opencastle 0.6.0 → 0.8.0

package/src/orchestrator/agent-workflows/schema-changes.md

@@ -1,10 +1,10 @@
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Workflow: Schema / CMS Changes
 
 Structured workflow for CMS schema modifications, query updates, and content model changes.
 
-> **Project config:** For CMS-specific paths, schema locations, and query library details, see the relevant CMS customization file (e.g., `sanity-config.md`).
+> **Project config:** For CMS-specific paths, schema locations, and query library details, see the relevant CMS customization file in `customizations/stack/`.
 
 ## Phases
 
@@ -37,14 +37,14 @@ Follow the **Delivery Outcome** in `general.instructions.md` and the **Branch Ow
 3. Check the query library (see CMS customization) for queries that will be affected
 4. Verify schema changes don't conflict with existing content in the CMS
 5. Document field mapping (new vs existing fields)
-6. Create Linear issue with schema change details
+6. Create tracker issue with schema change details
 
 ### Exit Criteria
 
 - [ ] Existing schema understood
 - [ ] Impact on data queries assessed
 - [ ] Impact on existing content assessed
-- [ ] Linear issue created
+- [ ] Tracker issue created
 - [ ] Approach decided (new type vs modify existing)
 
 ---
@@ -146,7 +146,7 @@ Follow the **Delivery Outcome** in `general.instructions.md` and the **Branch Ow
 3. Start dev server and verify pages render correctly
 4. Check both apps if shared schema/queries changed
 5. Verify data model documentation is updated
-6. Move Linear issue to Done
+6. Move tracker issue to Done
 
 ### Exit Criteria
 
@@ -154,8 +154,8 @@ Follow the **Delivery Outcome** in `general.instructions.md` and the **Branch Ow
 - [ ] Pages render correctly in browser
 - [ ] Both apps verified (if shared code changed)
 - [ ] Data model documentation updated (if applicable)
-- [ ] Linear issue moved to Done
-- [ ] Delivery Outcome completed (see `general.instructions.md`) — branch pushed, PR opened (not merged), Linear linked
+- [ ] Tracker issue moved to Done
+- [ ] Delivery Outcome completed (see `general.instructions.md`) — branch pushed, PR opened (not merged), tracker linked
 
 ---
 
@@ -163,4 +163,4 @@ Follow the **Delivery Outcome** in `general.instructions.md` and the **Branch Ow
 
 > **See [shared-delivery-phase.md](shared-delivery-phase.md) for the standard delivery steps.**
 >
-> Commit → Push → PR → Linear linkage. Team Lead owns delivery.
+> Commit → Push → PR → tracker linkage. Team Lead owns delivery.

package/src/orchestrator/agent-workflows/security-audit.md

@@ -1,4 +1,4 @@
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Workflow: Security Audit
 
@@ -31,19 +31,19 @@ Follow the **Delivery Outcome** in `general.instructions.md` and the **Branch Ow
 ### Steps
 
 1. Define audit scope (full audit vs. targeted area)
-2. Read `docs/PROJECT.md` security sections
-3. Read `docs/KNOWN-ISSUES.md` for existing security items
+2. Read `.github/customizations/project.instructions.md` security sections
+3. Read `.github/customizations/KNOWN-ISSUES.md` for existing security items
 4. Check current CSP configuration in `next.config.js`
 5. Review auth flow (see database/auth customization for library paths)
 6. Map all API routes and Server Actions
-7. Create Linear issue for the audit
+7. Create tracker issue for the audit
 
 ### Exit Criteria
 
 - [ ] Scope defined (which apps, libs, routes)
 - [ ] Existing security docs reviewed
 - [ ] Attack surface mapped
-- [ ] Linear issue created
+- [ ] Tracker issue created
 
 ---
 
@@ -114,7 +114,7 @@ Follow the **Delivery Outcome** in `general.instructions.md` and the **Branch Ow
 ### Exit Criteria
 
