read", "Write", "Grep", "Glob"]
+---
+
+# /feature-development
+
+Use this workflow when working on **feature-development** in `mework`.
+
+## Goal
+
+Standard feature implementation workflow
+
+## Common Files
+
+- `**/api/**`
+
+## Suggested Sequence
+
+1. Understand the current state and failure mode before editing.
+2. Make the smallest coherent change that satisfies the workflow goal.
+3. Run the most relevant verification for touched files.
+4. Summarize what changed and what still needs review.
+
+## Typical Commit Signals
+
+- Add feature implementation
+- Add tests for feature
+- Update documentation
+
+## Notes
+
+- Treat this as a scaffold, not a hard-coded script.
+- Update the command if the workflow evolves materially.
\ No newline at end of file
diff --git a/.claude/commands/refactoring.md b/.claude/commands/refactoring.md
new file mode 100644
index 0000000..033ddc5
--- /dev/null
+++ b/.claude/commands/refactoring.md
@@ -0,0 +1,35 @@
+---
+name: refactoring
+description: Workflow command scaffold for refactoring in mework.
+allowed_tools: ["Bash", "Read", "Write", "Grep", "Glob"]
+---
+
+# /refactoring
+
+Use this workflow when working on **refactoring** in `mework`.
+
+## Goal
+
+Code refactoring and cleanup workflow
+
+## Common Files
+
+- `src/**/*`
+
+## Suggested Sequence
+
+1. Understand the current state and failure mode before editing.
+2. Make the smallest coherent change that satisfies the workflow goal.
+3. Run the most relevant verification for touched files.
+4. Summarize what changed and what still needs review.
+
+## Typical Commit Signals
+
+- Ensure tests pass before refactor
+- Refactor code structure
+- Verify tests still pass
+
+## Notes
+
+- Treat this as a scaffold, not a hard-coded script.
+- Update the command if the workflow evolves materially.
\ No newline at end of file
diff --git a/.claude/ecc-tools.json b/.claude/ecc-tools.json
new file mode 100644
index 0000000..5a21467
--- /dev/null
+++ b/.claude/ecc-tools.json
@@ -0,0 +1,261 @@
+{
+  "version": "1.3",
+  "schemaVersion": "1.0",
+  "generatedBy": "ecc-tools",
+  "generatedAt": "2026-03-20T03:03:49.551Z",
+  "repo": "https://github.com/jaayslaughter-cpu/mework",
+  "profiles": {
+    "requested": "full",
+    "recommended": "full",
+    "effective": "developer",
+    "requestedAlias": "full",
+    "recommendedAlias": "full",
+    "effectiveAlias": "developer"
+  },
+  "requestedProfile": "full",
+  "profile": "developer",
+  "recommendedProfile": "full",
+  "effectiveProfile": "developer",
+  "tier": "free",
+  "requestedComponents": [
+    "repo-baseline",
+    "workflow-automation",
+    "security-audits",
+    "research-tooling",
+    "team-rollout",
+    "governance-controls"
+  ],
+  "selectedComponents": [
+    "repo-baseline",
+    "workflow-automation"
+  ],
+  "requestedAddComponents": [],
+  "requestedRemoveComponents": [],
+  "blockedRemovalComponents": [],
+  "tierFilteredComponents": [
+    "security-audits",
+    "research-tooling",
+    "team-rollout",
+    "governance-controls"
+  ],
+  "requestedRootPackages": [
+    "runtime-core",
+    "workflow-pack",
+    "agentshield-pack",
+    "research-pack",
+    "team-config-sync",
+    "enterprise-controls"
+  ],
+  "selectedRootPackages": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "requestedPackages": [
+    "runtime-core",
+    "workflow-pack",
+    "agentshield-pack",
+    "research-pack",
+    "team-config-sync",
+    "enterprise-controls"
+  ],
+  "requestedAddPackages": [],
+  "requestedRemovePackages": [],
+  "selectedPackages": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "packages": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "blockedRemovalPackages": [],
+  "tierFilteredRootPackages": [
+    "agentshield-pack",
+    "research-pack",
+    "team-config-sync",
+    "enterprise-controls"
+  ],
+  "tierFilteredPackages": [
+    "agentshield-pack",
+    "research-pack",
+    "team-config-sync",
+    "enterprise-controls"
+  ],
+  "conflictingPackages": [],
+  "dependencyGraph": {
+    "runtime-core": [],
+    "workflow-pack": [
+      "runtime-core"
+    ]
+  },
+  "resolutionOrder": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "requestedModules": [
+    "runtime-core",
+    "workflow-pack",
+    "agentshield-pack",
+    "research-pack",
+    "team-config-sync",
+    "enterprise-controls"
+  ],
+  "selectedModules": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "modules": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "managedFiles": [
+    ".claude/skills/mework/SKILL.md",
+    ".agents/skills/mework/SKILL.md",
+    ".agents/skills/mework/agents/openai.yaml",
+    ".claude/identity.json",
+    ".codex/config.toml",
+    ".codex/AGENTS.md",
+    ".codex/agents/explorer.toml",
+    ".codex/agents/reviewer.toml",
+    ".codex/agents/docs-researcher.toml",
+    ".claude/homunculus/instincts/inherited/mework-instincts.yaml",
+    ".claude/commands/database-migration.md",
+    ".claude/commands/feature-development.md",
