next-slice

name	next-slice
description	Continue working through a project plan. Finds the next actionable slice and implements every task in it.
disable-model-invocation	true

Next Slice

Resume work from a project plan, in the main thread, one whole slice per invocation.

Context

• Project plans: !find docs/plans -maxdepth 1 -name '*.md' ! -name 'README.md' -newer docs/plans/completed 2>/dev/null | head -10 || find docs/plans -maxdepth 1 -name '*.md' ! -name 'README.md' 2>/dev/null | head -10
• Task lists: !find docs/tasks -maxdepth 1 -name '*.md' ! -name 'README.md' 2>/dev/null | head -10

Process

1. Identify the plan or task list. Use the user's file if specified; otherwise pick from the context above. If multiple candidates exist, present them as a numbered list with filenames and ask which to use. Always state the file you'll use and wait for confirmation.

   I'll work from docs/plans/cross-team-routing-isolation.md.
   OK, or did you have a different plan in mind?
   

2. Read the file and find the first actionable slice (a ### Slice N: heading with at least one unchecked task - [ ]) in document order. A slice is actionable unless its - **Blocked by**: line names a slice that still has unchecked tasks — skip a blocked slice and keep scanning. Plans without Blocked by (older phase-based plans) never block, so the first slice with an unchecked task wins. A flat task list with no ### Slice headings is treated as a single slice — take all its actionable unchecked tasks. If every remaining slice is blocked, report which slice is next and what it waits on, then stop.