tower/agentic-data-engineering
Hook Claude Code
Runs before the agent uses a tool for Bash and mcp__tower-mcp__tower_run_local tool calls, executing block-secret-leaks.sh, block-direct-execution.sh and suggest-debug-mode.sh via bash (3 commands). From tower/agentic-data-engineering.
tower/agentic-data-engineering
Hook Claude Code
Runs after a tool call finishes for mcp__tower-mcp__tower_run_local tool calls, executing log-pipeline-run.sh via bash. From tower/agentic-data-engineering.
tower/agentic-data-engineering
Hook Claude Code
Runs when a tool call fails for mcp__tower-mcp__tower_run_local tool calls, executing log-pipeline-run.sh via bash. From tower/agentic-data-engineering.
tower/agentic-data-engineering
Settings file Claude Code
Agent settings declaring 3 hook events (PreToolUse, PostToolUse, PostToolUseFailure) and 26 allowed tools.
tower/agentic-data-engineering
Skill Claude CodeCodex
Create a dlt REST API pipeline to run as a Tower app. Use for the restapi core source, or any generic REST/HTTP API source. Not for sqldatabase or filesystem sources.
tower/agentic-data-engineering
Skill Claude CodeCodex
Explore and profile loaded data from a data consumer perspective. Scores 5 dimensions (completeness, freshness, consistency, queryability, discoverability). Absorbs validate-data. Modes — PROFILE (automated after load), VALIDATE (cross-reference against source), EXPLORE (interactive queries). Routes issues to…
tower/agentic-data-engineering
Skill Claude CodeCodex
Debug and inspect a Tower app after running it. Supports dlt pipelines, ASGI apps, and plain Python scripts. Use after a run (success or failure) to inspect logs, diagnose errors, and fix issues.
tower/agentic-data-engineering
Skill Claude CodeCodex
Find a dlt destination for a given storage provider. Use when the user asks about a destination, wants to find a connector, or asks to implement a pipeline for a specific data destination.
tower/agentic-data-engineering
Skill Claude CodeCodex
Find a dlt source for a given API or data provider. Use when the user asks about a source, wants to find a connector, or asks to implement a pipeline for a specific data source.
tower/agentic-data-engineering
Skill Claude CodeCodex
Detect existing project stack, learn conventions from code, and produce a project profile. Run before other skills to give them richer context, or let skills invoke it automatically when no profile exists.
tower/agentic-data-engineering
Skill Claude CodeCodex
Create a Tower app — either a hello-world scaffold (greenfield) or a wrapper around existing Python pipeline code.
tower/agentic-data-engineering
Skill Claude CodeCodex
Review data app requirements from a business analyst perspective. Auto-detects intent — SCOPE CHECK (30s) for high-intent users, DISCOVERY (5min, 6 scored dimensions) for low-intent. Gates entry into pipeline development. Use before find-source or when adding endpoints.
tower/agentic-data-engineering
Skill Claude CodeCodex
Review data model design for schema quality, dimensional modeling, and dbt best practices. Scores 6 dimensions (key integrity, normalization, naming, type correctness, join readiness, evolution safety). Modes — PRE-LOAD (config review), POST-LOAD (materialized schema), MODEL (dbt dimensional modeling). Use when schema…
tower/agentic-data-engineering
Skill Claude CodeCodex
Review a Tower data app for reliability and production readiness. Scores 5 gradient dimensions (incremental strategy, error resilience, resource efficiency, observability, test coverage) + 6 pass/fail checks. Modes — DEV REVIEW (read-only), PROD READINESS (makes changes, absorbs adjust-endpoint), INCIDENT (root…
tower/agentic-data-engineering
Skill Claude CodeCodex
Pre-deploy operational review for a Tower data app. Scores 4 dimensions (schedule appropriateness, failure recovery, cost awareness, monitoring) + 3 pass/fail checks (Towerfile resources, schedule configured, runbook). Single mode — PRE-DEPLOY. Use before towerdeploy.
tower/agentic-data-engineering
Skill Claude CodeCodex
Review credential handling, data sensitivity, and access control for a Tower data app. 5 pass/fail checks + 2 scored dimensions (PII awareness, secret rotation readiness). Modes — AUDIT (before first deploy), INCIDENT (credential compromise response). Use before towerdeploy or when credential issues arise.
tower/agentic-data-engineering
Skill Claude CodeCodex
Safely manage secrets as runtime environment variables. Use when the user directly asks to set up, configure, or inspect credentials (API keys, database passwords, tokens). Do NOT use when in need for reading secrets, for pipeline creation, source discovery, or debugging pipeline execution — those skills call…
tower/agentic-data-engineering
MCP server Claude CodeCodexCursor +2
MCP server "tower-mcp", hosted remotely at 127.0.0.1, as configured in tower/agentic-data-engineering.
tower/agentic-data-engineering
Instructions file CodexOpenCode
AGENTS.md instructions for tower/agentic-data-engineering, covering tower data apps, app types in scope, tower ecosystem rules, running apps and python environment.
Settings file Claude Code
Agent settings declaring 9 allowed tools.
Instructions file CodexOpenCode
AGENTS.md instructions for tower/agent-skills, covering agent skills for tower, repository layout, skill conventions, design principles for data skills and making changes.
Instructions file
Claude Code instructions for tower/agent-skills: See @AGENTS.md for repository conventions.
Skill Claude CodeCodex
Query and analyze data in a Tower-managed Apache Iceberg lakehouse using the Tower CLI's built-in read-only SQL query command (tower catalogs query), and record what you learn about the data with tower catalogs knowledge. Use this skill whenever the user asks a question about their company or business data (revenue…
Skill Claude CodeCodex
Build a verified ontology for a Tower-managed Apache Iceberg lakehouse — profile every table, prove the grain and join keys with SQL, and record the entity model as catalog knowledge with tower catalogs knowledge. Use this skill when a catalog has no recorded knowledge, when the user asks to document, map, model…