 - [ ] Panel completed (PASS or BLOCK)
-- [ ] Panel report linked to Linear issue
+- [ ] Panel report linked to tracker issue
 - [ ] If BLOCK: MUST-FIX items extracted
 
 ---
@@ -127,19 +127,19 @@ Follow the **Delivery Outcome** in `general.instructions.md` and the **Branch Ow
 ### Steps
 
 1. Fix Critical and High severity findings first
-2. Create separate Linear issues for Medium/Low findings if not fixing now
+2. Create separate tracker issues for Medium/Low findings if not fixing now
 3. Run verification after each fix
 4. Re-run panel review if initial panel BLOCKed
-5. Update `docs/KNOWN-ISSUES.md` for any accepted risks
+5. Update `.github/customizations/KNOWN-ISSUES.md` for any accepted risks
 
 ### Exit Criteria
 
 - [ ] Critical/High findings remediated
-- [ ] Medium/Low findings tracked in Linear
+- [ ] Medium/Low findings tracked in tracker
 - [ ] Panel review passed (if applicable)
 - [ ] Known issues updated for accepted risks
-- [ ] All Linear issues updated
-- [ ] Delivery Outcome completed (see `general.instructions.md`) — branch pushed, PR opened (not merged), Linear linked
+- [ ] All tracker issues updated
+- [ ] Delivery Outcome completed (see `general.instructions.md`) — branch pushed, PR opened (not merged), tracker linked
 
 ---
 
@@ -147,4 +147,4 @@ Follow the **Delivery Outcome** in `general.instructions.md` and the **Branch Ow
 
 > **See [shared-delivery-phase.md](shared-delivery-phase.md) for the standard delivery steps.**
 >
-> Commit → Push → PR → Linear linkage. Team Lead owns delivery.
+> Commit → Push → PR → tracker linkage. Team Lead owns delivery.

package/src/orchestrator/agent-workflows/shared-delivery-phase.md

@@ -1,4 +1,4 @@
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Shared Delivery Phase
 
@@ -6,14 +6,14 @@ This phase is referenced by all workflow templates. It covers the final delivery
 
 ## Steps
 
-1. **Commit all changes** to the feature branch with Linear issue IDs in commit messages
+1. **Commit all changes** to the feature branch with tracker issue IDs in commit messages
 2. **Push the branch** to origin: `git push -u origin <branch-name>`
 3. **Open a PR** using `gh` CLI (always use `GH_PAGER=cat` to prevent pager issues):
    ```bash
    GH_PAGER=cat gh pr create --base main --title "TAS-XX: Short description" --body "Resolves TAS-XX"
    ```
 4. **Do NOT merge** — PRs are opened for human review only
-5. **Update Linear issues** with the PR URL for traceability
+5. **Update tracker issues** with the PR URL for traceability
 6. **Clean up session checkpoint** if one exists
 
 ## Branch & Delivery Strategy
@@ -28,8 +28,8 @@ The **Team Lead owns delivery**, not individual specialist agents:
 
 ## Exit Criteria
 
-- [ ] All changes committed with Linear issue IDs in messages
+- [ ] All changes committed with tracker issue IDs in messages
 - [ ] Branch pushed to origin
 - [ ] PR opened on GitHub (NOT merged)
-- [ ] Linear issues updated with PR URL
+- [ ] Tracker issues updated with PR URL
 - [ ] All project issues marked Done or Cancelled

package/src/orchestrator/agents/api-designer.agent.md

@@ -5,7 +5,7 @@ model: Gemini 3.1 Pro (Preview)
 tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # API Designer
 

package/src/orchestrator/agents/architect.agent.md

@@ -2,10 +2,10 @@
 description: 'Software architect for strategic architecture decisions, roadmap planning, ADRs, system design, and technology evaluation.'
 name: 'Architect'
 model: Claude Opus 4.6
-tools: ['search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'search', 'search/usages', 'execute/runInTerminal', 'execute/getTerminalOutput', 'read/terminalLastCommand', 'nx-mcp-server/nx_workspace', 'nx-mcp-server/nx_project_details', 'nx-mcp-server/nx_visualize_graph']
+tools: ['search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'search', 'search/usages', 'execute/runInTerminal', 'execute/getTerminalOutput', 'read/terminalLastCommand']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Software Architect
 

