← ClaudeAtlas

add-review-disciplinelisted

Use when a command dispatches a reviewer, a cold reader or the prompt reviewer over a document or a delivery — how many times each runs, why none of them writes a file, and the rule that a finding is judged before it is applied.
brabos-ai/code-addiction · ★ 8 · Code & Development · score 75
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