opencastle 0.1.0

package/src/orchestrator/customizations/logs/sessions.ndjson

@@ -0,0 +1 @@
+

package/src/orchestrator/customizations/project/docs-structure.md

@@ -0,0 +1,23 @@
+# Documentation Structure
+
+<!-- Populated by the `bootstrap-customizations` prompt based on project structure. -->
+
+Project-specific documentation layout referenced by the `documentation-standards` skill.
+
+## Directory Tree
+
+<!-- Map your project's docs/ directory here -->
+
+```
+docs/
+├── README.md               — Documentation index
+└── ...                     — Add entries as docs are created
+```
+
+## Practices
+
+- **Check Known Issues** before starting any task
+- **Review Architecture** docs for context
+- **Update roadmap** after completing features
+- **Add new issues** with: Issue ID, Status, Severity, Evidence, Root Cause, Solution Options
+- **Archive** outdated docs rather than deleting

package/src/orchestrator/customizations/project/tracker-config.md

@@ -0,0 +1,45 @@
+# Task Tracker Configuration
+
+<!-- Populated by the `bootstrap-customizations` prompt.
+     Rename this file to match your tracker: linear-config.md, jira-config.md, etc. -->
+
+Project-specific task tracker details referenced by the `task-management` skill.
+
+## Workspace
+
+- **Team:** _(team name)_
+- **Prefix:** _(issue prefix, e.g., PRJ)_
+- **Team ID:** _(team UUID)_
+
+## Workflow State IDs
+
+<!-- The `update_issue` MCP tool requires state UUIDs (not names) for status changes.
+     Populate these from your task tracker's settings. -->
+
+| Status | UUID |
+|--------|------|
+| Backlog | |
+| Todo | |
+| In Progress | |
+| In Review | |
+| Done | |
+| Canceled | |
+
+## Label UUIDs
+
+<!-- Map issues to the specialist agent responsible.
+     Labels must be created in the tracker UI first, then UUIDs copied here. -->
+
+| Label | Agent | UUID |
+|-------|-------|------|
+| `nextjs` | Developer | _TBD_ |
+| `ui` | UI/UX Expert | _TBD_ |
+| `testing` | Testing Expert | _TBD_ |
+| `docs` | Documentation Writer | _TBD_ |
+| `devops` | DevOps Expert | _TBD_ |
+| `data` | Data Expert | _TBD_ |
+| `security` | Security Expert | _TBD_ |
+| `performance` | Performance Expert | _TBD_ |
+| `architecture` | Architect | _TBD_ |
+| `bug` | _(any)_ | _TBD_ |
+| `follow-up` | _(any)_ | _TBD_ |

package/src/orchestrator/customizations/project.instructions.md

@@ -0,0 +1,64 @@
+```instructions
+# Project Context
+
+<!-- This file is populated by the `bootstrap-customizations` prompt.
+     Run that prompt to auto-discover your project's structure, tech stack, and configuration. -->
+
+## Overview
+
+<!-- Project name, description, and current status -->
+
+## System Architecture
+
+<!-- Architecture diagram showing apps, shared libraries, and external services -->
+
+## Tech Stack
+
+<!-- Table of technologies with versions and notes -->
+
+| Layer | Technology | Version | Notes |
+|-------|-----------|---------|-------|
+| | | | |
+
+## Project Structure
+
+<!-- Table of directories and their purpose -->
+
+| Path | Purpose |
+|------|---------|
+| | |
+
+## Apps & Deployment
+
+<!-- Table of apps with production URLs and dev ports -->
+
+| App | Production URL | Dev Port |
+|-----|---------------|----------|
+| | | |
+
+## Key Commands
+
+<!-- Package manager and common development commands -->
+
+## Routes
+
+<!-- Application routes and their descriptions -->
+
+## Key Documentation
+
+<!-- Links to important docs files -->
+
+| Document | Description |
+|----------|-------------|
+| | |
+
+## Domain Quick Reference
+
+<!-- Maps domains to skills and key file paths -->
+
+| Domain | Skill | Key Paths |
+|--------|-------|-----------|
+| | | |
+
+<!-- End of Project Context -->
+```