package/src/orchestrator/agents/content-engineer.agent.md

@@ -2,10 +2,10 @@
 description: 'Content engineer for CMS schema design, content queries, content modeling, releases, and studio customization.'
 name: 'Content Engineer'
 model: Gemini 3.1 Pro (Preview)
-tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages', 'sanity/get_schema', 'sanity/get_sanity_rules', 'sanity/list_sanity_rules', 'sanity/query_documents', 'sanity/get_document', 'sanity/create_documents_from_json', 'sanity/create_documents_from_markdown', 'sanity/patch_document_from_json', 'sanity/patch_document_from_markdown', 'sanity/deploy_schema', 'sanity/publish_documents', 'sanity/unpublish_documents', 'sanity/discard_drafts', 'sanity/list_projects', 'sanity/list_datasets', 'sanity/list_workspace_schemas', 'sanity/list_embeddings_indices', 'sanity/search_docs', 'sanity/read_docs', 'sanity/semantic_search', 'sanity/migration_guide', 'sanity/create_version', 'sanity/generate_image', 'sanity/transform_image', 'sanity/add_cors_origin']
+tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Content Engineer
 
@@ -42,7 +42,7 @@ Resolve via [skill-matrix.md](.github/customizations/agents/skill-matrix.md).
 
 ## Out of Scope
 
-- Building React components that render CMS content
+- Building UI components that render CMS content
 - Creating database migrations for data that mirrors CMS content
 - Writing E2E tests for pages that consume CMS data
 - Deploying frontend applications

package/src/orchestrator/agents/copywriter.agent.md

@@ -2,10 +2,10 @@
 description: 'Copywriter for UI microcopy, marketing text, email templates, venue descriptions, error messages, and all user-facing text.'
 name: 'Copywriter'
 model: GPT-5 mini
-tools: ['search/codebase', 'edit/editFiles', 'web/fetch', 'search', 'read/problems', 'search/usages', 'sanity/get_schema', 'sanity/query_documents', 'sanity/get_document', 'sanity/patch_document_from_json', 'sanity/patch_document_from_markdown', 'sanity/list_datasets', 'sanity/list_projects', 'resend/send-email']
+tools: ['search/codebase', 'edit/editFiles', 'web/fetch', 'search', 'read/problems', 'search/usages']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Copywriter
 

package/src/orchestrator/agents/data-expert.agent.md

@@ -1,11 +1,11 @@
 ---
-description: 'Data engineering expert for ETL pipelines, web scrapers (Puppeteer), data processors, CLI tools, and CMS data import.'
+description: 'Data engineering expert for ETL pipelines, web crowlers, data processors, CLI tools, and CMS data import.'
 name: 'Data Expert'
 model: GPT-5.3-Codex
-tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages', 'sanity/get_schema', 'sanity/query_documents', 'sanity/create_documents_from_json', 'sanity/patch_document_from_json', 'sanity/get_document', 'sanity/list_datasets', 'sanity/list_projects']
+tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Data Expert
 
@@ -32,7 +32,7 @@ Resolve via [skill-matrix.md](.github/customizations/agents/skill-matrix.md).
 - Idempotent imports with `createOrReplace` and deterministic `_id`
 - Validate with Zod before importing — never import invalid data
 - Respect `robots.txt` and rate limit all scraping requests
-- Use Puppeteer Cluster for concurrent scraping
+- Use the project's web crawling library for concurrent crowling (see the **data-pipeline** skill)
 - Handle errors gracefully — skip bad records, don't halt pipeline
 - Preserve UTF-8 encoding for special characters and diacritics
 - Backup before bulk operations
@@ -48,9 +48,9 @@ Resolve via [skill-matrix.md](.github/customizations/agents/skill-matrix.md).
 
