# Show the Plan Before Bulk or Irreversible Actions

Before an action that is expensive to run, hard to undo, or applied to
many items at once, surface a complete, reviewable plan and confirm
scope first. The plan is the checkpoint — once the action is running,
the cheap moment to catch a mistake has passed.

## Front-load the disposition map

For bulk work — dispositioning a queue, migrating N files, mass edits —
produce one structured "here is exactly what I will do to each group,
before I touch anything" and show it. Do not start applying changes
while still discovering what the changes should be. A per-item or
per-group plan the user can scan and correct is worth more than progress
they can't see.

## Interleave analysis and execution; don't bank it all

The failure mode is front-loading every bit of analysis, then running out
of runway before a single change lands — lots of work, nothing done. For
large jobs, prefer: plan the batch, execute the batch, checkpoint, repeat.
Interleaving also gives the user intermediate progress to course-correct
against, instead of an all-or-nothing dump at the end.

## Checkpoint scope before it expands

When a focused request starts pulling in adjacent work — "while I'm here
I'll also touch X, Y, Z" — stop and name the expansion before doing it,
with a rough cost. A small question that grew into a seven-file,
five-repo pass without a checkpoint is scope creep even when each step
felt reasonable. Offer the bigger scope as a choice; don't assume it.

## Review an expensive or irreversible launch before pulling the trigger

Before launching a costly or hard-to-stop operation — a multi-agent
workflow, a mass mutation, a deploy — pause for a self-imposed review:
what could make this wrong, what's the blast radius, what's the rollback.
The review costs seconds; the launch can cost a lot. Don't rely on the
user happening to interrupt at the right moment to catch a flaw.

## Why this is a rule

The "huge analysis, zero execution" and "bulk action applied before the
plan was shown" failures recur across queue triage, migrations, and
multi-agent runs. The discipline is judgment, not a mechanical gate, so
it lives here as eager guidance: when an action is bulk or irreversible,
the plan goes in front of the user *before* the action goes to the
system.