+    ".claude/commands/refactoring.md"
+  ],
+  "packageFiles": {
+    "runtime-core": [
+      ".claude/skills/mework/SKILL.md",
+      ".agents/skills/mework/SKILL.md",
+      ".agents/skills/mework/agents/openai.yaml",
+      ".claude/identity.json",
+      ".codex/config.toml",
+      ".codex/AGENTS.md",
+      ".codex/agents/explorer.toml",
+      ".codex/agents/reviewer.toml",
+      ".codex/agents/docs-researcher.toml",
+      ".claude/homunculus/instincts/inherited/mework-instincts.yaml"
+    ],
+    "workflow-pack": [
+      ".claude/commands/database-migration.md",
+      ".claude/commands/feature-development.md",
+      ".claude/commands/refactoring.md"
+    ]
+  },
+  "moduleFiles": {
+    "runtime-core": [
+      ".claude/skills/mework/SKILL.md",
+      ".agents/skills/mework/SKILL.md",
+      ".agents/skills/mework/agents/openai.yaml",
+      ".claude/identity.json",
+      ".codex/config.toml",
+      ".codex/AGENTS.md",
+      ".codex/agents/explorer.toml",
+      ".codex/agents/reviewer.toml",
+      ".codex/agents/docs-researcher.toml",
+      ".claude/homunculus/instincts/inherited/mework-instincts.yaml"
+    ],
+    "workflow-pack": [
+      ".claude/commands/database-migration.md",
+      ".claude/commands/feature-development.md",
+      ".claude/commands/refactoring.md"
+    ]
+  },
+  "files": [
+    {
+      "moduleId": "runtime-core",
+      "path": ".claude/skills/mework/SKILL.md",
+      "description": "Repository-specific Claude Code skill generated from git history."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".agents/skills/mework/SKILL.md",
+      "description": "Codex-facing copy of the generated repository skill."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".agents/skills/mework/agents/openai.yaml",
+      "description": "Codex skill metadata so the repo skill appears cleanly in the skill interface."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".claude/identity.json",
+      "description": "Suggested identity.json baseline derived from repository conventions."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/config.toml",
+      "description": "Repo-local Codex MCP and multi-agent baseline aligned with ECC defaults."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/AGENTS.md",
+      "description": "Codex usage guide that points at the generated repo skill and workflow bundle."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/agents/explorer.toml",
+      "description": "Read-only explorer role config for Codex multi-agent work."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/agents/reviewer.toml",
+      "description": "Read-only reviewer role config focused on correctness and security."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/agents/docs-researcher.toml",
+      "description": "Read-only docs researcher role config for API verification."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".claude/homunculus/instincts/inherited/mework-instincts.yaml",
+      "description": "Continuous-learning instincts derived from repository patterns."
+    },
+    {
+      "moduleId": "workflow-pack",
+      "path": ".claude/commands/database-migration.md",
+      "description": "Workflow command scaffold for database-migration."
+    },
+    {
+      "moduleId": "workflow-pack",
+      "path": ".claude/commands/feature-development.md",
+      "description": "Workflow command scaffold for feature-development."
+    },
+    {
+      "moduleId": "workflow-pack",
+      "path": ".claude/commands/refactoring.md",
+      "description": "Workflow command scaffold for refactoring."
+    }
+  ],
+  "workflows": [
+    {
+      "command": "database-migration",
+      "path": ".claude/commands/database-migration.md"
+    },
+    {
+      "command": "feature-development",
+      "path": ".claude/commands/feature-development.md"
+    },
+    {
+      "command": "refactoring",
+      "path": ".claude/commands/refactoring.md"
+    }
+  ],
+  "adapters": {
+    "claudeCode": {
+      "skillPath": ".claude/skills/mework/SKILL.md",
+      "identityPath": ".claude/identity.json",
+      "commandPaths": [
+        ".claude/commands/database-migration.md",
+        ".claude/commands/feature-development.md",
+        ".claude/commands/refactoring.md"
+      ]
+    },
+    "codex": {
+      "configPath": ".codex/config.toml",
+      "agentsGuidePath": ".codex/AGENTS.md",
+      "skillPath": ".agents/skills/mework/SKILL.md"
+    }
+  }
+}
\ No newline at end of file
diff --git a/.claude/homunculus/instincts/inherited/mework-instincts.yaml b/.claude/homunculus/instincts/inherited/mework-instincts.yaml
new file mode 100644
index 0000000..6da1677
--- /dev/null
+++ b/.claude/homunculus/instincts/inherited/mework-instincts.yaml
@@ -0,0 +1,357 @@
+# Instincts generated from https://github.com/jaayslaughter-cpu/mework
+# Generated: 2026-03-20T03:04:10.701Z
+# Version: 2.0
+# NOTE: This file supplements (does not replace) any existing curated instincts.