package/src/orchestrator/customizations/stack/api-config.md

@@ -0,0 +1,37 @@
+# API Configuration
+
+<!-- Populated by the `bootstrap-customizations` prompt based on detected API routes and Server Actions. -->
+
+Project-specific API inventory referenced by the `api-patterns` skill.
+
+## API Endpoints
+
+<!-- List all API route handlers with HTTP method, purpose, and auth requirements. -->
+
+| Endpoint | Method | Purpose | Auth |
+|----------|--------|---------|------|
+| | | | |
+
+## Server Actions
+
+<!-- List Server Actions with their file locations and purpose. -->
+
+| Action | Purpose |
+|--------|---------|
+| | |
+
+## Security Layers
+
+<!-- Describe the security middleware chain (WAF, proxy, rate limiting, etc.) -->
+
+## External APIs
+
+<!-- List third-party APIs used by the project. -->
+
+| API | Purpose | Used In |
+|-----|---------|---------|
+| | | |
+
+## Key Files
+
+<!-- List key files related to API routes, middleware, and search. -->

package/src/orchestrator/customizations/stack/cms-config.md

@@ -0,0 +1,26 @@
+# CMS Configuration
+
+<!-- Populated by the `bootstrap-customizations` prompt based on detected CMS.
+     Rename this file to match your CMS: sanity-config.md, contentful-config.md, strapi-config.md, etc. -->
+
+Project-specific CMS details referenced by the corresponding CMS skill (e.g., `sanity-cms`).
+
+## Configuration
+
+<!-- CMS project IDs, dataset, API version, studio location, etc. -->
+
+## Plugins
+
+<!-- List CMS plugins and their purpose. -->
+
+## Schema / Document Types
+
+<!-- List document types with key fields and references to full schema docs. -->
+
+## Query Examples
+
+<!-- Provide representative query examples for the CMS query language (GROQ, GraphQL, etc.) -->
+
+## Key Files
+
+<!-- List key CMS config, schema, and query files. -->

package/src/orchestrator/customizations/stack/data-pipeline-config.md

@@ -0,0 +1,41 @@
+# Data Pipeline Configuration
+
+<!-- Populated by the `bootstrap-customizations` prompt based on detected ETL/scraping infrastructure. -->
+
+Project-specific pipeline details referenced by the `data-engineering` skill.
+
+## Pipeline Architecture
+
+<!-- Describe the pipeline stages from data source to final destination. -->
+
+## Library Structure
+
+<!-- Map the data pipeline directory tree with file purposes. -->
+
+## Target Sources
+
+<!-- List data sources with URLs, data types, and status. -->
+
+| Source | URL | Data Type | Status |
+|--------|-----|-----------|--------|
+| | | | |
+
+## Data Model
+
+<!-- Reference the canonical data model documentation. -->
+
+## CLI Commands
+
+<!-- List CLI commands for running pipeline stages. -->
+
+```bash
+# Example commands — replace with your project's actual commands
+```
+
+## Key Documentation
+
+<!-- List key documentation files related to the data pipeline. -->
+
+| File | Content |
+|------|---------|
+| | |

package/src/orchestrator/customizations/stack/database-config.md

@@ -0,0 +1,44 @@
+# Database Configuration
+
+<!-- Populated by the `bootstrap-customizations` prompt based on detected database.
+     Rename this file to match your provider: supabase-config.md, prisma-config.md, drizzle-config.md, etc. -->
+
+Project-specific database details referenced by the corresponding database skill (e.g., `supabase-database`).
+
+## Integration
+
+<!-- Auth library path, migration directory, session pattern, role system overview. -->
+
+## Database Schema
+
+### Core Tables
+
+<!-- List tables with their purpose and RLS status. -->
+
+| Table | Purpose | RLS |
+|-------|---------|-----|
+| | | |
+
+### Role System
+
+<!-- Describe roles and their permissions. -->
+
+| Role | Permissions |
+|------|------------|
+| | |
+
+### Migration History
+
+<!-- List migrations in chronological order. -->
+
+```
+001_initial_schema.sql    — Description
+```
+
+### Auth Flow
+
+<!-- Describe the authentication flow step by step. -->
+
+## Key Files
+
+<!-- List key database, auth, and migration files. -->

