add-review-disciplinelisted
Install: claude install-skill brabos-ai/code-addiction
# Review Discipline
<!-- uses:
- agent: plan-review-agent
- agent: plan-readback-agent
- agent: prompt-review-agent
- mention: /add-framework--build
- mention: /add-framework--plan
- mention: /add-framework--brainstorm
- mention: add-plan-authoring
- mention: add-build-ledger
-->
Owns HOW review is dispatched in the internal layer: the counts, the fact that nothing reaches disk,
and what the caller owes a report it receives. WHAT each reader looks for belongs to that reader's own
definition.
Three commands dispatch under this skill: `/add-framework--build`, `/add-framework--plan` and
`/add-framework--brainstorm`. **The rule lives here and only here.** It used to be restated in each of
them, which is exactly how it survived in some and died in others.
## When to Use
- A command is about to dispatch `@plan-review-agent`, `@plan-readback-agent` or
`@prompt-review-agent`.
- A report has come back and the caller is deciding what to do with it.
## When NOT to Use
- Writing the plan document itself — that is `add-plan-authoring`.
- Executing F-blocks and recording rulings — that is `add-build-ledger`.
---
## The Readers, and the Question Each Answers
| Reader | Asks | Returns |
|---|---|---|
| `@plan-review-agent` | "Can this be executed? What breaks?" | A verdict and required fixes |
| `@plan-readback-agent` | "Would someone with a clean context build the right thing?" | A restatement and every gap it filled in |
| `@prompt-review-agent` | "Does this artefact say one th