+# High-confidence manually curated instincts should be preserved alongside these.
+
+---
+id: mework-commit-conventional
+trigger: "when writing a commit message"
+confidence: 0.85
+domain: git
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Commit Conventional
+
+## Action
+
+Use conventional commit format with prefixes: feat, fix, chore
+
+## Evidence
+
+- 55 commits analyzed
+- Detected conventional commit pattern
+- Examples: feat: PropIQ complete implementation [fix/sync-worker-bugs], fix(docker): Add REDIS_PASSWORD env var to hub service
+
+---
+id: mework-commit-length
+trigger: "when writing a commit message"
+confidence: 0.6
+domain: git
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Commit Length
+
+## Action
+
+Write moderate-length commit messages (~58 characters)
+
+## Evidence
+
+- Average commit message length: 58 chars
+- Based on 55 commits
+
+---
+id: mework-naming-files
+trigger: "when creating a new file"
+confidence: 0.8
+domain: code-style
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Naming Files
+
+## Action
+
+Use snake_case naming convention
+
+## Evidence
+
+- Analyzed file naming patterns in repository
+- Dominant pattern: snake_case
+
+---
+id: mework-export-style
+trigger: "when exporting from a module"
+confidence: 0.7
+domain: code-style
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Export Style
+
+## Action
+
+Prefer mixed exports
+
+## Evidence
+
+- Export pattern analysis
+- Dominant style: mixed
+
+---
+id: mework-test-separate
+trigger: "when writing tests"
+confidence: 0.8
+domain: testing
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Test Separate
+
+## Action
+
+Place tests in the tests/ or __tests__/ directory, mirroring src structure
+
+## Evidence
+
+- Separate test directory pattern detected
+- Tests live in dedicated test folders
+
+---
+id: mework-workflow-database-migration
+trigger: "when modifying the database schema or adding tables"
+confidence: 0.9
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Database Migration
+
+## Action
+
+Follow the database-migration workflow:
+1. Create migration file
+2. Update schema definitions
+3. Generate/update types
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~10x per month
+- Files: 
+
+---
+id: mework-workflow-feature-development
+trigger: "when implementing a new feature"
+confidence: 0.9
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Feature Development
+
+## Action
+
+Follow the feature-development workflow:
+1. Add feature implementation
+2. Add tests for feature
+3. Update documentation
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~17x per month
+- Files: **/api/**
+
+---
+id: mework-workflow-refactoring
+trigger: "when refactoring code"
+confidence: 0.6
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Refactoring
+
+## Action
+
+Follow the refactoring workflow:
+1. Ensure tests pass before refactor
+2. Refactor code structure
+3. Verify tests still pass
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~2x per month
+- Files: src/**/*
+
+---
+id: mework-workflow-add-or-update-database-table-or-schema
+trigger: "when doing add or update database table or schema"
+confidence: 0.7
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Add Or Update Database Table Or Schema
+
+## Action
+
+Follow the add-or-update-database-table-or-schema workflow:
+1. Create or update SQL migration file in db/init/*.sql
+2. Sometimes update related backend code (e.g., api/database.py, hub/src/sync.js) to use new/changed tables
+3. Commit migration and related code
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~4x per month
+- Files: db/init/01_core_reference.sql, db/init/02_projection_market_layer.sql, db/init/03_bets_log_views_indexes.sql
+
+---
+id: mework-workflow-add-or-enhance-api-endpoint
+trigger: "when doing add or enhance api endpoint"
+confidence: 0.65
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Add Or Enhance Api Endpoint
+
+## Action
+
+Follow the add-or-enhance-api-endpoint workflow:
+1. Create or update api/routers/*.py for endpoint logic
+2. Create or update api/services/*.py for business logic
+3. Update api/main.py to register new routers
+4. Update api/requirements.txt if new dependencies are needed
+5. Commit all related files
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~3x per month
+- Files: api/routers/*.py, api/services/*.py, api/main.py
+
+---
+id: mework-workflow-add-or-train-ml-model
+trigger: "when doing add or train ml model"
+confidence: 0.6
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Add Or Train Ml Model
+
+## Action
+
+Follow the add-or-train-ml-model workflow:
+1. Create or update scripts/train_model.py for training logic
+2. Generate or update model artifact files in api/models/*.json
+3. Update api/services/predictor.py to use new models if needed
+4. Update api/requirements.txt if new ML dependencies are needed
+5. Commit all related files
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~2x per month
+- Files: scripts/train_model.py, api/models/*.json, api/services/predictor.py
+
+---
+id: mework-workflow-add-or-enhance-hub-sync-worker
+trigger: "when doing add or enhance hub sync worker"
+confidence: 0.6