package/src/orchestrator/customizations/stack/deployment-config.md

@@ -0,0 +1,45 @@
+# Deployment Configuration
+
+<!-- Populated by the `bootstrap-customizations` prompt based on detected deployment config. -->
+
+Project-specific deployment infrastructure referenced by the `deployment-infrastructure` skill.
+
+## Architecture
+
+<!-- Describe the deployment platform, CI/CD pipeline, and trigger mechanism. -->
+
+## Apps & URLs
+
+<!-- Reference the Apps & Deployment table in `project.instructions.md` for production URLs and dev ports. -->
+
+## Cron Jobs
+
+<!-- List scheduled jobs with their schedule, purpose, and auth mechanism. -->
+
+| Cron | Schedule | Purpose | Auth |
+|------|----------|---------|------|
+| | | | |
+
+## Environment Variables
+
+<!-- List environment variable names (NEVER values) with their purpose and which apps need them. -->
+
+| Variable | Purpose | Required For |
+|----------|---------|--------------|
+| | | |
+
+## Caching Headers
+
+<!-- Define cache-control headers for different content types. -->
+
+| Source Pattern | Cache-Control |
+|----------------|---------------|
+| | |
+
+## Security Headers
+
+<!-- Reference the security-hardening skill for full header inventory and CSP configuration. -->
+
+## Key Files
+
+<!-- List key deployment config files. -->

package/src/orchestrator/customizations/stack/testing-config.md

@@ -0,0 +1,56 @@
+# Testing Configuration
+
+<!-- Populated by the `bootstrap-customizations` prompt based on detected test infrastructure. -->
+
+Project-specific testing details referenced by the `browser-testing` skill.
+
+## Primary Test App
+
+<!-- Specify which app to use for E2E testing and how to build/start it. -->
+
+- **App:** _(app name)_ (port XXXX)
+- **Pre-test build:** _(build command)_
+- **Start server:** _(serve command)_
+
+## Data Test IDs
+
+<!-- List `data-testid` selectors used across the project for E2E testing. -->
+
+| Selector | Element |
+|----------|---------|
+| | |
+
+## Breakpoints
+
+<!-- Define responsive breakpoints for UI testing. -->
+
+| Breakpoint | Width | CSS prefix | Test viewport |
+|-----------|-------|------------|---------------|
+| Mobile | | (default) | |
+| Tablet | | | |
+| Desktop | | | |
+
+## E2E Test Suites
+
+<!-- List E2E test suite files and their focus areas. -->
+
+| Suite | Focus |
+|-------|-------|
+| | |
+
+## Reporting Format
+
+```markdown
+## Browser Test: [Feature Name]
+**Date:** [Date] | **App:** [app] (localhost:XXXX)
+
+| Test | Status | Notes |
+|------|--------|-------|
+| Page loads | ✅ PASS | |
+| Interaction works | ⚠️ ISSUE | Description |
+| Edge case handled | ✅ PASS | |
+```
+
+## Test Results Log
+
+<!-- Specify where to log test results. -->

