| name | plan-slicing |
| description | Use when broad work needs to be broken into small verifiable slices. |
plan-slicing
Lifecycle stage: PLAN
Trigger
Use after a brief/design is accepted and before build.
When not to use
Do not use when this trigger is absent; choose the command or skill that owns the requested state, artifact, and verification gate.
Inputs
- User request or current artifact.
- Known constraints and context.
- Relevant evidence or source links, if available.
- Current Agent Brain state.
Procedure
- State the current state and target artifact.
- Identify missing blockers and ask at most three blocking questions.
- Separate facts, assumptions, hypotheses, and open questions.
- Split broad work into vertical slices small enough to verify independently.
- For each slice, name the user-visible outcome, files likely touched, acceptance checks, and verification command.
- Apply the anti-rationalization table below.
- Produce the required artifact: Implementation Plan.
- Add evidence, risks, decision, and next state.
Anti-Rationalization
| Shortcut | Rebuttal |
|---|
| "This is obvious." | Write the assumption and evidence. If you cannot, it is not obvious. |
| "We can do this later." | If the missing step changes the decision, do it now or state the risk. |
| "The user wants speed." | Reduce scope; do not skip the quality bar. |
| "This does not need verification." | Every important claim or behavior needs proof. |
Verification
- Required artifact exists and is named.