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Add Or Enhance Hub Sync Worker
+
+## Action
+
+Follow the add-or-enhance-hub-sync-worker workflow:
+1. Update or create hub/src/sync.js for polling logic
+2. Update related fetchers (hub/src/fetchers/*.js) for new data sources
+3. Update hub/src/server.js to integrate sync worker
+4. Update docker-compose.yml or .env.example if new env vars are needed
+5. Commit all related files
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~2x per month
+- Files: hub/src/sync.js, hub/src/fetchers/*.js, hub/src/server.js
+
+---
+id: mework-workflow-add-or-enhance-dashboard-feature
+trigger: "when doing add or enhance dashboard feature"
+confidence: 0.6
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Add Or Enhance Dashboard Feature
+
+## Action
+
+Follow the add-or-enhance-dashboard-feature workflow:
+1. Create or update dashboard/app.py for Streamlit UI
+2. Update dashboard/requirements.txt for new dependencies
+3. Update dashboard/Dockerfile if needed
+4. Update docker-compose.yml if dashboard service changes
+5. Commit all related files
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~2x per month
+- Files: dashboard/app.py, dashboard/requirements.txt, dashboard/Dockerfile
+
+---
+id: mework-workflow-add-or-update-docker-orchestration
+trigger: "when doing add or update docker orchestration"
+confidence: 0.6
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Add Or Update Docker Orchestration
+
+## Action
+
+Follow the add-or-update-docker-orchestration workflow:
+1. Update docker-compose.yml with new/changed services or env vars
+2. Update service Dockerfiles as needed (api/Dockerfile, dashboard/Dockerfile, hub/Dockerfile)
+3. Update .env.example for new environment variables
+4. Commit all related files
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~2x per month
+- Files: docker-compose.yml, api/Dockerfile, dashboard/Dockerfile
+
+---
+id: mework-workflow-add-or-update-backend-service-logic
+trigger: "when doing add or update backend service logic"
+confidence: 0.65
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/jaayslaughter-cpu/mework
+---
+
+# Mework Workflow Add Or Update Backend Service Logic
+
+## Action
+
+Follow the add-or-update-backend-service-logic workflow:
+1. Create or update api/services/*.py with new logic
+2. Update api/services/predictor.py to integrate new logic
+3. Update or create tests if needed
+4. Commit all related files
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~3x per month
+- Files: api/services/*.py
+
diff --git a/.claude/identity.json b/.claude/identity.json
new file mode 100644
index 0000000..aea70de
--- /dev/null
+++ b/.claude/identity.json
@@ -0,0 +1,14 @@
+{
+  "version": "2.0",
+  "technicalLevel": "technical",
+  "preferredStyle": {
+    "verbosity": "moderate",
+    "codeComments": true,
+    "explanations": true
+  },
+  "domains": [
+    "python"
+  ],
+  "suggestedBy": "ecc-tools-repo-analysis",
+  "createdAt": "2026-03-20T03:04:10.701Z"
+}
\ No newline at end of file
diff --git a/.claude/skills/mework/SKILL.md b/.claude/skills/mework/SKILL.md
new file mode 100644
index 0000000..a26498a
--- /dev/null
+++ b/.claude/skills/mework/SKILL.md
@@ -0,0 +1,417 @@
+---
+name: mework-conventions
+description: Development conventions and patterns for mework. Python project with conventional commits.
+---
+
+# Mework Conventions
+
+> Generated from [jaayslaughter-cpu/mework](https://github.com/jaayslaughter-cpu/mework) on 2026-03-20
+
+## Overview
+
+This skill teaches Claude the development patterns and conventions used in mework.
+
+## Tech Stack
+
+- **Primary Language**: Python
+- **Architecture**: hybrid module organization
+- **Test Location**: separate
+
+## When to Use This Skill
+
+Activate this skill when:
+- Making changes to this repository
+- Adding new features following established patterns
+- Writing tests that match project conventions
+- Creating commits with proper message format
+
+## Commit Conventions
+
+Follow these commit message conventions based on 55 analyzed commits.
+
+### Commit Style: Conventional Commits
+
+### Prefixes Used
+
+- `feat`
+- `fix`
+- `chore`
+
+### Message Guidelines
+
+- Average message length: ~58 characters
+- Keep first line concise and descriptive
+- Use imperative mood ("Add feature" not "Added feature")
+
+
+*Commit message example*
+
+```text
+feat: PropIQ complete implementation [fix/sync-worker-bugs]
+```
+
+*Commit message example*
+
+```text
+fix(docker): Add REDIS_PASSWORD env var to hub service
+```
+
+*Commit message example*
+
+```text
+chore: Tighten CORS origins, remove wildcard
+```
+
+*Commit message example*
+
+```text
+Merge pull request #25 from jaayslaughter-cpu/ticket-6.4-defensive-contrast
+```
+
+*Commit message example*
+
+```text
+Merge branch 'main' into ticket-6.4-defensive-contrast
+```
+
+*Commit message example*
+
+```text
+chore: Remove Streamlit dashboard
+```
+
+*Commit message example*
+
+```text
+feat(scripts): Enhanced training pipeline with multi-source data
+```
+
+*Commit message example*
+
+```text
+feat(api): Defensive Contrast Engine for batted-ball profile mismatches
+```
+
+## Architecture
+
+### Project Structure: Single Package
+
+This project uses **hybrid** module organization.
