safety

DE//AGENT currently lists 7 resources under safety: 3 hooks, 1 tutorial, 1 skill. 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: 1 agent, 1 pattern.

Documented learning objectives across these resources:

• Scope a backfill by date and by dependency — via Backfill Planner
• Detect which downstream tables must also be rebuilt — via Backfill Planner
• Stage a backfill gradually with validation between batches — via Backfill Planner
• Write correctness criteria for a backfill before running it — via Plan and execute a safe backfill
• Compute the downstream impact set from lineage — via Plan and execute a safe backfill
• Execute the backfill in batches with validation gates and a rollback path — via Plan and execute a safe backfill

These resources map to stages: Orchestration (5), Reliability (2). 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.

How scores are computed: source quality score.

Highest composite score first:

1. Backfill Planner score 39.5 — advanced
2. Safe Backfill score 34.75 — advanced
3. Plan and execute a safe backfill score 34.15 — intermediate

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

Start here if you're new: Destructive SQL Guard, Production Write Confirmation.

Reach for these with production experience: Backfill Planner, Safe Backfill, Backfill Safety Check.

Security-flagged entries: Backfill Planner (1 flag), Backfill Planner (3 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 tiny table you can recompute in one safe step (Safe Backfill)

• Backfill Planner — Produces a backfill plan: date ranges, blast radius, resource contention, idempotency check, validation gates and rollback. details
• Plan and execute a safe backfill — Use the Backfill Planner's four-step plan — correctness criteria, downstream impact from lineage, cost and contention, staged batches — then execute it the way the backfill runbook… details
• Destructive SQL Guard — Intercept DROP / TRUNCATE / DELETE-without-WHERE before an agent executes it. details
• Production Write Confirmation — Force human confirmation for any write against a production data target. details

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

npx de-agent-platform add backfill-planner

Backfill Planner — review first

Adjacent topics: backfill (5 shared), hook (3 shared), planning (3 shared), orchestration (2 shared), guardrail (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.