 ## Out of Scope
 
-- Modifying Sanity schemas (report needed changes to Team Lead)
+- Modifying CMS schemas (report needed changes to Team Lead)
 - Building UI components that consume the imported data
-- Creating Supabase migrations or RLS policies
+- Creating database migrations or RLS policies
 - Deploying scrapers to production infrastructure
 
 ## Output Contract

package/src/orchestrator/agents/database-engineer.agent.md

@@ -2,10 +2,10 @@
 description: 'Database engineer for schema design, migrations, security policies, performance optimization, and auth integration.'
 name: 'Database Engineer'
 model: Gemini 3.1 Pro (Preview)
-tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages', 'supabase/apply_migration', 'supabase/execute_sql', 'supabase/list_tables', 'supabase/list_migrations', 'supabase/list_extensions', 'supabase/get_logs', 'supabase/get_project', 'supabase/get_project_url', 'supabase/list_projects', 'supabase/search_docs', 'supabase/generate_typescript_types', 'supabase/get_advisors', 'supabase/create_branch', 'supabase/list_branches']
+tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Database Engineer
 
@@ -47,7 +47,7 @@ Resolve via [skill-matrix.md](.github/customizations/agents/skill-matrix.md).
 ## Out of Scope
 
 - Building API routes or Server Actions that use the new schema
-- Creating React components for data display
+- Creating UI components for data display
 - CMS schema changes
 - Deploying migrations to production (only development/preview)
 

package/src/orchestrator/agents/developer.agent.md

@@ -2,10 +2,10 @@
 description: 'Full-stack developer for building pages, components, routing, layouts, API routes, server-side logic, and feature implementation.'
 name: 'Developer'
 model: Gemini 3.1 Pro (Preview)
-tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'vscode/getProjectSetupInfo', 'vscode/installExtension', 'vscode/newWorkspace', 'vscode/runCommand', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages', 'nx-mcp-server/nx_project_details', 'nx-mcp-server/nx_workspace', 'nx-mcp-server/nx_generators']
+tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'vscode/getProjectSetupInfo', 'vscode/installExtension', 'vscode/newWorkspace', 'vscode/runCommand', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Developer
 
@@ -44,7 +44,7 @@ After code changes, always run lint, test, and build for affected projects. The
 
 ## Done When
 
-- All acceptance criteria from the Linear issue are met
+- All acceptance criteria from the tracker issue are met
 - Lint, test, and build pass for the affected project(s)
 - Changed files stay within the assigned file partition
 - TypeScript compiler reports zero errors in modified files
@@ -62,7 +62,7 @@ When completing a task, return a structured summary:
 
 1. **Files Changed** — List every file created or modified with a one-line description
 2. **Verification Results** — Lint, test, and build output (pass/fail + error count)
-3. **Acceptance Criteria Status** — Checklist from the Linear issue, each item marked ✅ or ❌
+3. **Acceptance Criteria Status** — Checklist from the tracker issue, each item marked ✅ or ❌
 4. **Assumptions Made** — Decisions you made that weren't explicitly specified
 
 See **Base Output Contract** in `general.instructions.md` for the standard closing items (Discovered Issues + Lessons Applied).