+
+### Configuration Files
+
+- `.github/workflows/npm-publish-github-packages.yml`
+- `api/Dockerfile`
+- `docker-compose.yml`
+- `hub/Dockerfile`
+- `hub/package.json`
+
+### Guidelines
+
+- This project uses a hybrid organization
+- Follow existing patterns when adding new code
+
+## Code Style
+
+### Language: Python
+
+### Naming Conventions
+
+| Element | Convention |
+|---------|------------|
+| Files | snake_case |
+| Functions | camelCase |
+| Classes | PascalCase |
+| Constants | SCREAMING_SNAKE_CASE |
+
+### Import Style: Mixed Style
+
+### Export Style: Mixed Style
+
+
+## Error Handling
+
+### Error Handling Style: Try-Catch Blocks
+
+
+*Standard error handling pattern*
+
+```typescript
+try {
+  const result = await riskyOperation()
+  return result
+} catch (error) {
+  console.error('Operation failed:', error)
+  throw new Error('User-friendly message')
+}
+```
+
+## Common Workflows
+
+These workflows were detected from analyzing commit patterns.
+
+### Database Migration
+
+Database schema changes with migration files
+
+**Frequency**: ~10 times per month
+
+**Steps**:
+1. Create migration file
+2. Update schema definitions
+3. Generate/update types
+
+**Example commit sequence**:
+```
+fix: CI bot feedback - placeholder files, security, and schema fixes
+Merge pull request #4 from jaayslaughter-cpu/ticket-1.4-bets-log-views-indexes
+fix: change npm ci to npm install, reorder USER before EXPOSE
+```
+
+### Feature Development
+
+Standard feature implementation workflow
+
+**Frequency**: ~17 times per month
+
+**Steps**:
+1. Add feature implementation
+2. Add tests for feature
+3. Update documentation
+
+**Files typically involved**:
+- `**/api/**`
+
+**Example commit sequence**:
+```
+fix: CI bot feedback - placeholder files, security, and schema fixes
+Merge pull request #4 from jaayslaughter-cpu/ticket-1.4-bets-log-views-indexes
+fix: change npm ci to npm install, reorder USER before EXPOSE
+```
+
+### Refactoring
+
+Code refactoring and cleanup workflow
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Ensure tests pass before refactor
+2. Refactor code structure
+3. Verify tests still pass
+
+**Files typically involved**:
+- `src/**/*`
+
+**Example commit sequence**:
+```
+fix: 8 architecture improvements from CI bot review
+fix: 5 architecture refinements from CI bot review
+feat(api): FastAPI bootstrap with async SQLAlchemy
+```
+
+### Add Or Update Database Table Or Schema
+
+Adds or updates a database table, view, or index, often for new features or analytics. Includes SQL migration files and sometimes updates to related backend code.
+
+**Frequency**: ~4 times per month
+
+**Steps**:
+1. Create or update SQL migration file in db/init/*.sql
+2. Sometimes update related backend code (e.g., api/database.py, hub/src/sync.js) to use new/changed tables
+3. Commit migration and related code
+
+**Files typically involved**:
+- `db/init/01_core_reference.sql`
+- `db/init/02_projection_market_layer.sql`
+- `db/init/03_bets_log_views_indexes.sql`
+
+**Example commit sequence**:
+```
+Create or update SQL migration file in db/init/*.sql
+Sometimes update related backend code (e.g., api/database.py, hub/src/sync.js) to use new/changed tables
+Commit migration and related code
+```
+
+### Add Or Enhance Api Endpoint
+
+Adds or updates FastAPI endpoints, including new routers, services, and sometimes model or requirements updates.