package/src/orchestrator/instructions/ai-optimization.instructions.md

@@ -0,0 +1,143 @@
+---
+description: 'AI assistant optimization techniques for efficient context usage and faster responses'
+applyTo: '**'
+---
+
+# AI Assistant Optimization Instructions
+
+## Batch Processing
+
+### DO: Batch Independent Operations
+
+When gathering context, batch all read operations together in a single parallel call:
+
+```
+Good: Read 3 files + search in parallel → 1 cache-friendly turn
+Bad: Read file 1 → Read file 2 → Read file 3 → 3 separate turns
+```
+
+When modifying multiple independent files, batch the edits:
+
+```
+Good: Update 5 config files in parallel
+Bad: Update config 1 → wait → Update config 2 → wait...
+```
+
+### DON'T: Batch Dependent Operations
+
+Don't batch operations where one depends on the output of another:
+
+```
+Bad: Read file + Edit file (need to read first)
+Good: Read file → Analyze → Edit file
+```
+
+## Context Gathering Workflow
+
+Gather all necessary context upfront before analysis/implementation:
+
+```
+Phase 1 (parallel): Read files + search for patterns + check errors
+Phase 2: Analyze and plan
+Phase 3 (parallel if independent): Create/modify files
+Phase 4: Verify (tests, errors, lint)
+```
+
+## Token Reduction Techniques
+
+### Strategic Tool Selection
+
+- Use `grep_search` with `includePattern` to scope searches to specific directories
+- Use `file_search` to find files by pattern before reading
+- Use `semantic_search` for exploring unfamiliar code instead of multiple grep searches
+- Read targeted line ranges when you know approximately where code is
+
+### Avoid Redundant Operations
+
+- Don't re-read files already in context from the same conversation turn
+- Check errors once per phase, not after every single change
+- Don't search for what's already mentioned in context
+- Use regex with alternation (e.g., `word1|word2|word3`) to combine searches
+
+### Read Strategically
+
+- Read larger sections (500-2000 lines) instead of many small reads
+- Use `grep_search` to locate code, then read targeted ranges around it
+- Deduplicate file paths before batching read operations
+
+## Multi-Agent Optimization
+
+### Sub-Agent Context Isolation
+
+Sub-agents run in isolated context windows. Use this to your advantage:
+
+- **Offload exploration** — fire a sub-agent to research a broad question; only the concise result comes back, keeping your primary context clean
+- **Parallel research** — launch multiple sub-agents simultaneously for independent research tasks (e.g., "find all GROQ queries" + "list all components using X" at the same time)
+- **Detailed prompts save tokens** — a specific sub-agent prompt avoids the sub-agent doing its own exploratory searches, which would waste its context budget
+
+### Trust Sub-Agent Results
+
+- Don't re-read files a sub-agent just analyzed — trust the returned summary
+- Don't re-search for patterns a sub-agent already identified
+- If a sub-agent returns file paths or code snippets, use them directly
+
+### Background Agents for Long Work
+
+- Delegate tasks expected to take >5 minutes to background agents — they run in parallel without blocking
+- Include **all necessary context** in the delegation prompt (background agents can't ask follow-up questions)
+- Batch independent background delegations together (e.g., launch DB migration + UI components + docs simultaneously)
+
+### Delegation Prompt Efficiency
+
+- Include exact file paths so the delegated agent doesn't waste time searching
+- Reference existing patterns ("follow the structure in `libs/ui-kit/src/lib/Button/`") instead of describing patterns from scratch
+- Set clear scope boundaries ("only modify files under `libs/queries/`") to prevent unnecessary exploration
+
+## Response Optimization
+
+- Provide brief progress updates after batched operations
+- Describe changes concisely instead of repeating large code blocks
+- Plan what context is needed before making tool calls
+- Combine multiple related edits in planning before executing
+
+## Planning Thresholds
+
+Scale planning effort to task complexity — don't over-plan simple work:
+
+| Complexity | Planning | Approach |
+|-----------|----------|----------|
+| Trivial (1-2 files, clear fix) | None | Act directly |
+| Small (3-5 files, single concern) | Mental plan | Brief reasoning, then act |
+| Medium (5-10 files, multiple concerns) | Todo list | Track steps, batch reads |
+| Large (10+ files, cross-cutting) | Full decomposition | Dependency graph, phased execution |
+
+**Stop-and-re-plan trigger:** See the Task Decomposition Protocol in `general.instructions.md` (step 5).
+
+## Test & Build Output Efficiency
+
+- Capture full test/build output **once** per verification phase, not after each micro-change
+- Pipe verbose output through `tail -n 30` or `grep -E 'FAIL|ERROR|PASS'` to reduce noise
+- When tests fail, read the **relevant failure block** — don't re-run the entire suite repeatedly
+
+## README Cascade Reading
+
+When entering an unfamiliar directory, check for a `README.md` before exploring files. READMEs provide architecture context that prevents wasted searches. Priority order:
+1. Project root `README.md` (already covered by instruction files)
+2. Library/app-level `README.md` (e.g., `libs/queries/README.md`)
+3. Feature-level `README.md` (e.g., `libs/data-pipeline/src/lib/scrapers/README.md`)
+
+## Anti-Patterns to Avoid
+
+1. **Micro-reads** — Reading tiny file sections repeatedly
+2. **Sequential searches** — Running searches one at a time when they're independent
+3. **Premature actions** — Acting before gathering sufficient context
+4. **Silent processing** — Batching without progress updates
+5. **Exploratory tool calls** — Making tool calls without a clear plan
+6. **Over-checking** — Validating after every tiny change instead of batching
+7. **Re-gathering delegated context** — Re-reading files or re-searching after a sub-agent already returned the information
+8. **Vague delegation prompts** — Forcing sub-agents to waste their context budget on discovery you already completed
+9. **Sequential delegation** — Running independent sub-agents one-by-one when they could run in parallel
+10. **Leaking secrets** — Printing tokens, keys, or passwords in terminal output or logs (violates Constitution #1)
+11. **Over-planning** — Writing a full decomposition for a 2-file fix (see Planning Thresholds)
+
+<!-- End of AI Optimization Instructions -->