package/src/orchestrator/agents/devops-expert.agent.md

@@ -1,15 +1,15 @@
 ---
-description: "DevOps expert for Vercel deployments, CI/CD integration, cron jobs, security headers, caching, environment variables, and build optimization."
+description: "DevOps expert for deployments, CI/CD integration, cron jobs, security headers, caching, environment variables, and build optimization."
 name: "DevOps Expert"
 model: GPT-5.3-Codex
-tools: ["search/changes", "search/codebase", "edit/editFiles", "web/fetch", "vscode/getProjectSetupInfo", "vscode/installExtension", "vscode/newWorkspace", "vscode/runCommand", "read/problems", "execute/getTerminalOutput", "execute/runInTerminal", "read/terminalLastCommand", "read/terminalSelection", "search", "execute/testFailure", "search/usages", "vercel/deploy_to_vercel", "vercel/get_deployment", "vercel/get_deployment_build_logs", "vercel/get_project", "vercel/get_runtime_logs", "vercel/list_deployments", "vercel/list_projects", "vercel/list_teams", "vercel/search_vercel_documentation", "vercel/check_domain_availability_and_price", "nx-mcp-server/nx_project_details", "nx-mcp-server/nx_workspace", "nx-mcp-server/nx_workspace_path"]
+tools: ["search/changes", "search/codebase", "edit/editFiles", "web/fetch", "vscode/getProjectSetupInfo", "vscode/installExtension", "vscode/newWorkspace", "vscode/runCommand", "read/problems", "execute/getTerminalOutput", "execute/runInTerminal", "read/terminalLastCommand", "read/terminalSelection", "search", "execute/testFailure", "search/usages"]
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # DevOps Expert
 
-You are a DevOps expert specializing in Vercel deployments, CI/CD pipelines, cron jobs, security headers, caching strategies, and build optimization.
+You are a DevOps expert specializing in deployments, CI/CD pipelines, cron jobs, security headers, caching strategies, and build optimization.
 
 ## Critical Rules
 
@@ -43,7 +43,7 @@ Resolve via [skill-matrix.md](.github/customizations/agents/skill-matrix.md).
 
 - Writing application code or business logic
 - Creating database migrations or RLS policies
-- Designing Sanity schemas or GROQ queries
+- Designing CMS schemas or content queries
 - Writing tests beyond build verification
 
 ## Output Contract

package/src/orchestrator/agents/documentation-writer.agent.md

@@ -5,7 +5,7 @@ model: GPT-5 mini
 tools: ['search/codebase', 'edit/editFiles', 'web/fetch', 'search', 'read/problems']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Documentation Writer
 

package/src/orchestrator/agents/performance-expert.agent.md

@@ -2,10 +2,10 @@
 description: 'Performance optimization expert for frontend, backend, and build performance.'
 name: 'Performance Expert'
 model: Gemini 3.1 Pro (Preview)
-tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages', 'chrome-devtools/*', 'nx-mcp-server/nx_project_details', 'nx-mcp-server/nx_workspace']
+tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Performance Expert
 

package/src/orchestrator/agents/release-manager.agent.md

@@ -2,10 +2,10 @@
 description: 'Release manager for pre-release verification, changelog generation, version management, regression checks, and release coordination.'
 name: 'Release Manager'
 model: GPT-5.3-Codex
-tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages', 'vercel/get_deployment', 'vercel/get_deployment_build_logs', 'vercel/get_runtime_logs', 'vercel/list_deployments', 'vercel/list_projects', 'nx-mcp-server/nx_project_details', 'nx-mcp-server/nx_workspace', 'nx-mcp-server/nx_workspace_path', 'slack/*']
+tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'read/terminalSelection', 'search', 'execute/testFailure', 'search/usages']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Release Manager
 
@@ -38,8 +38,8 @@ Load the **deployment-infrastructure** skill for the detailed release process st
 
 ## Guidelines
 
-- Review Linear board for Done issues that should be in the release
-- Cross-reference merged PRs with Linear issues for completeness
+- Review tracker board for Done issues that should be in the release
+- Cross-reference merged PRs with tracker issues for completeness
 - Never skip the regression check — "it's a small change" is when things break
 - Keep changelogs audience-appropriate (users care about features, not refactors)
 - Coordinate with DevOps Expert for deployment-specific concerns

package/src/orchestrator/agents/researcher.agent.md

@@ -21,7 +21,7 @@ handoffs:
     prompt: 'Use the generate-task-spec prompt to create an opencastle.tasks.yml spec for autonomous overnight runs based on:'
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Researcher
 
@@ -87,7 +87,7 @@ Given a feature request, answer:
 Given a bug report, answer:
 - Where does the relevant code live? (entry points → data flow)
 - What does the git history show? (recent changes that might have caused it)
-- Are there related known issues in `docs/KNOWN-ISSUES.md`?
+- Are there related known issues in `.github/customizations/KNOWN-ISSUES.md`?
 - Are there related lessons in `.github/customizations/LESSONS-LEARNED.md`?
 - What test coverage exists for the affected area?
 