+
+**Frequency**: ~3 times per month
+
+**Steps**:
+1. Create or update api/routers/*.py for endpoint logic
+2. Create or update api/services/*.py for business logic
+3. Update api/main.py to register new routers
+4. Update api/requirements.txt if new dependencies are needed
+5. Commit all related files
+
+**Files typically involved**:
+- `api/routers/*.py`
+- `api/services/*.py`
+- `api/main.py`
+- `api/requirements.txt`
+
+**Example commit sequence**:
+```
+Create or update api/routers/*.py for endpoint logic
+Create or update api/services/*.py for business logic
+Update api/main.py to register new routers
+Update api/requirements.txt if new dependencies are needed
+Commit all related files
+```
+
+### Add Or Train Ml Model
+
+Adds new ML models, training scripts, and updates model artifacts for predictions.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Create or update scripts/train_model.py for training logic
+2. Generate or update model artifact files in api/models/*.json
+3. Update api/services/predictor.py to use new models if needed
+4. Update api/requirements.txt if new ML dependencies are needed
+5. Commit all related files
+
+**Files typically involved**:
+- `scripts/train_model.py`
+- `api/models/*.json`
+- `api/services/predictor.py`
+- `api/requirements.txt`
+
+**Example commit sequence**:
+```
+Create or update scripts/train_model.py for training logic
+Generate or update model artifact files in api/models/*.json
+Update api/services/predictor.py to use new models if needed
+Update api/requirements.txt if new ML dependencies are needed
+Commit all related files
+```
+
+### Add Or Enhance Hub Sync Worker
+
+Implements or updates the Node.js hub's background sync worker for polling APIs and syncing betting markets.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Update or create hub/src/sync.js for polling logic
+2. Update related fetchers (hub/src/fetchers/*.js) for new data sources
+3. Update hub/src/server.js to integrate sync worker
+4. Update docker-compose.yml or .env.example if new env vars are needed
+5. Commit all related files
+
+**Files typically involved**:
+- `hub/src/sync.js`
+- `hub/src/fetchers/*.js`
+- `hub/src/server.js`
+- `docker-compose.yml`
+- `.env.example`
+
+**Example commit sequence**:
+```
+Update or create hub/src/sync.js for polling logic
+Update related fetchers (hub/src/fetchers/*.js) for new data sources
+Update hub/src/server.js to integrate sync worker
+Update docker-compose.yml or .env.example if new env vars are needed
+Commit all related files
+```
+
+### Add Or Enhance Dashboard Feature
+
+Adds or updates the Streamlit dashboard, including app logic, requirements, and Dockerfile.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Create or update dashboard/app.py for Streamlit UI
+2. Update dashboard/requirements.txt for new dependencies
+3. Update dashboard/Dockerfile if needed
+4. Update docker-compose.yml if dashboard service changes
+5. Commit all related files
+
+**Files typically involved**:
+- `dashboard/app.py`
+- `dashboard/requirements.txt`
+- `dashboard/Dockerfile`
+- `docker-compose.yml`
+
+**Example commit sequence**:
+```
+Create or update dashboard/app.py for Streamlit UI
+Update dashboard/requirements.txt for new dependencies
+Update dashboard/Dockerfile if needed
+Update docker-compose.yml if dashboard service changes
+Commit all related files
+```
+
+### Add Or Update Docker Orchestration
+
+Updates Docker Compose and service Dockerfiles to orchestrate multi-service deployments, often when adding new services or changing environment variables.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Update docker-compose.yml with new/changed services or env vars
+2. Update service Dockerfiles as needed (api/Dockerfile, dashboard/Dockerfile, hub/Dockerfile)
+3. Update .env.example for new environment variables
+4. Commit all related files
+
+**Files typically involved**:
+- `docker-compose.yml`
+- `api/Dockerfile`
+- `dashboard/Dockerfile`
+- `hub/Dockerfile`
+- `.env.example`
+
+**Example commit sequence**:
+```
+Update docker-compose.yml with new/changed services or env vars
+Update service Dockerfiles as needed (api/Dockerfile, dashboard/Dockerfile, hub/Dockerfile)
+Update .env.example for new environment variables
+Commit all related files
+```
+
+### Add Or Update Backend Service Logic
+
+Implements or enhances backend service logic, especially in api/services/*.py, often for analytics engines (fatigue, usage vacuums, defensive contrast, etc).
+
+**Frequency**: ~3 times per month
+
+**Steps**:
+1. Create or update api/services/*.py with new logic
+2. Update api/services/predictor.py to integrate new logic
+3. Update or create tests if needed
+4. Commit all related files
+
+**Files typically involved**:
+- `api/services/*.py`
+
+**Example commit sequence**:
+```
+Create or update api/services/*.py with new logic
+Update api/services/predictor.py to integrate new logic
+Update or create tests if needed
+Commit all related files
+```
+
+
+## Best Practices
+
+Based on analysis of the codebase, follow these practices:
+
+### Do
+
+- Use conventional commit format (feat:, fix:, etc.)
+- Use snake_case for file names
+- Prefer mixed exports
+
+### Don't
+
+- Don't write vague commit messages
+- Don't deviate from established patterns without discussion
+
+---
+
+*This skill was auto-generated by [ECC Tools](https://ecc.tools). Review and customize as needed for your team.*
diff --git a/.codex/AGENTS.md b/.codex/AGENTS.md
new file mode 100644
index 0000000..32b1802
--- /dev/null
+++ b/.codex/AGENTS.md
@@ -0,0 +1,28 @@
+# ECC for Codex CLI
+
+This supplements the root `AGENTS.md` with a repo-local ECC baseline.
+
+## Repo Skill
+
+- Repo-generated Codex skill: `.agents/skills/mework/SKILL.md`
+- Claude-facing companion skill: `.claude/skills/mework/SKILL.md`
+- Keep user-specific credentials and private MCPs in `~/.codex/config.toml`, not in this repo.
+
+## MCP Baseline
+
+Treat `.codex/config.toml` as the default ECC-safe baseline for work in this repository.
