review

DE//AGENT currently lists 21 resources under review: 13 tutorials, 3 skills, 2 plugins. Everything below is derived from the live registry — counts, capabilities, verification state and security posture come from the curated records, never from marketing copy.

Also present: 2 agents, 1 pattern.

Documented learning objectives across these resources:

• State a model's grain and match it to its unique key test — via dbt Model Review
• Choose table vs incremental vs view deliberately — via dbt Model Review
• Handle late data in an incremental model — via dbt Model Review
• Read a tool schema and predict its side effects — via MCP Tool Contract Auditor
• Classify tools by blast radius — via MCP Tool Contract Auditor
• Write a least-privilege MCP configuration — via MCP Tool Contract Auditor
• Prove a join cannot fan out before writing it — via SQL Review
• Spot NULL-unsafe `NOT IN` and `=` predicates — via SQL Review

34 more objectives live on the individual resource pages.

These resources map to stages: Agentic Data Engineering (6), Orchestration (2), Cloud (2), Python + SQL (5), Warehousing (4), Data Quality (1), System Design (1). Follow the four-phase roadmap to place this topic inside a progression instead of learning it in isolation.

Every entry, its shape and its trust state — sorted by the registry's composite score. This table is the honest version of a marketing comparison: no sponsored placements, no unverifiable claims.

9 more in the full list below.

How scores are computed: source quality score.

Highest composite score first:

1. dbt Model Review score 40.5 — intermediate
2. MCP Tool Contract Auditor score 40.5 — advanced
3. SQL Review score 39.9 — beginner

Scores rank provenance, completeness and trust — read how verification works before adopting anything.

Start here if you're new: SQL Review, SQL Reviewer, Keep an agent read-only until a human approves, Review a DAG for idempotency and retry safety.

Reach for these with production experience: MCP Tool Contract Auditor, Capstone checklist — a design is done when these all hold.

Security-flagged entries: dbt Model Review (1 flag), MCP Tool Contract Auditor (1 flag), SQL Review (1 flag), SQL Reviewer (1 flag), DE Data Toolkit (2 flags), Pipeline Reviewer (1 flag), dbt Workbench (4 flags). Flags mean the record declares capabilities like credential use or write access — read the security posture on each page before connecting.

Known limits: A purely local sandbox with no real data (Agent-in-the-Loop Review)

• dbt Model Review — Checks a dbt model's grain statement, ref/dependency hygiene, incremental strategy and late-arriving-data handling, then proposes a test set. details
• MCP Tool Contract Auditor — Inspects an MCP server's tool list and schemas, flags tools that can write, delete, spend money or exfiltrate data, and produces a least-privilege connection recommendation. details
• SQL Review — Reviews a SQL statement for fan-out joins, NULL-unsafe predicates, implicit casts, non-deterministic ordering, and functions that silently change grain. details
• Agent-in-the-Loop Review — Coding agents can do real data-engineering work, but can also ship a schema change or drop a table. details

Real install commands from the registry — read the source before running any of them:

npx de-agent-platform add dbt-model-review

dbt Model Review — review first

npx de-agent-platform add mcp-tool-contract-auditor

MCP Tool Contract Auditor — review first

npx de-agent-platform add sql-review

SQL Review — review first

amp plugin add de-agent/de-data-toolkit

DE Data Toolkit — review first

Adjacent topics: tutorial (13 shared), plugin (4 shared), guardrails (4 shared), beginner (3 shared), agentic (3 shared), security (3 shared).

Study path: the roadmap places this topic in a progression · the scoring model explains the numbers · the trust rule catalog shows every security check these entries passed through.