@@ -118,7 +118,7 @@ Given a file or module, answer:
 
 - Writing or editing code files
 - Running tests or builds
-- Creating Linear issues or updating the board
+- Creating tracker issues or updating the board
 - Making architectural decisions (present options, don't decide)
 
 ## Output Contract

package/src/orchestrator/agents/reviewer.agent.md

@@ -5,7 +5,7 @@ model: GPT-5 mini
 tools: [read/readFile, search/codebase, search/fileSearch, search/textSearch, search/listDirectory, read/problems]
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Reviewer
 

package/src/orchestrator/agents/security-expert.agent.md

@@ -2,14 +2,14 @@
 description: "Security expert for authentication, authorization, RLS policies, security headers, input validation, API security, and vulnerability management."
 name: "Security Expert"
 model: Claude Opus 4.6
-tools: ["search/changes", "search/codebase", "edit/editFiles", "web/fetch", "vscode/getProjectSetupInfo", "vscode/installExtension", "vscode/newWorkspace", "vscode/runCommand", "read/problems", "execute/getTerminalOutput", "execute/runInTerminal", "read/terminalLastCommand", "read/terminalSelection", "search", "execute/testFailure", "search/usages", "supabase/execute_sql", "supabase/list_tables", "supabase/get_advisors", "supabase/list_migrations", "supabase/get_project"]
+tools: ["search/changes", "search/codebase", "edit/editFiles", "web/fetch", "vscode/getProjectSetupInfo", "vscode/installExtension", "vscode/newWorkspace", "vscode/runCommand", "read/problems", "execute/getTerminalOutput", "execute/runInTerminal", "read/terminalLastCommand", "read/terminalSelection", "search", "execute/testFailure", "search/usages"]
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # Security Expert
 
-You are a security expert specializing in authentication, authorization, security headers, input validation, API security, and vulnerability management for Next.js applications with Supabase.
+You are a security expert specializing in authentication, authorization, security headers, input validation, API security, and vulnerability management. Resolve technology-specific details via the **security** and **database** capability slots in the skill matrix.
 
 ## Critical Rules
 
@@ -18,7 +18,7 @@ You are a security expert specializing in authentication, authorization, securit
 3. **Enable RLS on all tables** — default-deny, explicit-allow policies
 4. **Validate all inputs** — use Zod schemas before database operations
 5. **Sanitize user content** — escape HTML in user-generated content
-6. **Use parameterized queries** — Supabase client handles this automatically
+6. **Use parameterized queries** — use the database client's built-in parameterization
 7. **Rotate secrets regularly** — cron secrets, API keys, OAuth secrets
 
 ## Skills

package/src/orchestrator/agents/seo-specialist.agent.md

@@ -2,10 +2,10 @@
 description: 'SEO specialist for meta tags, structured data, sitemap strategy, Open Graph, search visibility, and crawlability audits.'
 name: 'SEO Specialist'
 model: GPT-5 mini
-tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'search', 'search/usages', 'chrome-devtools/*']
+tools: ['search/changes', 'search/codebase', 'edit/editFiles', 'web/fetch', 'read/problems', 'execute/getTerminalOutput', 'execute/runInTerminal', 'read/terminalLastCommand', 'search', 'search/usages']
 ---
 
-<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the customizations/ directory instead. -->
+<!-- ⚠️ This file is managed by OpenCastle. Edits will be overwritten on update. Customize in the .github/customizations/ directory instead. -->
 
 # SEO Specialist