+The generated baseline enables GitHub, Context7, Exa, Memory, Playwright, and Sequential Thinking.
+
+## Multi-Agent Support
+
+- Explorer: read-only evidence gathering
+- Reviewer: correctness, security, and regression review
+- Docs researcher: API and release-note verification
+
+## Workflow Files
+
+- `.claude/commands/database-migration.md`
+- `.claude/commands/feature-development.md`
+- `.claude/commands/refactoring.md`
+
+Use these workflow files as reusable task scaffolds when the detected repository workflows recur.
\ No newline at end of file
diff --git a/.codex/agents/docs-researcher.toml b/.codex/agents/docs-researcher.toml
new file mode 100644
index 0000000..0daae57
--- /dev/null
+++ b/.codex/agents/docs-researcher.toml
@@ -0,0 +1,9 @@
+model = "gpt-5.4"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+
+developer_instructions = """
+Verify APIs, framework behavior, and release-note claims against primary documentation before changes land.
+Cite the exact docs or file paths that support each claim.
+Do not invent undocumented behavior.
+"""
\ No newline at end of file
diff --git a/.codex/agents/explorer.toml b/.codex/agents/explorer.toml
new file mode 100644
index 0000000..732df7a
--- /dev/null
+++ b/.codex/agents/explorer.toml
@@ -0,0 +1,9 @@
+model = "gpt-5.4"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+
+developer_instructions = """
+Stay in exploration mode.
+Trace the real execution path, cite files and symbols, and avoid proposing fixes unless the parent agent asks for them.
+Prefer targeted search and file reads over broad scans.
+"""
\ No newline at end of file
diff --git a/.codex/agents/reviewer.toml b/.codex/agents/reviewer.toml
new file mode 100644
index 0000000..b13ed9c
--- /dev/null
+++ b/.codex/agents/reviewer.toml
@@ -0,0 +1,9 @@
+model = "gpt-5.4"
+model_reasoning_effort = "high"
+sandbox_mode = "read-only"
+
+developer_instructions = """
+Review like an owner.
+Prioritize correctness, security, behavioral regressions, and missing tests.
+Lead with concrete findings and avoid style-only feedback unless it hides a real bug.
+"""
\ No newline at end of file
diff --git a/.codex/config.toml b/.codex/config.toml
new file mode 100644
index 0000000..bc1ee67
--- /dev/null
+++ b/.codex/config.toml
@@ -0,0 +1,48 @@
+#:schema https://developers.openai.com/codex/config-schema.json
+
+# ECC Tools generated Codex baseline
+approval_policy = "on-request"
+sandbox_mode = "workspace-write"
+web_search = "live"
+
+[mcp_servers.github]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-github"]
+
+[mcp_servers.context7]
+command = "npx"
+args = ["-y", "@upstash/context7-mcp@latest"]
+
+[mcp_servers.exa]
+url = "https://mcp.exa.ai/mcp"
+
+[mcp_servers.memory]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-memory"]
+
+[mcp_servers.playwright]
+command = "npx"
+args = ["-y", "@playwright/mcp@latest", "--extension"]
+
+[mcp_servers.sequential-thinking]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-sequential-thinking"]
+
+[features]
+multi_agent = true
+
+[agents]
+max_threads = 6
+max_depth = 1
+
+[agents.explorer]
+description = "Read-only codebase explorer for gathering evidence before changes are proposed."
+config_file = "agents/explorer.toml"
+
+[agents.reviewer]
+description = "PR reviewer focused on correctness, security, and missing tests."
+config_file = "agents/reviewer.toml"
+
+[agents.docs_researcher]
+description = "Documentation specialist that verifies APIs, framework behavior, and release notes."
