plugin

DE//AGENT currently lists 16 resources under plugin: 10 plugins, 6 tutorials. Everything below is derived from the live registry — counts, capabilities, verification state and security posture come from the curated records, never from marketing copy.

Documented learning objectives across these resources:

• Attribute warehouse/cluster spend with /cost-by-pipeline — via Attribute spend with the Cost Lens plugin
• Compute unit economics with /unit-cost — via Attribute spend with the Cost Lens plugin
• Guard cost-per-run regressions with /cost-guard — via Attribute spend with the Cost Lens plugin
• Read a table-health report before planning maintenance — via Check lakehouse table health with Lakehouse Guard
• Generate a compaction plan instead of running compaction ad hoc — via Check lakehouse table health with Lakehouse Guard
• Understand when the guard blocks maintenance actions — via Check lakehouse table health with Lakehouse Guard
• Inventory topics with /topic-info before touching lag — via Debug a Kafka stream with the Kafka Console plugin
• Triage per-partition lag and rebalance detection with /lag-triage — via Debug a Kafka stream with the Kafka Console plugin

10 more objectives live on the individual resource pages.

These resources map to stages: Reliability (3), Lakehouse (2), Streaming (2), Agentic Data Engineering (2), Data Processing (2), Warehousing (3), Data Quality (1), Observability (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.

4 more in the full list below.

How scores are computed: source quality score.

Highest composite score first:

1. Runbook Runner score 35.6 — beginner
2. Attribute spend with the Cost Lens plugin score 34.15 — intermediate
3. Check lakehouse table health with Lakehouse Guard score 34.15 — intermediate

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

Start here if you're new: Runbook Runner, DE Data Toolkit.

Reach for these with production experience: Spark Lens, Kafka Console, Lakehouse Guard.

Security-flagged entries: Runbook Runner (1 flag), DE Data Toolkit (2 flags), Contract Kit (2 flags), Spark Lens (2 flags), Lineage Graph (3 flags), Warehouse Explorer (3 flags), Kafka Console (3 flags), Lakehouse Guard (3 flags), dbt Workbench (4 flags), Cost Lens (5 flags). Flags mean the record declares capabilities like credential use or write access — read the security posture on each page before connecting.

• Runbook Runner — Loads the production playbooks into the agent, matches an alert to a runbook, and walks the operator through diagnosis and mitigation step by step. details
• Attribute spend with the Cost Lens plugin — Install the Cost Lens plugin and use its three commands to attribute spend, compute unit economics, and guard cost-per-run. The plugin pairs the unit-economics skill with the Spark… details
• Check lakehouse table health with Lakehouse Guard — Use the Lakehouse Guard plugin's three commands on a Delta/Iceberg table: /table-health for a status read, /plan-compaction for a maintenance plan, and /expire-snapshots for a safe… details
• Debug a Kafka stream with the Kafka Console plugin — Drive the Kafka Console plugin's three commands across a lag incident: /topic-info for inventory, /lag-triage for per-partition lag and rebalance detection, and /sample-topic for a… details

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

amp plugin add de-agent/runbook-runner

Runbook Runner — review first

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

DE Data Toolkit — review first

amp plugin add de-agent/contract-kit

Contract Kit — review first

amp plugin add de-agent/spark-lens

Spark Lens — review first

Adjacent topics: tutorial (6 shared), cost (4 shared), review (4 shared), performance (2 shared), streaming (2 shared), testing (2 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.