+config_file = "agents/docs-researcher.toml"
\ No newline at end of file
diff --git a/.env.example b/.env.example
index d04b12e..65fa285 100644
--- a/.env.example
+++ b/.env.example
@@ -1,3 +1,31 @@
+# ─── PostgreSQL ──────────────────────────────────────
+POSTGRES_DB=propiq
+POSTGRES_USER=propiq_admin
+POSTGRES_PASSWORD=REPLACE_ME
+POSTGRES_HOST=postgres
+
+# ─── Redis ───────────────────────────────────────────
+REDIS_PASSWORD=REPLACE_ME
+REDIS_URL=redis://:REPLACE_ME@redis:6379
+
+# ─── SportsData.io ───────────────────────────────────
+SPORTSDATA_API_KEY=REPLACE_ME
+
+# ─── The Odds API ─────────────────────────────────────
+ODDS_API_KEY=REPLACE_ME
+
+# ─── SportsBlaze Advanced Stats ───────────────────────
+SPORTSBLAZE_API_KEY=REPLACE_ME
+
+# ─── Tank01 (via RapidAPI) ───────────────────────────
+TANK01_RAPIDAPI_KEY=REPLACE_ME
+
+# ─── Apify (Web Scraping) ────────────────────────────
+APIFY_API_TOKEN=REPLACE_ME
+
+# ─── Next.js Frontend ────────────────────────────────
+NEXT_PUBLIC_HUB_URL=http://localhost:3002
+NEXT_PUBLIC_ENGINE_URL=http://localhost:8000
 # PropIQ Agent Army — Environment Variables
 # Copy to .env and fill in your values
 
diff --git a/api/requirements.txt b/api/requirements.txt
index c710255..ce661de 100644
--- a/api/requirements.txt
+++ b/api/requirements.txt
@@ -4,7 +4,11 @@ sqlalchemy==2.0.28
 asyncpg==0.29.0
 pybaseball==2.2.7
 pandas==2.2.1
+numpy==1.26.4
 lxml==5.1.0
 xgboost==2.0.3
 scikit-learn==1.5.0
 pydantic==2.6.3
+requests==2.31.0
+httpx==0.27.0
+python-dotenv==1.0.1
diff --git a/hub/src/sync.js b/hub/src/sync.js
index a15bc1e..ba4aeb9 100644
--- a/hub/src/sync.js
+++ b/hub/src/sync.js
@@ -1,5 +1,5 @@
 // hub/src/sync.js
-// Unified 15-second polling loop for real-time data sync.
+// Unified 60-second polling loop for real-time data sync.
 
 const { Pool } = require('pg');
 const oddsapi = require('./fetchers/oddsapi');
@@ -7,20 +7,22 @@ const espn = require('./fetchers/espn');
 
 const pool = new Pool({
   user: process.env.POSTGRES_USER,
-  host: 'postgres',
+  host: process.env.POSTGRES_HOST || 'postgres',
   database: process.env.POSTGRES_DB,
   password: process.env.POSTGRES_PASSWORD,
   port: 5432,
 });
 
-async function syncLoop() {
+const syncLoop = async () => {
   try {
-    // 1. Fetch ESPN Live Scores (Keeps cache piping hot for the REST API)
-    await espn.getLiveScores().catch(err => console.warn('[Sync] ESPN fetch warning:', err.message));
+    // 1. Fetch ESPN Live Scores (Keeps cache hot for REST API)
+    await espn.getLiveScores().catch(() => {});
 
     // 2. Fetch and UPSERT Odds API lines
     const events = await oddsapi.getMLBEvents().catch(() => []);
-    if (!events || events.length === 0) return;
+    if (!events || events.length === 0) {
+      return;
+    }
 
     for (const event of events) {
       try {
@@ -32,12 +34,34 @@ async function syncLoop() {
             // 1. Aggregate Over/Under outcomes in JavaScript memory first
 
             for (const outcome of market.outcomes) {
-              const point = outcome.point ?? 0.5;
-              const marketId = `${event.id}_${book.key}_${market.key}_${outcome.description || 'base'}_${point}`.replace(/\s+/g, '_').toLowerCase();
-              
+              const desc = outcome.description || 'base';
+              if (!outcomeMap[desc]) {
+                outcomeMap[desc] = { over_odds: null, under_odds: null, point: outcome.point ?? 0.5 };
+              }
+              const key = oddsKeyMap[outcome.name];
+              if (key) {
+                outcomeMap[desc][key] = outcome.price;
+              }
+              }
+              const nameLower = (outcome.name || '').toLowerCase();
+              if (nameLower === 'over') {
+                outcomeMap[desc].over_odds = outcome.price;
+              } else if (nameLower === 'under') {
+                outcomeMap[desc].under_odds = outcome.price;
+              }
+            }
+
+            // Now insert each aggregated market row
+            for (const [desc, data] of Object.entries(outcomeMap)) {
+              if (data.over_odds === null && data.under_odds === null) continue;
+
+              const marketId = `${event.id}_${book.key}_${market.key}_${desc}_${data.point}`
+                .replace(/\s+/g, '_')
+                .toLowerCase();
+
               const query = `
                 INSERT INTO betting_markets (
-                  market_id, game_id, pitcher_id, sportsbook, prop_category, 
+                  market_id, game_id, pitcher_id, sportsbook, prop_category,
                   line, over_odds, under_odds, updated_at
                 ) VALUES (
                   $1, $2, NULL, $3, $4, $5, $6, $7, NOW()
@@ -61,22 +85,19 @@ async function syncLoop() {
       }
     }
   } catch (error) {
-    console.error('[Sync] Critical error in unified loop:', error.message);
   }
 }
 
-async function startSyncWorker() {
-  console.log('🚀 Starting Unified 60-Second Polling Loop...');
-  
+window.startSyncWorker = function startSyncWorker() {
+
   async function runLoop() {
     const start = Date.now();
     await syncLoop();
     const elapsed = Date.now() - start;
-    
     setTimeout(runLoop, Math.max(0, 60000 - elapsed));
   }
-  
-  runLoop(); // Start first run immediately
-}
+
+  runLoop(); // Start immediately
+};
 
 module.exports = { startSyncWorker };